English

Models

Models published by each vendor: context, modalities, reasoning levels and pricing. Prices are per million tokens unless another unit is shown.

Qwen-Image-2.1-Turboqwen-image-2.1-turboAlibabaImageimages———No— / $0.016 / image——Active2026-10-09—Claude Haiku 5.5claude-haiku-5-5AnthropicChatmessages · batch1M1M128Klow · medium · high · xhigh · max$0.1 / $0.5$0.01 / $0.125tools · structured_output · streaming · caching · batchActive2026-10-072026-06 Vidu Q4 Previewviduq4-previewShengshu ViduVideovideo———————Active2026-10-07—Nano Banana 2.1gemini-nano-banana-2.1GoogleChatimages · batch—131.1K32.8Kminimal · medium · high$1.5 / $30—batchActive2026-10-06—Mistral Large 4mistral-large-4Mistral AIChatchat · batch1.05M——none · high$1.36 / $4.18$0.14 / —tools · structured_output · caching · batchPreview2026-10-06—Pegasus 1.6pegasus1.6Twelve LabsChatgenerate261.1K—————structured_outputActive2026-10-06—Qwen-Image-2.1-Proqwen-image-2.1-proAlibabaImageimages———No— / $0.04 / image——Active2026-10-02—FLUX 3 Imageflux-3-imageBlack Forest LabsImageimages————— / $0.041 / image——Active2026-10-01—Embed v5.0 Fastembed-v5.0-fastCohereEmbeddingembeddings128K———$0.08 / ———Active2026-09-30—Embed v5.0 Proembed-v5.0-proCohereEmbeddingembeddings128K———$0.12 / ———Active2026-09-30—Document Parsedocument-parseUpstageChatocr————$0.01 / — / page——Active2026-09-30—Document OCRocrUpstageChatocr————$0.0015 / — / page——Active2026-09-30—Rerank 3rerank-3Voyage AIRerankrerank32K———$0.05 / ———Active2026-09-30—Rerank 3 Litererank-3-liteVoyage AIRerankrerank32K———$0.02 / ———Active2026-09-30—GPT-6.1 Solgpt-6.1-solOpenAIChatchat · responses · batch1.05M922K128Klow · medium · high · xhigh · max$2 / $10$0.1 / $2.5tools · structured_output · streaming · caching · batchActive2026-09-292026-04-30 Claude Sonnet 5.5claude-sonnet-5-5AnthropicChatmessages · batch1M1M128Klow · medium · high · xhigh · max$2 / $10$0.1 / $2.5tools · structured_output · streaming · caching · batchActive2026-09-282026-06 Eleven v4eleven_v4ElevenLabsAudioaudio————$80 / — / 1M characters——Active2026-09-28—Eleven v4 Turboeleven_v4_turboElevenLabsAudioaudio · realtime————$40 / — / 1M characters—streamingActive2026-09-28—LongCat-2.5-Previewlongcat-2.5-previewMeituanChatchat · messages1.05M—131.1KYes——streamingPreview2026-09-25—Claude Opus 5.5claude-opus-5-5AnthropicChatmessages · batch1M1M128Klow · medium · high · xhigh · max$4 / $20$0.2 / $5tools · structured_output · streaming · caching · batchActive2026-09-222026-06 Gemini 3.8 Flash-Lite TTSgemini-3.8-flash-lite-ttsGoogleAudioaudio · batch—8.2K16.4KNo$0.5 / $6—batchActive2026-09-22—Gemini 3.8 Flash TTSgemini-3.8-flash-ttsGoogleAudioaudio · batch—8.2K16.4KNo$0.5 / $9—batchActive2026-09-22—GPT-6 Lunagpt-6-lunaOpenAIChatchat · responses · batch1.05M922K128Knone · low · medium · high · xhigh · max$0.1 / $0.5$0.01 / $0.125tools · structured_output · streaming · caching · batchActive2026-09-222026-05-18 GPT-6 Solgpt-6-solOpenAIChatchat · responses · batch1.05M922K128Knone · low · medium · high · xhigh · max$2 / $10$0.2 / $2.5tools · structured_output · streaming · caching · batchActive2026-09-222026-04-20 Solar Mini 4solar-mini4UpstageChatchat———none · minimal · low · medium · high · xhigh · max$0.1 / $0.4$0.01 / —tools · structured_output · streamingActive2026-09-222026-02 MiMo-V2.6-Flashmimo-v2.6-flashXiaomiChatchat · messages · batch1.05M—131.1KYes¥1 / ¥2¥0.02 / —tools · structured_output · streaming · caching · batchActive2026-09-22—MiMo-V2.6-Promimo-v2.6-proXiaomiChatchat · messages · batch1.05M—131.1KYes¥3 / ¥6¥0.025 / —tools · structured_output · streaming · caching · batchActive2026-09-22—MiMo-V2.6-Pro-UltraSpeedmimo-v2.6-pro-ultraspeedXiaomiChatchat · messages1.05M—131.1KYes¥30 / ¥60¥0.25 / —tools · structured_output · streaming · cachingActive2026-09-22—Qwen3.8-Omni-Flash-Realtimeqwen3.8-omni-flash-realtimeAlibabaChatrealtime—196.6K65.5KNo——tools · streamingActive2026-09-21—Grok 4.7grok-4.7xAIChatchat · responses500K——low · medium · high · xhigh$2 / $6$0.5 / —tools · structured_output · cachingActive2026-09-212026-05 Qwen-Audio-3.1-Realtime-Plusqwen-audio-3.1-realtime-plusAlibabaChatrealtime262.1K245.8K16.4KNo——tools · streamingActive2026-09-20—HappyOyster-1.0-Actinghappyoyster-1.0-actingAlibabaVideovideo———No———Active2026-09-17—HappyOyster-1.0-Adventurehappyoyster-1.0-adventureAlibabaVideovideo———No———Active2026-09-17—HappyOyster-1.0-Directinghappyoyster-1.0-directingAlibabaVideovideo———No———Active2026-09-17—Qwen3.8-Omni-Flashqwen3.8-omni-flashAlibabaChatchat · responses1M991.8K131.1KYes$0.15 / $0.47$0.016 / —tools · streaming · cachingActive2026-09-17—Ink 2ink-2CartesiaChataudio · realtime———————Active2026-09-17—Nova-3 Pharmanova-3-pharmaDeepgramChataudio———————Active2026-09-17—Antigravity Preview 09-2026antigravity-preview-09-2026GoogleChatresponses1.05M1.05M65.5K———tools · streamingPreview2026-09-17—Linden 1linden-1SpeechmaticsChatrealtime————$0.3 / — / hour——Active2026-09-17—Grok Voice Transcribe 2.0grok-voice-transcribe-2.0xAIChataudio————$0.1 / — / hour—streamingActive2026-09-17—Gemini 3.8 Livegemini-3.8-liveGoogleChatrealtime—131.1K65.5KYes——toolsActive2026-09-15—Gemini 3.8 Live Extended Thinkinggemini-3.8-live-extended-thinkingGoogleChatrealtime—131.1K65.5Klow · medium · high——toolsActive2026-09-15—Jina OCR v1jina-ocr-v1Jina AIChatocr32.8K———$0.5 / $2——Active2026-09-14—Intern-S2intern-s2Shanghai AI LabChatchat · messages262.1K——Yes——tools · streamingActive2026-09-13—Scribe v2 Medicalscribe_v2_medicalElevenLabsChataudio————$0.22 / — / hour——Active2026-09-11—Nemotron Parse 2.0nemotron-parse-2.0NVIDIAChatocr———————Active2026-09-11—DeepSeek-V4.1-Flashdeepseek-flashDeepSeekChatchat · messages1.05M—393.2Klow · high · max$0.3 / $1.2$0.006 / —tools · structured_output · streaming · cachingActive2026-09-10—GPT-Live 1gpt-live-1OpenAIChatrealtime————$0.05 / — / minute—tools · streamingActive2026-09-102025-07-31 North Small Translate 1.0north-small-translate-1-0CohereChatchat16K—16K————Active2026-09-09—Mercury 2.5mercury-2.5Inception LabsChatchat260K—65.5Kinstant · low · medium · high$0.2 / $0.75$0.02 / —tools · structured_output · streamingActive2026-09-08—GPT-Image-2.5 Flaregpt-image-2.5-flareOpenAIImageimages · batch————$5 / $30$1.25 / —batchActive2026-09-08—GPT-Image-2.5 Sunburstgpt-image-2.5-sunburstOpenAIImageimages · batch————$5 / $30$1.25 / —batchActive2026-09-08—Spark X2.5spark-x2.5iFlytekChatchat262.1K——————Active2026-09-06—Ling-3.0-flash-VLling-3.0-flash-vlAnt GroupChatchat · messages262.1K——Yes¥0.5 / ¥1.5¥0.1 / —tools · streamingActive2026-09-04—MAI-Image-2.6mai-image-2.6MicrosoftImageimages32K——————Preview2026-09-04—MAI-Image-2.6-Flashmai-image-2.6-flashMicrosoftImageimages32K——————Preview2026-09-04—Information Extractinformation-extractUpstageChatocr————$0.04 / — / page——Active2026-09-04—Lyria 3.5lyria-3.5GoogleChataudio—131.1K—No— / $0.08 / request——Active2026-09-03—MAI-Transcribe-2mai-transcribe-2MicrosoftChataudio———————Preview2026-09-03—GPT-6 Astragpt-6-astraOpenAIChatchat · responses · batch1.05M922K128Klow · medium · high · xhigh · max$10 / $50$1 / $12.5tools · structured_output · streaming · caching · batchActive2026-09-032026-04-30 Gemini 3.8 Flashgemini-3.8-flashGoogleChatgenerate · batch1.05M1.05M65.5Klow · medium · high$0.75 / $3.75$0.075 / —tools · structured_output · streaming · caching · batchActive2026-09-022026-03 Muse Spark 1.3muse-spark-1.3MetaChatchat · responses1.05M——minimal · low · medium · high · xhigh · max$1.25 / $4.25$0.15 / —tools · structured_output · streaming · cachingActive2026-09-02—Claude Fable 5.1claude-fable-5-1AnthropicChatmessages · batch1M1M128Klow · medium · high · xhigh · max$10 / $50$0.25 / $12.5tools · structured_output · streaming · caching · batchActive2026-09-012026-06 Muse Voice Transcribe 1.0muse-voice-transcribe-1.0MetaChataudio · realtime————$0.18 / — / hour—streamingActive2026-09-01—Spark X2.5-1.7Bspark-x2.5-1.7biFlytekChatchat1.05M———¥0 / ¥0——Active2026-08-31—Spark X2.5-4Bspark-x2.5-4biFlytekChatchat1.05M——————Active2026-08-31—Marengo 3.5marengo3.5Twelve LabsEmbeddingembeddings———————Active2026-08-31—Qwen-MT-Image-2.0qwen-mt-image-2.0AlibabaImageimages————— / $0.0006 / image——Active2026-08-28—Hy4 Previewhy4-previewTencentChatchat · messages1.05M983K65.5KYes¥6 / ¥18¥0.3 / —tools · structured_output · streaming · cachingPreview2026-08-28—Sonic 3.6sonic-3.6CartesiaAudioaudio———————Active2026-08-27—Parse v5.0parse-v5.0CohereChatocr8.2K———$0.0015 / — / page——Active2026-08-27—Gemini Omni Flashgemini-omni-1.1-flashGoogleVideovideo1.05M———$1.5 / $17.5——Active2026-08-27—Qwen3.8-Flashqwen3.8-flashAlibabaChatchat · messages1M991.8K131.1KYes$0.15 / $0.47$0.016 / $0.2tools · structured_output · streaming · cachingActive2026-08-26—Gemini 3.5 Transcribegemini-3.5-transcribeGoogleChataudio———No$2 / $12——Active2026-08-262025-01 Gemini 3.5 Transcribe Livegemini-3.5-transcribe-liveGoogleChatrealtime———No$3.5 / $21——Active2026-08-262025-01 GLM-5.3-Flashglm-5.3-flashZhipu AIChatchat1.05M—131.1KYes$0.15 / $0.5$0.03 / —tools · structured_output · streaming · cachingActive2026-08-26—Muse Image 1.0muse-image-1.0MetaImageimages · responses————— / $0.01 / image——Active2026-08-25—Wan3.0-Video-Primewan3.0-video-primeAlibabaVideovideo———No$0.068 / $0.068 / second——Active2026-08-20—Saaras v3 Realtimesaaras-v3-realtimeSarvam AIChatrealtime———————Active2026-08-18—Saaras v4saaras-v4Sarvam AIChataudio————INR 30 / — / hour——Active2026-08-18—GLM-5.3glm-5.3Zhipu AIChatchat · messages1.05M—131.1Klow · high · max$1.4 / $4.4$0.26 / —tools · structured_output · streaming · cachingActive2026-08-18—Qwen3.8-27Bqwen3.8-27bAlibabaChatchat · messages1M991.8K131.1KYes$0.5 / $3—tools · structured_output · streaming · cachingActive2026-08-17—DeepSeek-V4-Prodeepseek-v4-proDeepSeekChatchat · messages1.05M—393.2Klow · high · max$1.32 / $3.96$0.044 / —tools · structured_output · streaming · cachingActive2026-08-13—Gemini 3.7 Flashgemini-3.7-flashGoogleChatgenerate · batch1.05M1.05M65.5Klow · medium · high——tools · structured_output · streaming · caching · batchDeprecated2026-08-132026-03 Voyage Code 4voyage-code-4Voyage AIEmbeddingembeddings32K———$0.12 / ———Active2026-08-13—Palmyra X6palmyra-x6WriterChatchat1M—8.2K—$2 / $8—tools · streamingActive2026-08-13—Qwen3.8-2.4T-A95Bqwen3.8-2.4t-a95bAlibabaChatchat · messages1M991.8K131.1KYes$2 / $6—tools · structured_output · streaming · cachingActive2026-08-12—Grok 4.6grok-4.6xAIChatchat · responses500K——low · medium · high · xhigh$2 / $6$0.5 / —tools · structured_output · cachingActive2026-08-12—LTX-2.5 Fastltx-2-5-fastLightricks (LTX)Videovideo————— / $0.09 / second——Active2026-08-11—LTX-2.5 Proltx-2-5-proLightricks (LTX)Videovideo————— / $0.12 / second——Active2026-08-11—Nemotron 3.5 Lightning 30B A3Bnemotron-3.5-lightning-30b-a3bNVIDIAChatchat1.05M—32.8KYes——tools · structured_outputActive2026-08-11—Soniox tts-rt-v2tts-rt-v2SonioxAudioaudio · realtime————$4 / $21.5——Active2026-08-11—GPT-5.6 Cybergpt-5.6-cyberOpenAIChatresponses400K272K128KYes$12.5 / $75$1.25 / —tools · structured_output · streaming · cachingActive2026-08-072026-02-16 Wan3.0-Videowan3.0-videoAlibabaVideovideo———No$0.05 / $0.05 / second——Active2026-08-06—Solar Pro 4solar-pro4UpstageChatchat———none · minimal · low · medium · high · xhigh · max$0.3 / $1.2$0.06 / —tools · structured_output · streamingActive2026-08-062026-02 Muse Spark 1.2muse-spark-1.2MetaChatchat · responses1.05M——minimal · low · medium · high · xhigh$1.25 / $4.25$0.15 / —tools · structured_output · streaming · cachingActive2026-08-05—Qwen-Image-3.0qwen-image-3.0AlibabaImageimages———No$0.003 / $0.03 / image——Active2026-08-04—FLUX 3 Videoflux-3-videoBlack Forest LabsVideovideo————— / $0.17 / second——Preview2026-08-04—Qwen3.8-Maxqwen3.8-maxAlibabaChatchat · messages · responses1M991.8K131.1KYes$2 / $6$0.17 / $2.5tools · structured_output · streaming · caching · batchActive2026-08-03—Sakana Namazusakana-namazuSakana AIChatchat———Yes$0.95 / $4$0.15 / —toolsActive2026-08-03—Qwen3.7-Text-Embeddingqwen3.7-text-embeddingAlibabaEmbeddingembeddings131.1K131.1K—No———Active2026-07-31—MiniMax-H3minimax-h3MiniMaxVideovideo———No— / $0.08 / second——Active2026-07-31—Qwen-Audio-3.0-ASR-Flash-Streamingqwen-audio-3.0-asr-flash-streamingAlibabaChatrealtime———No$0.0001 / — / second——Active2026-07-30—Gemini Robotics-ER 2 Previewgemini-robotics-er-2-previewGoogleChatgenerate · batch131.1K131.1K65.5KYes$1 / $5$0.1 / —tools · structured_output · streaming · caching · batchPreview2026-07-30—Gemini Robotics-ER 2 Streaming Previewgemini-robotics-er-2-streaming-previewGoogleChatrealtime131.1K131.1K65.5KYes$1 / $5—tools · streamingPreview2026-07-30—Grok Voice Think Fast 2.0grok-voice-think-fast-2.0xAIChatrealtime——————toolsActive2026-07-29—GPT-Live-Transcribegpt-live-transcribeOpenAIChatrealtime————$0.017 / — / minute—streamingActive2026-07-28—GPT-Transcribegpt-transcribeOpenAIChataudio · realtime————$0.0045 / — / minute—streamingActive2026-07-28—Jina Reranker v3.5jina-reranker-v3.5Jina AIRerankrerank131.1K———$0.05 / ———Active2026-07-27—mxbai-rerank-v3.1-listwisemxbai-rerank-v3.1-listwiseMixedbreadRerankrerank———————Active2026-07-27—Riva Translate 4B Instruct v2riva-translate-4b-instruct-v2NVIDIAChatchat———————Active2026-07-27—Claude Opus 5claude-opus-5AnthropicChatmessages · batch1M1M128Klow · medium · high · xhigh · max$5 / $25$0.5 / $6.25tools · structured_output · streaming · caching · batchActive2026-07-242026-05 Ling-3.0-flashling-3.0-flashAnt GroupChatchat · messages262.1K——Yes¥0.5 / ¥1.5¥0.1 / —tools · streamingActive2026-07-23—MAI-Image-2.5-Promai-image-2.5-proMicrosoftImageimages32K——————Preview2026-07-23—Qwen3.7-Flashqwen3.7-flashAlibabaChatchat · messages1M991.8K131.1KYes$0.03 / $0.13$0.003 / $0.038tools · structured_output · streaming · cachingActive2026-07-21—Gemini 3.5 Flash-Litegemini-3.5-flash-liteGoogleChatgenerate · batch1.05M1.05M65.5KYes$0.3 / $2.5$0.03 / —tools · structured_output · streaming · caching · batchActive2026-07-212026-03 Gemini 3.6 Flashgemini-3.6-flashGoogleChatgenerate · batch1.05M1.05M65.5KYes$0.75 / $3.75$0.075 / —tools · structured_output · streaming · caching · batchActive2026-07-212026-03 Qwen-Image-3.0-Proqwen-image-3.0-proAlibabaImageimages———No$0.003 / $0.04 / image——Active2026-07-20—Ising Calibration 1.5 31Bising-calibration-1.5-31bNVIDIAChatchat262.1K——No———Preview2026-07-20—Mistral OCR 4.1mistral-ocr-4-1Mistral AIChatocr————$0.004 / — / page—batchActive2026-07-16—Kimi K3kimi-k3Moonshot AIChatchat · messages1.05M—1.05Mlow · high · max$3 / $15$0.3 / $3tools · structured_output · cachingActive2026-07-16—Nemotron 3 Embed 1Bnemotron-3-embed-1bNVIDIAEmbeddingembeddings32.8K——————Active2026-07-16—Qwen-Audio-3.0-Realtime-Flashqwen-audio-3.0-realtime-flashAlibabaChatrealtime41K16.4K8.2KNo——streamingActive2026-07-14—Qwen-Audio-3.0-Realtime-Plusqwen-audio-3.0-realtime-plusAlibabaChatrealtime———No——streamingActive2026-07-14—Qwen-Audio-3.0-TTS-Flashqwen-audio-3.0-tts-flashAlibabaAudioaudio———No$15 / — / 1M characters——Active2026-07-14—Qwen-Audio-3.0-TTS-Plusqwen-audio-3.0-tts-plusAlibabaAudioaudio———No$20 / — / 1M characters——Active2026-07-14—Muse Spark 1.1muse-spark-1.1MetaChatchat · responses1.05M——minimal · low · medium · high · xhigh$1.25 / $4.25$0.15 / —tools · structured_output · streaming · cachingActive2026-07-09—GPT-5.6 Lunagpt-5.6-lunaOpenAIChatchat · responses · batch1.05M922K128Knone · low · medium · high · xhigh · max$0.2 / $1.2$0.02 / $0.25tools · structured_output · streaming · caching · batchActive2026-07-092026-02-16 GPT-5.6 Solgpt-5.6-solOpenAIChatchat · responses · batch1.05M922K128Knone · low · medium · high · xhigh · max$4 / $20$0.4 / $5tools · structured_output · streaming · caching · batchActive2026-07-092026-02-16 GPT-5.6 Terragpt-5.6-terraOpenAIChatchat · responses · batch1.05M922K128Knone · low · medium · high · xhigh · max$2 / $12$0.2 / $2.5tools · structured_output · streaming · caching · batchActive2026-07-092026-02-16 Solar Open 2Retiredsolar-open2UpstageChatchat———Yes——tools · structured_outputRetired2026-07-08—Grok 4.5grok-4.5xAIChatchat · responses500K——low · medium · high · xhigh$2 / $6$0.3 / —tools · structured_output · cachingActive2026-07-08—Universal-3.5 Prouniversal-3-5-proAssemblyAIChataudio————$0.21 / — / hour——Active2026-07-07—Cohere Transcribe Arabiccohere-transcribe-arabic-07-2026CohereChataudio———————Active2026-07-07—GPT-Realtime-2.1gpt-realtime-2.1OpenAIChatrealtime128K—32KYes——tools · cachingActive2026-07-062024-09-30 GPT-Realtime-2.1 Minigpt-realtime-2.1-miniOpenAIChatrealtime128K—32KYes——tools · cachingActive2026-07-062024-09-30 Hy3hy3TencentChatchat · messages262.1K196.6K131.1KYes¥1 / ¥4¥0.25 / —tools · structured_output · streaming · cachingActive2026-07-06—Claude Sonnet 5claude-sonnet-5AnthropicChatmessages · batch1M1M128Klow · medium · high · xhigh · max$2 / $10$0.2 / $2.5tools · structured_output · streaming · caching · batchActive2026-06-302026-01 Nano Banana 2 Litegemini-3.1-flash-lite-imageGoogleChatimages · batch—65.5K4.1Kminimal · high$0.25 / $30—batchActive2026-06-302025-01 LongCat-2.0longcat-2.0MeituanChatchat · messages1.05M—131.1KYes——tools · streamingActive2026-06-30—Leanstral 1.5Retiredlabs-leanstral-1-5Mistral AIChatchat262.1K—131.1K———tools · structured_outputRetired2026-06-30—Solar Embedding 2 Passagesolar-embedding-2-passageUpstageEmbeddingembeddings————$0.02 / ———Active2026-06-30—Solar Embedding 2 Querysolar-embedding-2-queryUpstageEmbeddingembeddings————$0.02 / ———Active2026-06-30—Voyage Context 4voyage-context-4Voyage AIEmbeddingembeddings32K———$0.12 / ———Active2026-06-29—Doubao-Seed-2.1-Prodoubao-seed-2-1-proByteDanceChatchat · responses1.05M1.05M262.1Knone · minimal · low · medium · high · xhigh · max¥6 / ¥30¥1.2 / —tools · structured_output · streaming · caching · batchActive2026-06-23—Doubao-Seed-2.1-Turbodoubao-seed-2-1-turboByteDanceChatchat · responses262.1K262.1K262.1Knone · minimal · low · medium · high · xhigh · max¥3 / ¥15¥0.6 / —tools · structured_output · streaming · caching · batchActive2026-06-23—OCR 4.0Retiredmistral-ocr-4-0Mistral AIChatocr · batch——————batchRetired2026-06-23—PLaMo 3.0 Primeplamo-3.0-primePreferred NetworksChatchat262.1K—20.5Knone · mediumJPY 60 / JPY 250—tools · structured_output · streamingActive2026-06-22—Kling 3.0 Turbokling-3.0-turboKuaishouVideovideo————— / $0.112 / second——Active2026-06-17—Melia 1melia-1SpeechmaticsChataudio————$0.24 / — / hour——Active2026-06-17—HappyHorse-1.1-I2Vhappyhorse-1.1-i2vAlibabaVideovideo———No— / $0.07 / second——Active2026-06-16—HappyHorse-1.1-R2Vhappyhorse-1.1-r2vAlibabaVideovideo———No— / $0.07 / second——Active2026-06-16—HappyHorse-1.1-T2Vhappyhorse-1.1-t2vAlibabaVideovideo———No— / $0.07 / second——Active2026-06-16—Qwen3.5-OCRqwen3.5-ocrAlibabaChatchat · responses · ocr————¥0.5 / ¥2——Active2026-06-16—Soniox stt-rt-v5stt-rt-v5SonioxChatrealtime————$2 / $4——Active2026-06-16—Grok Imagine Video 1.5grok-imagine-video-1.5xAIVideovideo · batch————— / $0.08 / second—batchActive2026-06-16—GLM-5.2glm-5.2Zhipu AIChatchat1.05M—131.1KYes$1.4 / $4.4$0.26 / —tools · structured_output · streaming · cachingActive2026-06-16—Kimi K2.7 Codekimi-k2.7-codeMoonshot AIChatchat · messages262.1K——Yes$0.95 / $4$0.19 / —tools · cachingActive2026-06-12—Soniox stt-async-v5stt-async-v5SonioxChataudio————$1.5 / $3.5——Active2026-06-11—Claude Fable 5claude-fable-5AnthropicChatmessages · batch1M1M128Klow · medium · high · xhigh · max$10 / $50$1 / $12.5tools · structured_output · streaming · caching · batchActive2026-06-092026-01 North Mini Code 1.0north-mini-code-1-0CohereChatchat256K—64K————Active2026-06-09—Ray 3.2ray-3.2Luma AIVideovideo————— / $0.15 / request——Active2026-06-09—Nemotron 3 Ultra 550B A55Bnemotron-3-ultra-550b-a55bNVIDIAChatchat1.05M—32.8KYes——toolsActive2026-06-04—MAI-Image-2.5mai-image-2.5MicrosoftImageimages32K——————Preview2026-06-02—MAI-Image-2.5-Flashmai-image-2.5-flashMicrosoftImageimages32K———$1.75 / $19.5——Preview2026-06-02—MAI-Transcribe-1.5mai-transcribe-1.5MicrosoftChataudio———————Preview2026-06-02—Nemotron 3.5 Content Safetynemotron-3.5-content-safetyNVIDIAChatmoderation131.1K——————Active2026-06-02—Aleph 2.0aleph2RunwayVideovideo————— / $0.28 / second——Active2026-06-02—MiMo-V2.5-ASRmimo-v2.5-asrXiaomiChataudio8.2K—2KNo¥0.5 / — / hour—streamingActive2026-06-02—Qwen3.7-Plusqwen3.7-plusAlibabaChatchat · messages1M991.8K131.1KYes$0.4 / $1.6$0.04 / $0.5tools · structured_output · streaming · cachingActive2026-06-01—MiniMax-M3minimax-m3MiniMaxChatchat · messages1M—524.3KYes$0.3 / $1.2$0.06 / —tools · streaming · cachingActive2026-06-01—Step 3.7 Flashstep-3.7-flashStepFunChatchat · messages262.1K——low · medium · high$0.2 / $1.15$0.04 / —tools · streaming · cachingActive2026-05-29—Claude Opus 4.8claude-opus-4-8AnthropicChatmessages · batch1M1M128Klow · medium · high · xhigh · max$5 / $25$0.5 / $6.25tools · structured_output · streaming · caching · batchActive2026-05-282026-01 Nano Banana Progemini-3-pro-imageGoogleChatimages · batch—65.5K32.8KYes$2 / $120—batchActive2026-05-28—Nano Banana 2gemini-3.1-flash-imageGoogleChatimages · batch—131.1K32.8KYes$0.5 / $60—batchDeprecated2026-05-282025-01 Qwen-SEA-LION v4.5 27B ITqwen-sea-lion-v4.5-27b-itAI SingaporeChatchat262.1K—————toolsActive2026-05-20—Qwen3.7-Maxqwen3.7-maxAlibabaChatchat · messages1M991.8K131.1KYes$2.5 / $7.5$0.25 / $3.125tools · structured_output · streaming · cachingActive2026-05-20—Qwen3.7-Max-Previewqwen3.7-max-previewAlibabaChatchat1M991.8K131.1KYes$2.5 / $7.5—tools · structured_output · streamingActive2026-05-20—Command A+command-a-plus-05-2026CohereChatchat128K—64KYes$2.5 / $10—tools · structured_outputActive2026-05-202025-04 Stable Audio 3.0stable-audio-3Stability AIAudioaudio————— / $0.08 / request——Active2026-05-20—Gemini 3.5 Flashgemini-3.5-flashGoogleChatgenerate · batch1.05M1.05M65.5KYes——tools · structured_output · streaming · caching · batchDeprecated2026-05-19—Grok Build 0.1grok-build-0.1xAIChatchat · responses256K——Yes$1 / $2$0.2 / —tools · structured_output · cachingActive2026-05-19—Ring-2.6-1Tring-2.6-1tAnt GroupChatchat · messages262.1K——high · xhigh¥4.5 / ¥18¥0.9 / —tools · streamingActive2026-05-15—Intern-S2 Preview 35Bintern-s2-preview-35bShanghai AI LabChatchat262.1K——Yes——tools · streamingActive2026-05-15—ERNIE 5.1ernie-5.1BaiduChatchat · messages131.1K121.9K65.5K—¥4 / ¥18—streamingActive2026-05-09—Gemini 3.1 Flash-Litegemini-3.1-flash-liteGoogleChatgenerate · batch1.05M1.05M65.5KYes$0.25 / $1.5$0.025 / —tools · structured_output · streaming · caching · batchDeprecated2026-05-07—Jina Embeddings v5 Omni Nanojina-embeddings-v5-omni-nanoJina AIEmbeddingembeddings8.2K8.2K——$0.02 / ———Active2026-05-07—Jina Embeddings v5 Omni Smalljina-embeddings-v5-omni-smallJina AIEmbeddingembeddings32.8K32.8K——$0.05 / ———Active2026-05-07—GPT-Realtime-2gpt-realtime-2OpenAIChatrealtime128K—32KYes——tools · cachingActive2026-05-072024-09-30 GPT-Realtime-Translategpt-realtime-translateOpenAIChatrealtime16K—2K—$0.034 / — / minute—streamingActive2026-05-072024-09-30 GPT-Realtime-Whispergpt-realtime-whisperOpenAIChatrealtime16K—2K—$0.017 / — / minute—streamingActive2026-05-07—chat-latestchat-latestOpenAIChatchat · responses400K272K128K—$5 / $30$0.5 / —tools · structured_output · streaming · cachingActive2026-05-052025-08-31 Ling-2.6-1Tling-2.6-1tAnt GroupChatchat · messages262.1K———¥4.5 / ¥18¥0.9 / —tools · streamingActive2026-04-29—Mistral Medium 3.5mistral-medium-3-5Mistral AIChatchat · batch262.1K——none · high$1.5 / $7.5$0.15 / —tools · structured_output · caching · batchActive2026-04-28—Nemotron 3 Nano Omni 30B A3B Reasoningnemotron-3-nano-omni-30b-a3b-reasoningNVIDIAChatchat262.1K——Yes——toolsActive2026-04-28—HappyHorse-1.0-R2Vhappyhorse-1.0-r2vAlibabaVideovideo————— / $0.14 / second——Active2026-04-26—HappyHorse-1.0-Video-Edithappyhorse-1.0-video-editAlibabaVideovideo———No$0.14 / $0.14 / second——Active2026-04-26—GPT-5.5gpt-5.5OpenAIChatchat · responses · batch1.05M—128Knone · low · medium · high · xhigh$5 / $30$0.5 / —tools · structured_output · streaming · caching · batchActive2026-04-242025-12-01 GPT-5.5 Progpt-5.5-proOpenAIChatresponses · batch1.05M—128Kmedium · high · xhigh$30 / $180—tools · structured_output · batchActive2026-04-242025-12-01 Qwen-Image-2.0-Proqwen-image-2.0-proAlibabaImageimages———No— / $0.075 / image——Active2026-04-23—MiMo-V2.5mimo-v2.5XiaomiChatchat · messages1.05M—131.1KYes¥1 / ¥2¥0.02 / —tools · structured_output · streaming · cachingDeprecated2026-04-23—MiMo-V2.5-Promimo-v2.5-proXiaomiChatchat · messages1.05M—131.1KYes¥3 / ¥6¥0.025 / —tools · structured_output · streaming · cachingDeprecated2026-04-23—MiMo-V2.5-TTSmimo-v2.5-ttsXiaomiAudioaudio8.2K—8.2KNo——streamingActive2026-04-23—MiMo-V2.5-TTS-VoiceClonemimo-v2.5-tts-voicecloneXiaomiAudioaudio8.2K—8.2KNo——streamingActive2026-04-23—MiMo-V2.5-TTS-VoiceDesignmimo-v2.5-tts-voicedesignXiaomiAudioaudio8.2K—8.2KNo——streamingActive2026-04-23—HappyHorse-1.0-I2Vhappyhorse-1.0-i2vAlibabaVideovideo————— / $0.14 / second——Active2026-04-22—Qwen3.6-27Bqwen3.6-27bAlibabaChatchat · messages262.1K260.1K65.5KYes$0.6 / $3.6—tools · structured_output · streamingActive2026-04-22—Ling-2.6-flashling-2.6-flashAnt GroupChatchat · messages————¥0.6 / ¥1.8¥0.12 / —tools · streamingActive2026-04-22—Gemini Embedding 2gemini-embedding-2GoogleEmbeddingembeddings—8.2K—No$0.2 / ———Active2026-04-22—HappyHorse-1.0-T2Vhappyhorse-1.0-t2vAlibabaVideovideo———No— / $0.14 / second——Active2026-04-21—Gemini Deep Research Max Preview 04-2026deep-research-max-preview-04-2026GoogleChatresponses1.05M1.05M65.5K———streamingPreview2026-04-21—Gemini Deep Research Preview 04-2026deep-research-preview-04-2026GoogleChatresponses1.05M1.05M65.5K———streamingPreview2026-04-21—GPT-Image-2gpt-image-2OpenAIImageimages · batch————$5 / $30$1.25 / —batchActive2026-04-21—Kimi K2.6kimi-k2.6Moonshot AIChatchat · messages262.1K——Yes$0.95 / $4$0.16 / —tools · cachingActive2026-04-20—Pegasus 1.5pegasus1.5Twelve LabsChatgenerate261.1K—98.3K———structured_outputActive2026-04-20—Qwen3.6-35B-A3Bqwen3.6-35b-a3bAlibabaChatchat262.1K260.1K65.5KYes$0.375 / $2.25—tools · structured_output · streamingActive2026-04-16—Qwen3.6-Flashqwen3.6-flashAlibabaChatchat · messages1M991.8K65.5KYes$0.25 / $1.5$0.025 / $0.3125tools · structured_output · streaming · cachingActive2026-04-16—Claude Opus 4.7claude-opus-4-7AnthropicChatmessages · batch1M1M128Klow · medium · high · xhigh · max$5 / $25$0.5 / $6.25tools · structured_output · streaming · caching · batchActive2026-04-162026-01 Qwen3.6-Max-PreviewRetiredqwen3.6-max-previewAlibabaChatchat262.1K245.8K65.5KYes$1.3 / $7.8$0.13 / $1.625tools · structured_output · cachingRetired2026-04-14—Vidu Q3 Mixviduq3-mixShengshu ViduVideovideo———————Active2026-04-13—PixVerse C1c1PixVerseVideovideo———————Active2026-04-07—GLM-5.1glm-5.1Zhipu AIChatchat202.8K—131.1KYes$1.4 / $4.4$0.26 / —tools · structured_output · streaming · cachingActive2026-04-07—Wan2.7-I2Vwan2.7-i2vAlibabaVideovideo———No— / $0.1 / second——Active2026-04-03—Wan2.7-R2Vwan2.7-r2vAlibabaVideovideo————$0.1 / $0.1 / second——Active2026-04-03—Wan2.7-T2Vwan2.7-t2vAlibabaVideovideo———No— / $0.1 / second——Active2026-04-03—Wan2.7-VideoEditwan2.7-videoeditAlibabaVideovideo———No$0.1 / $0.1 / second——Active2026-04-03—Gemma 4 26B A4B ITgemma-4-26b-a4b-itGoogleChatgenerate262.1K——minimal · high——toolsActive2026-04-022025-01 Gemma 4 31B ITgemma-4-31b-itGoogleChatgenerate262.1K——minimal · high——toolsActive2026-04-022025-01 GLM-5V-Turboglm-5v-turboZhipu AIChatchat202.8K—131.1KYes¥5 / ¥22¥1.2 / —tools · streaming · cachingActive2026-04-02—Qwen3.6-Plusqwen3.6-plusAlibabaChatchat · messages1M991.8K65.5KYes$0.5 / $3$0.05 / $0.625tools · structured_output · streaming · cachingActive2026-04-01—Wan2.7-Imagewan2.7-imageAlibabaImageimages———No— / $0.03 / image——Active2026-04-01—Wan2.7-Image-Prowan2.7-image-proAlibabaImageimages———No— / $0.075 / image——Active2026-04-01—Veo 3.1 Lite Previewveo-3.1-lite-generate-previewGoogleVideovideo—1K—No— / $0.05 / second——Deprecated2026-03-31—Mercury Edit 2mercury-edit-2Inception LabsChatcompletions32K—8.2K—$0.25 / $0.75$0.025 / —streamingActive2026-03-30—PixVerse V6v6PixVerseVideovideo———————Active2026-03-29—Segment Anything Model 3.1sam-3.1MetaChatresponses——————streamingActive2026-03-27—Qwen3.5-Omni-Flashqwen3.5-omni-flashAlibabaChatchat262.1K196.6K65.5KNo——streamingActive2026-03-26—Qwen3.5-Omni-Flash-Realtimeqwen3.5-omni-flash-realtimeAlibabaChatrealtime262.1K196.6K65.5KNo——tools · streamingActive2026-03-26—Qwen3.5-Omni-Plusqwen3.5-omni-plusAlibabaChatchat262.1K196.6K65.5KNo——streamingActive2026-03-26—Qwen3.5-Omni-Plus-Realtimeqwen3.5-omni-plus-realtimeAlibabaChatrealtime262.1K196.6K65.5KNo——tools · streamingActive2026-03-26—Cohere Transcribecohere-transcribe-03-2026CohereChataudio———————Active2026-03-26—Lyria 3 Clip Previewlyria-3-clip-previewGoogleChataudio—131.1K—No— / $0.04 / request——Preview2026-03-25—Lyria 3 Pro Previewlyria-3-pro-previewGoogleChataudio—131.1K—No— / $0.08 / request——Preview2026-03-25—Voxtral TTSvoxtral-mini-tts-2603Mistral AIAudioaudio————$0 / $16 / 1M characters——Active2026-03-23—Solar Pro 3solar-pro3UpstageChatchat128K——none · minimal · low · medium · high · xhigh · max$0.15 / $0.6$0.015 / —tools · structured_output · streamingDeprecated2026-03-232025-07 MiniMax-M2.7minimax-m2.7MiniMaxChatchat · messages204.8K—204.8KYes$0.3 / $1.2$0.06 / $0.375tools · streaming · cachingActive2026-03-18—MiniMax-M2.7-highspeedminimax-m2.7-highspeedMiniMaxChatchat · messages204.8K—204.8KYes$0.6 / $2.4$0.06 / $0.375tools · streaming · cachingActive2026-03-18—GPT-5.4 Minigpt-5.4-miniOpenAIChatchat · responses · batch400K272K128Knone · low · medium · high · xhigh$0.75 / $4.5$0.075 / —tools · structured_output · streaming · caching · batchActive2026-03-172025-08-31 GPT-5.4 nanogpt-5.4-nanoOpenAIChatchat · responses · batch400K272K128Knone · low · medium · high · xhigh$0.2 / $1.25$0.02 / —tools · structured_output · streaming · caching · batchDeprecated2026-03-172025-08-31 SEA-LION ModernBERT Embedding 600Msea-lion-modernbert-embedding-600mAI SingaporeEmbeddingembeddings8.2K——————Active2026-03-16—LeanstralRetiredlabs-leanstral-2603Mistral AIChatchat262.1K—————tools · structured_outputRetired2026-03-16—Mistral Small 4mistral-small-2603Mistral AIChatchat · batch262.1K——none · high$0.15 / $0.6$0.015 / —tools · structured_output · caching · batchActive2026-03-16—GLM-5-Turboglm-5-turboZhipu AIChatchat202.8K—131.1KYes¥5 / ¥22¥1.2 / —tools · structured_output · streaming · cachingActive2026-03-15—Llama Nemotron Rerank VL 1B v2llama-nemotron-rerank-vl-1b-v2NVIDIARerankrerank———————Active2026-03-13—Gemini 3.1 Flash Live Previewgemini-3.1-flash-live-previewGoogleChatrealtime—131.1K65.5Kminimal · low · medium · high——toolsDeprecated2026-03-11—LongCat-Flash-Omni-2603Retiredlongcat-flash-omni-2603MeituanChatchat———————Retired2026-03-11—Nemotron 3 Super 120B A12Bnemotron-3-super-120b-a12bNVIDIAChatchat1.05M—32.8KYes——tools · structured_outputActive2026-03-11—Reka Edge 2603reka-edge-2603Reka AIChatchat16.4K—16.4KNo$0.1 / $0.1—tools · structured_output · streamingActive2026-03-11—Grok 4.20 (Non-Reasoning)grok-4.20-0309-non-reasoningxAIChatchat · responses · batch1M——No$1.25 / $2.5$0.2 / —tools · structured_output · caching · batchActive2026-03-10—Grok 4.20 (Reasoning)grok-4.20-0309-reasoningxAIChatchat · responses · batch1M——Yes$1.25 / $2.5$0.2 / —tools · structured_output · caching · batchActive2026-03-10—Grok 4.20 Multi-Agentgrok-4.20-multi-agent-0309xAIChatresponses · batch1M——Yes$1.25 / $2.5$0.2 / —structured_output · caching · batchActive2026-03-10—LTX-2.3 Fastltx-2-3-fastLightricks (LTX)Videovideo————— / $0.03 / second——Active2026-03-05—LTX-2.3 Proltx-2-3-proLightricks (LTX)Videovideo————— / $0.04 / second——Active2026-03-05—GPT-5.4gpt-5.4OpenAIChatchat · responses · batch1.05M—128Knone · low · medium · high · xhigh$2.5 / $15$0.25 / —tools · structured_output · streaming · caching · batchActive2026-03-052025-08-31 GPT-5.4 Progpt-5.4-proOpenAIChatresponses1.05M—128Kmedium · high · xhigh$30 / $180—tools · streamingActive2026-03-052025-08-31 Qwen-Image-2.0qwen-image-2.0AlibabaImageimages———No— / $0.035 / image——Active2026-03-03—Mistral Moderation 2mistral-moderation-2603Mistral AIChatmoderation131.1K—————batchActive2026-03-01—CosyVoice-V3.5-Flashcosyvoice-v3.5-flashAlibabaAudioaudio———No¥80 / — / 1M characters——Active2026-02-27—CosyVoice-V3.5-Pluscosyvoice-v3.5-plusAlibabaAudioaudio———No¥150 / — / 1M characters——Active2026-02-27—Gemini 3.1 Flash TTS Previewgemini-3.1-flash-tts-previewGoogleAudioaudio · batch—8.2K16.4KNo$1 / $20—batchDeprecated2026-02-26—pplx-embed-context-v1-0.6bpplx-embed-context-v1-0.6bPerplexityEmbeddingembeddings32.8K———$0.008 / ———Active2026-02-26—pplx-embed-context-v1-4bpplx-embed-context-v1-4bPerplexityEmbeddingembeddings32.8K———$0.05 / ———Active2026-02-26—pplx-embed-v1-0.6bpplx-embed-v1-0.6bPerplexityEmbeddingembeddings32.8K———$0.004 / ———Active2026-02-26—pplx-embed-v1-4bpplx-embed-v1-4bPerplexityEmbeddingembeddings32.8K———$0.03 / ———Active2026-02-26—Kling 3.0kling-v3KuaishouVideovideo · images———————Active2026-02-25—Kling 3.0 Omnikling-v3-omniKuaishouVideovideo · images———————Active2026-02-25—Mercury 2mercury-2Inception LabsChatchat128K—50Kinstant · low · medium · high$0.25 / $0.75$0.025 / —tools · structured_output · streamingActive2026-02-24—GPT-5.3-Codexgpt-5.3-codexOpenAIChatresponses400K272K128Klow · medium · high · xhigh$1.75 / $14$0.175 / —tools · structured_output · streaming · cachingDeprecated2026-02-242025-08-31 Qwen3.5-122B-A10Bqwen3.5-122b-a10bAlibabaChatchat · messages262.1K260.1K65.5KYes$0.4 / $3.2—tools · structured_output · streamingActive2026-02-23—Qwen3.5-27Bqwen3.5-27bAlibabaChatchat · messages262.1K260.1K65.5KYes$0.3 / $2.4—tools · structured_output · streamingActive2026-02-23—Qwen3.5-35B-A3Bqwen3.5-35b-a3bAlibabaChatchat · messages262.1K260.1K65.5KYes$0.25 / $2—tools · structured_output · streamingActive2026-02-23—Qwen3.5-Flashqwen3.5-flashAlibabaChatchat · messages1M991.8K65.5KYes$0.1 / $0.4$0.01 / $0.125tools · structured_output · streaming · cachingActive2026-02-23—GPT-Audio-1.5gpt-audio-1.5OpenAIChatchat128K—16.4K———tools · streamingActive2026-02-232024-09-30 GPT-Realtime-1.5gpt-realtime-1.5OpenAIChatrealtime32K—4.1K———tools · cachingActive2026-02-232024-09-30 Qwen3-Coder-NextRetiredqwen3-coder-nextAlibabaChatchat262.1K204.8K65.5KNo$0.3 / $1.5—streamingRetired2026-02-19—Gemini 3.1 Pro Previewgemini-3.1-pro-previewGoogleChatgenerate · batch1.05M1.05M65.5KYes$2 / $12$0.2 / —tools · structured_output · streaming · caching · batchPreview2026-02-19—Jina Embeddings v5 Text Nanojina-embeddings-v5-text-nanoJina AIEmbeddingembeddings8.2K8.2K——$0.02 / ———Active2026-02-18—Jina Embeddings v5 Text Smalljina-embeddings-v5-text-smallJina AIEmbeddingembeddings32.8K32.8K——$0.05 / ———Active2026-02-18—Claude Sonnet 4.6claude-sonnet-4-6AnthropicChatmessages · batch1M1M128Klow · medium · high · max$3 / $15$0.3 / $3.75tools · structured_output · streaming · caching · batchActive2026-02-172025-08 Tiny Aya Earthtiny-aya-earthCohereChatchat8K—8K————Active2026-02-17—Tiny Aya Firetiny-aya-fireCohereChatchat8K—8K————Active2026-02-17—Tiny Aya Globaltiny-aya-globalCohereChatchat8K—8K————Active2026-02-17—Tiny Aya Watertiny-aya-waterCohereChatchat8K—8K————Active2026-02-17—Qwen3.5-397B-A17Bqwen3.5-397b-a17bAlibabaChatchat · messages262.1K260.1K65.5KYes$0.6 / $3.6—tools · structured_output · streamingActive2026-02-15—Qwen3.5-Plusqwen3.5-plusAlibabaChatchat · messages1M991.8K65.5KYes$0.4 / $2.4—tools · structured_output · streaming · cachingActive2026-02-15—Doubao-Seed-2.0-Code Previewdoubao-seed-2-0-code-previewByteDanceChatchat · responses262.1K229.4K131.1Knone · minimal · low · medium · high · xhigh · max¥3.2 / ¥16¥0.64 / —tools · streaming · caching · batchDeprecated2026-02-14—Doubao-Seed-2.0-Litedoubao-seed-2-0-liteByteDanceChatchat · responses262.1K229.4K131.1Knone · minimal · low · medium · high · xhigh · max¥0.6 / ¥3.6¥0.12 / —tools · structured_output · streaming · caching · batchActive2026-02-14—Doubao-Seed-2.0-Minidoubao-seed-2-0-miniByteDanceChatchat · responses262.1K229.4K131.1Knone · minimal · low · medium · high · xhigh · max¥0.2 / ¥2¥0.04 / —tools · structured_output · streaming · caching · batchActive2026-02-14—Doubao-Seed-2.0-Prodoubao-seed-2-0-proByteDanceChatchat · responses262.1K229.4K131.1Knone · minimal · low · medium · high · xhigh · max¥3.2 / ¥16¥0.64 / —tools · structured_output · streaming · caching · batchDeprecated2026-02-14—Fun-ASR-Flash-8K-Realtimefun-asr-flash-8k-realtimeAlibabaChatrealtime———No¥0.0002 / — / second——Active2026-02-12—MiniMax-M2.5minimax-m2.5MiniMaxChatchat · messages204.8K—204.8KYes$0.3 / $1.2$0.03 / $0.375tools · streaming · cachingActive2026-02-12—MiniMax-M2.5-highspeedminimax-m2.5-highspeedMiniMaxChatchat · messages204.8K—204.8KYes$0.6 / $2.4$0.03 / $0.375tools · streaming · cachingActive2026-02-12—GLM-5glm-5Zhipu AIChatchat202.8K—131.1KYes$1 / $3.2$0.2 / —tools · structured_output · streaming · cachingActive2026-02-12—Vidu Q3 Turboviduq3-turboShengshu ViduVideovideo———————Active2026-02-11—Qwen3-TTS-Instruct-FlashRetiredqwen3-tts-instruct-flashAlibabaAudioaudio———No$11.5 / — / 1M characters——Retired2026-02-10—Llama Nemotron Embed VL 1B v2llama-nemotron-embed-vl-1b-v2NVIDIAEmbeddingembeddings———————Active2026-02-10—Gen-4.5gen4.5RunwayVideovideo————— / $0.12 / second——Active2026-02-10—Claude Opus 4.6claude-opus-4-6AnthropicChatmessages · batch1M1M128Klow · medium · high · max$5 / $25$0.5 / $6.25tools · structured_output · streaming · caching · batchActive2026-02-052025-05 LongCat-Flash-LiteRetiredlongcat-flash-liteMeituanChatchat———————Retired2026-02-05—Voxtral Mini Transcribe 2voxtral-mini-2602Mistral AIChataudio————$0.003 / — / minute——Active2026-02-04—Voxtral Mini Transcribe Realtimevoxtral-mini-transcribe-realtime-2602Mistral AIChataudio————$0.006 / — / minute——Active2026-02-04—Intern-S1-Prointern-s1-proShanghai AI LabChatchat262.1K——Yes——tools · streamingActive2026-02-04—GLM-OCRglm-ocrZhipu AIChatocr————$0.03 / $0.03——Active2026-02-03—Qwen3-VL-Rerankqwen3-vl-rerankAlibabaRerankrerank8K8K—No¥0.5 / ———Active2026-01-29—Wan2.6-R2V-Flashwan2.6-r2v-flashAlibabaVideovideo———No$0.025 / $0.025 / second——Active2026-01-29—Grok Imagine Videogrok-imagine-videoxAIVideovideo · batch————— / $0.05 / second—batchActive2026-01-28—Qwen3-Rerankqwen3-rerankAlibabaRerankrerank30K30K—No$0.1 / ———Active2026-01-27—Vidu Q3 Providuq3-proShengshu ViduVideovideo———————Active2026-01-27—PixVerse V5.6v5.6PixVerseVideovideo———————Active2026-01-26—speech-2.8-hdspeech-2.8-hdMiniMaxAudioaudio———No$100 / — / 1M characters——Active2026-01-23—speech-2.8-turbospeech-2.8-turboMiniMaxAudioaudio———No$60 / — / 1M characters——Active2026-01-23—Qwen3-TTS-Instruct-Flash-RealtimeRetiredqwen3-tts-instruct-flash-realtimeAlibabaAudiorealtime————$14.3 / — / 1M characters——Retired2026-01-21—Qwen3-VL-Embeddingqwen3-vl-embeddingAlibabaEmbeddingembeddings32K32K—No———Active2026-01-21—GLM-4.7-Flashglm-4.7-flashZhipu AIChatchat202.8K—131.1KYes$0 / $0$0 / —tools · structured_output · streaming · cachingActive2026-01-19—Qwen-Image-Edit-MaxRetiredqwen-image-edit-maxAlibabaImageimages————— / $0.075 / image——Retired2026-01-15—Wan2.6-I2V-Flashwan2.6-i2v-flashAlibabaVideovideo———No— / $0.025 / second——Active2026-01-15—FLUX.2 [klein] 4Bflux-2-klein-4bBlack Forest LabsImageimages———————Active2026-01-15—FLUX.2 [klein] 9Bflux-2-klein-9bBlack Forest LabsImageimages———————Active2026-01-15—Voyage 4voyage-4Voyage AIEmbeddingembeddings32K———$0.06 / ———Active2026-01-15—Voyage 4 Largevoyage-4-largeVoyage AIEmbeddingembeddings32K———$0.12 / ———Active2026-01-15—Voyage 4 Litevoyage-4-liteVoyage AIEmbeddingembeddings32K———$0.02 / ———Active2026-01-15—Voyage Multimodal 3.5voyage-multimodal-3.5Voyage AIEmbeddingembeddings32K——————Active2026-01-15—LongCat-Flash-Thinking-2601Retiredlongcat-flash-thinking-2601MeituanChatchat———Yes———Retired2026-01-14—GLM-Imageglm-imageZhipu AIImageimages————— / $0.015 / image——Active2026-01-14—Jamba Mini 2jamba-mini-2AI21 LabsChatchat262.1K—4.1KNo$0.2 / $0.4—tools · streamingActive2026-01-082024-08-22 Qwen-Image-MaxRetiredqwen-image-maxAlibabaImageimages————— / $0.075 / image——Retired2025-12-30—GLM-4.7glm-4.7Zhipu AIChatchat202.8K—131.1KYes$0.6 / $2.2$0.11 / —tools · structured_output · streaming · cachingActive2025-12-22—Z-Image-Turboz-image-turboAlibabaImageimages———No— / $0.015 / image——Active2025-12-18—Mistral OCR 3mistral-ocr-2512Mistral AIChatocr————$0.002 / — / page—batchActive2025-12-18—Gemini 3 Flash Previewgemini-3-flash-previewGoogleChatgenerate · batch1.05M1.05M65.5KYes$0.5 / $3$0.05 / —tools · structured_output · streaming · caching · batchPreview2025-12-17—Tencent HY Vision 1.5 Instructhunyuan-vision-1.5-instructTencentChatchat—24.6K16.4K—¥3 / ¥9—streamingActive2025-12-17—Wan2.6-R2Vwan2.6-r2vAlibabaVideovideo———No$0.1 / $0.1 / second——Active2025-12-16—FLUX.2 [max]flux-2-maxBlack Forest LabsImageimages———————Active2025-12-16—chatgpt-image-latestchatgpt-image-latestOpenAIChatimages · batch————$5 / $32$1.25 / —batchDeprecated2025-12-16—GPT-Image-1.5gpt-image-1.5OpenAIChatimages · batch————$5 / $32$1.25 / —batchDeprecated2025-12-16—Wan2.6-Imagewan2.6-imageAlibabaChatimages———No— / $0.03 / image——Active2025-12-15—Wan2.6-T2Iwan2.6-t2iAlibabaImageimages———No— / $0.03 / image——Active2025-12-15—Kling Image O1kling-image-o1KuaishouImageimages————— / $0.028 / image——Active2025-12-15—Kling 2.6kling-v2-6KuaishouVideovideo————— / $0.042 / second——Active2025-12-15—Kling O1kling-video-o1KuaishouVideovideo————— / $0.084 / second——Active2025-12-15—Solar Pro 2solar-pro2UpstageChatchat65.5K——Yes$0.15 / $0.6$0.015 / —tools · structured_outputDeprecated2025-12-152025-03 PP-StructureV3pp-structurev3BaiduChatocr————¥0.18 / — / page——Active2025-12-12—Gemini 2.5 Flash Livegemini-2.5-flash-native-audio-preview-12-2025GoogleChatrealtime—131.1K8.2K———toolsDeprecated2025-12-12—Rerank v4.0 Fastrerank-v4.0-fastCohereRerankrerank32K———$0.002 / — / request——Active2025-12-11—Rerank v4.0 Prorerank-v4.0-proCohereRerankrerank32K———$0.0025 / — / request——Active2025-12-11—Mistral Small CreativeRetiredlabs-mistral-small-creativeMistral AIChatchat · batch32.8K—————tools · structured_output · batchRetired2025-12-11—GPT-5.2gpt-5.2OpenAIChatchat · responses · batch400K—128Knone · low · medium · high · xhigh$1.75 / $14$0.175 / —tools · structured_output · streaming · caching · batchActive2025-12-112025-08-31 GPT-5.2 Progpt-5.2-proOpenAIChatresponses400K—128Kmedium · high · xhigh$21 / $168—tools · streamingActive2025-12-112025-08-31 AutoGLM-Phoneautoglm-phoneZhipu AIChatchat20.5K—2K————Active2025-12-11—GLM-TTSglm-ttsZhipu AIAudioaudio————¥200 / — / 1M characters——Active2025-12-11—GLM-TTS-Cloneglm-tts-cloneZhipu AIAudioaudio————— / ¥6 / request——Active2025-12-11—GLM-ASR-2512glm-asr-2512Zhipu AIChataudio————$0.03 / ———Active2025-12-10—Devstral 2Retireddevstral-2512Mistral AIChatchat · batch262.1K—————tools · structured_output · batchRetired2025-12-09—Devstral Small 2Retiredlabs-devstral-small-2512Mistral AIChatchat · batch262.1K—————tools · structured_output · batchRetired2025-12-09—GLM-4.6Vglm-4.6vZhipu AIChatchat131.1K—32.8KYes$0.3 / $0.9$0.05 / —tools · cachingActive2025-12-08—Wan2.6-I2Vwan2.6-i2vAlibabaVideovideo———No— / $0.1 / second——Active2025-12-03—Wan2.6-T2Vwan2.6-t2vAlibabaVideovideo———No— / $0.1 / second——Active2025-12-03—Amazon Nova 2 Litenova-2-liteAmazonChatchat1M—65.5Klow · medium · high$0.3 / $2.5$0.075 / —tools · streaming · cachingActive2025-12-022025-10 Amazon Nova 2 Sonicnova-2-sonicAmazonChatrealtime1M—65.5K—$3 / $12—streamingActive2025-12-02—Ministral 3 14Bministral-14b-2512Mistral AIChatchat · batch262.1K———$0.2 / $0.2$0.02 / —tools · structured_output · caching · batchActive2025-12-02—Ministral 3 3Bministral-3b-2512Mistral AIChatchat · batch262.1K———$0.1 / $0.1$0.01 / —tools · structured_output · caching · batchActive2025-12-02—Ministral 3 8Bministral-8b-2512Mistral AIChatchat · batch262.1K———$0.15 / $0.15$0.015 / —tools · structured_output · caching · batchActive2025-12-02—Mistral Large 3mistral-large-2512Mistral AIChatchat · batch262.1K———$0.5 / $1.5$0.05 / —tools · structured_output · caching · batchActive2025-12-02—PixVerse V5.5v5.5PixVerseVideovideo———————Active2025-12-02—PaddleOCR-VL-0.9Bpaddleocr-vl-0.9bBaiduChatocr————¥0.18 / — / page——Active2025-11-28—FLUX.2 [flex]flux-2-flexBlack Forest LabsImageimages———————Active2025-11-25—FLUX.2 [pro]flux-2-proBlack Forest LabsImageimages———————Active2025-11-25—Claude Opus 4.5claude-opus-4-5AnthropicChatmessages · batch200K200K64KYes$5 / $25$0.5 / $6.25tools · structured_output · streaming · caching · batchActive2025-11-242025-05 Gemini 3 Pro Image PreviewRetiredgemini-3-pro-image-previewGoogleChatgenerate65.5K65.5K32.8KYes——structured_output · batchRetired2025-11-202025-01 Qwen-MT-Liteqwen-mt-liteAlibabaChatchat—8.2K—No$0.12 / $0.36—streamingActive2025-11-19—Gemini 3 Pro PreviewRetiredgemini-3-pro-previewGoogleChatgenerate1.05M1.05M65.5KYes——tools · structured_output · caching · batchRetired2025-11-182025-01 CosyVoice-V3-Flashcosyvoice-v3-flashAlibabaAudioaudio———No$13 / — / 1M characters——Active2025-11-17—Qwen3-ASR-Flash-Filetransqwen3-asr-flash-filetransAlibabaChataudio———No$0 / — / second——Active2025-11-17—Marengo 3.0marengo3.0Twelve LabsEmbeddingembeddings———————Active2025-11-17—Typhoon OCRtyphoon-ocrSCB 10X TyphoonChatocr———————Active2025-11-14—ERNIE 5.0ernie-5.0BaiduChatchat · messages131.1K121.9K65.5KYes¥6 / ¥24—streamingDeprecated2025-11-13—ERNIE 5.0 Thinking Latesternie-5.0-thinking-latestBaiduChatchat · messages131.1K121.9K65.5KYes¥6 / ¥24—streamingDeprecated2025-11-13—ERNIE 5.0 Thinking Previewernie-5.0-thinking-previewBaiduChatchat · messages131.1K121.9K65.5KYes¥6 / ¥24—streamingDeprecated2025-11-13—GPT-5.1gpt-5.1OpenAIChatchat · responses · batch400K—128Knone · low · medium · high$1.25 / $10$0.125 / —tools · structured_output · streaming · caching · batchDeprecated2025-11-132024-09-30 Qwen-MT-Flashqwen-mt-flashAlibabaChatchat—8.2K—No$0.16 / $0.49—streamingActive2025-11-06—Tongyi Embedding Vision Flashtongyi-embedding-vision-flashAlibabaEmbeddingembeddings—1K—No———Active2025-10-31—Tongyi Embedding Vision Plustongyi-embedding-vision-plusAlibabaEmbeddingembeddings—1K—No$0.09 / ———Active2025-10-31—Qwen-Image-Edit-PlusRetiredqwen-image-edit-plusAlibabaImageimages————— / $0.03 / image——Retired2025-10-30—speech-2.6-hdspeech-2.6-hdMiniMaxAudioaudio———No$100 / — / 1M characters—streamingActive2025-10-29—speech-2.6-turbospeech-2.6-turboMiniMaxAudioaudio———No$60 / — / 1M characters—streamingActive2025-10-29—Amazon Nova Multimodal Embeddingsnova-multimodal-embeddingsAmazonEmbeddingembeddings———No$0.135 / ———Active2025-10-28—MiniMax-Hailuo-2.3minimax-hailuo-2.3MiniMaxVideovideo———No— / $0.28 / request——Active2025-10-28—MiniMax-Hailuo-2.3-Fastminimax-hailuo-2.3-fastMiniMaxVideovideo———No— / $0.19 / request——Active2025-10-28—Llama 3.1 Nemotron Safety Guard 8B v3llama-3.1-nemotron-safety-guard-8b-v3NVIDIAChatmoderation———————Active2025-10-28—Nemotron Parsenemotron-parseNVIDIAChatocr———————Active2025-10-28—Qwen3-ASR-Flash-Realtimeqwen3-asr-flash-realtimeAlibabaChatrealtime———No$0.0001 / — / second——Active2025-10-27—Sonic 3sonic-3CartesiaAudioaudio———————Active2025-10-27—MiniMax-M2minimax-m2MiniMaxChatchat · messages204.8K—131.1KYes$0.3 / $1.2$0.03 / $0.375tools · streaming · cachingActive2025-10-27—Qwen3-VL-32B-InstructRetiredqwen3-vl-32b-instructAlibabaChatchat———No$0.16 / $0.64—streamingRetired2025-10-21—Qwen3-VL-32B-ThinkingRetiredqwen3-vl-32b-thinkingAlibabaChatchat———Yes$0.16 / $0.64—streamingRetired2025-10-21—Kling 2.5 Turbokling-v2-5-turboKuaishouVideovideo————— / $0.042 / second——Active2025-10-20—Typhoon v2.5 30B A3B Instructtyphoon-v2.5-30b-a3b-instructSCB 10X TyphoonChatchat——————tools · streamingActive2025-10-20—Claude Haiku 4.5claude-haiku-4-5AnthropicChatmessages · batch200K200K64KYes$1 / $5$0.1 / $1.25tools · structured_output · streaming · caching · batchActive2025-10-152025-02 Veo 3.1 Fast Previewveo-3.1-fast-generate-previewGoogleVideovideo—1K—No— / $0.1 / second——Deprecated2025-10-15—Veo 3.1 Previewveo-3.1-generate-previewGoogleVideovideo—1K—No— / $0.4 / second——Deprecated2025-10-15—Qwen3-VL-FlashRetiredqwen3-vl-flashAlibabaChatchat262.1K260.1K32.8KYes$0.05 / $0.4$0.005 / $0.0625structured_output · streaming · cachingRetired2025-10-14—Hunyuan-Translationhunyuan-translationTencentChatchat—4.1K4.1K—¥1.2 / ¥3.6—streamingActive2025-10-14—GPT-5 Progpt-5-proOpenAIChatresponses · batch400K—272Khigh$15 / $120—tools · structured_output · streaming · batchActive2025-10-062024-09-30 GPT-Image-1 Minigpt-image-1-miniOpenAIImageimages · batch————$2 / $8$0.2 / —batchDeprecated2025-10-06—Nano Bananagemini-2.5-flash-imageGoogleChatimages · batch—65.5K32.8KNo——batchDeprecated2025-10-022025-06 Granite 4 H Smallgranite-4-h-smallIBMChatchat131.1K———$0.0636 / $0.265—streamingActive2025-10-02—Flux General (English)flux-general-enDeepgramChataudio————$0.0077 / — / minute——Active2025-10-01—Jina Reranker v3jina-reranker-v3Jina AIRerankrerank131.1K———$0.05 / ———Active2025-10-01—Qwen3-VL-30B-A3B-InstructRetiredqwen3-vl-30b-a3b-instructAlibabaChatchat———No$0.2 / $0.8—streamingRetired2025-09-30—Qwen3-VL-30B-A3B-ThinkingRetiredqwen3-vl-30b-a3b-thinkingAlibabaChatchat———Yes$0.2 / $2.4—streamingRetired2025-09-30—Qwen3-VL-8B-InstructRetiredqwen3-vl-8b-instructAlibabaChatchat———No$0.18 / $0.7—streamingRetired2025-09-30—Qwen3-VL-8B-ThinkingRetiredqwen3-vl-8b-thinkingAlibabaChatchat———Yes$0.18 / $2.1—streamingRetired2025-09-30—GLM-4.6glm-4.6Zhipu AIChatchat202.8K—131.1KYes$0.6 / $2.2$0.11 / —tools · structured_output · streaming · cachingActive2025-09-30—Claude Sonnet 4.5claude-sonnet-4-5AnthropicChatmessages · batch200K200K64KYes$3 / $15$0.3 / $3.75tools · structured_output · streaming · caching · batchDeprecated2025-09-292025-01 ERNIE X1.1Retiredernie-x1.1BaiduChatchat · messages65.5K56.3K65.5KYes——streamingRetired2025-09-26—Fun-ASR-MTLRetiredfun-asr-mtlAlibabaChataudio————$0 / — / second——Retired2025-09-25—Gemini 2.5 Flash-Lite Preview 09-2025Retiredgemini-2.5-flash-lite-preview-09-2025GoogleChatgenerate1.05M1.05M65.5KYes——tools · structured_output · caching · batchRetired2025-09-252025-01 Vidu Q2 Providuq2-proShengshu ViduVideovideo———————Active2025-09-24—Vidu Q2 Turboviduq2-turboShengshu ViduVideovideo———————Active2025-09-24—Hy-Role-Latesthunyuan-role-latestTencentChatchat · messages32.8K28.7K4.1K—¥2.4 / ¥9.6——Active2025-09-24—Fun-ASR-Realtimefun-asr-realtimeAlibabaChatrealtime———No$0.0001 / — / second——Active2025-09-23—Qwen-Image-PlusRetiredqwen-image-plusAlibabaImageimages———No— / $0.03 / image——Retired2025-09-23—Qwen3-MaxRetiredqwen3-maxAlibabaChatchat262.1K258K65.5KYes$1.2 / $6$0.12 / $1.5structured_output · streaming · cachingRetired2025-09-23—Qwen3-VL-235B-A22B-InstructRetiredqwen3-vl-235b-a22b-instructAlibabaChatchat———No$0.4 / $1.6—streamingRetired2025-09-23—Qwen3-VL-235B-A22B-ThinkingRetiredqwen3-vl-235b-a22b-thinkingAlibabaChatchat———Yes$0.4 / $4—streamingRetired2025-09-23—Qwen3-VL-Plusqwen3-vl-plusAlibabaChatchat · messages262.1K260.1K32.8KYes$0.2 / $1.6—structured_output · streaming · cachingActive2025-09-23—Wan2.5-I2I-Previewwan2.5-i2i-previewAlibabaImageimages————— / $0.03 / image——Active2025-09-23—LongCat-Flash-ThinkingRetiredlongcat-flash-thinkingMeituanChatchat———Yes———Retired2025-09-22—Wan2.2-Animate-Mixwan2.2-animate-mixAlibabaVideovideo———No— / $0.18 / second——Active2025-09-19—Wan2.2-Animate-Movewan2.2-animate-moveAlibabaVideovideo———No— / $0.12 / second——Active2025-09-19—Wan2.5-I2V-Previewwan2.5-i2v-previewAlibabaVideovideo————— / $0.05 / second——Active2025-09-19—Wan2.5-T2I-Previewwan2.5-t2i-previewAlibabaImageimages————— / $0.03 / image——Active2025-09-19—Wan2.5-T2V-Previewwan2.5-t2v-previewAlibabaVideovideo————— / $0.05 / second——Active2025-09-19—Magistral Medium 1.2Retiredmagistral-medium-2509Mistral AIChatchat · batch131.1K——Yes——tools · batchRetired2025-09-18—Magistral Small 1.2Retiredmagistral-small-2509Mistral AIChatchat · batch131.1K——Yes——tools · batchRetired2025-09-18—HY-Vision-1.5-Thinkinghunyuan-t1-vision-20250916TencentChatchat41K16.4K24.6KYes¥3 / ¥9——Active2025-09-16—Wan2.2-KF2V-Flashwan2.2-kf2v-flashAlibabaVideovideo———No— / $0.015 / second——Active2025-09-12—Qwen3-Next-80B-A3B-InstructRetiredqwen3-next-80b-a3b-instructAlibabaChatchat131.1K129K32.8KNo$0.15 / $1.2—structured_output · streamingRetired2025-09-11—Qwen3-Next-80B-A3B-ThinkingRetiredqwen3-next-80b-a3b-thinkingAlibabaChatchat131.1K127K32.8KYes$0.15 / $1.2—streamingRetired2025-09-11—ERNIE X1.1 PreviewRetiredernie-x1.1-previewBaiduChatchat · messages65.5K56.3K65.5KYes¥1 / ¥4—streamingRetired2025-09-09—Veo 3 FastRetiredveo-3.0-fast-generate-001GoogleVideovideo—1K—No———Retired2025-09-09—Veo 3Retiredveo-3.0-generate-001GoogleVideovideo—1K—No———Retired2025-09-09—Qwen3-ASR-Flashqwen3-asr-flashAlibabaChataudio———No$0 / — / second——Active2025-09-08—Typhoon ASR Real-Timetyphoon-asr-realtimeSCB 10X TyphoonChataudio———————Active2025-09-08—CosyVoice-V3-Pluscosyvoice-v3-plusAlibabaAudioaudio———No$26 / — / 1M characters——Active2025-09-03—Jina Code Embeddings 0.5Bjina-code-embeddings-0.5bJina AIEmbeddingembeddings32.8K32.8K——$0.05 / ———Active2025-09-01—Jina Code Embeddings 1.5Bjina-code-embeddings-1.5bJina AIEmbeddingembeddings32.8K32.8K——$0.05 / ———Active2025-09-01—LongCat-Flash-ChatRetiredlongcat-flash-chatMeituanChatchat———————Retired2025-08-29—PixVerse V5v5PixVerseVideovideo———————Active2025-08-29—Command A Translatecommand-a-translate-08-2025CohereChatchat8K—8K————Active2025-08-282024-06 Contextual AI Reranker v2 Instruct Multilingualctxl-rerank-v2-instruct-multilingualContextual AIRerankrerank8K———$0.05 / ———Active2025-08-27—Contextual AI Reranker v2 Instruct Multilingual Minictxl-rerank-v2-instruct-multilingual-miniContextual AIRerankrerank8K———$0.02 / ———Active2025-08-27—InternVL3.5 241B-A28Binternvl3.5-241b-a28bShanghai AI LabChatchat——————tools · streamingActive2025-08-26—Qwen-Deep-Researchqwen-deep-researchAlibabaChatchat1M998K32.8K—¥54 / ¥163—streamingActive2025-08-22—Command A Reasoningcommand-a-reasoning-08-2025CohereChatchat256K—32KYes——tools · structured_outputActive2025-08-212024-06 Gen-4 Image Turbogen4_image_turboRunwayImageimages————— / $0.02 / image——Active2025-08-19—Qwen-Image-EditRetiredqwen-image-editAlibabaImageimages————— / $0.045 / image——Retired2025-08-18—Wan2.2-I2V-Flashwan2.2-i2v-flashAlibabaVideovideo———No— / $0.015 / second——Active2025-08-15—Kling Image 2.0 NewRetiredkling-image-v2-newKuaishouImageimages———————Retired2025-08-15—Qwen-ImageRetiredqwen-imageAlibabaImageimages———No— / $0.035 / image——Retired2025-08-13—Mistral Medium 3.1Retiredmistral-medium-2508Mistral AIChatchat · batch131.1K—————tools · structured_output · batchRetired2025-08-12—Rerank 2.5rerank-2.5Voyage AIRerankrerank32K———$0.05 / ———Active2025-08-11—Rerank 2.5 Litererank-2.5-liteVoyage AIRerankrerank32K———$0.02 / ———Active2025-08-11—GLM-4.5Vglm-4.5vZhipu AIChatchat65.5K—16.4KYes$0.6 / $1.8$0.11 / ——Active2025-08-11—ERNIE 4.5 Turbo VLernie-4.5-turbo-vlBaiduChatchat · messages131.1K126K16.4K—¥3 / ¥9—streamingDeprecated2025-08-07—GPT-5gpt-5OpenAIChatchat · responses · batch400K272K128Kminimal · low · medium · high$1.25 / $10$0.125 / —tools · structured_output · streaming · caching · batchActive2025-08-072024-09-30 GPT-5 Minigpt-5-miniOpenAIChatchat · responses · batch400K272K128KYes$0.25 / $2$0.025 / —tools · structured_output · streaming · caching · batchActive2025-08-072024-05-31 GPT-5 Nanogpt-5-nanoOpenAIChatchat · responses · batch400K272K128KYes$0.05 / $0.4$0.005 / —tools · structured_output · streaming · caching · batchActive2025-08-072024-05-31 Claude Opus 4.1Retiredclaude-opus-4-1AnthropicChatmessages · batch200K—32KYes$15 / $75$1.5 / $18.75tools · caching · batchRetired2025-08-052025-03 Lucid Originlucid-originLeonardo.AiImageimages———————Active2025-08-05—Qwen-Flashqwen-flashAlibabaChatchat · messages1M998K32.8KYes$0.05 / $0.4$0.005 / $0.063structured_output · streaming · cachingActive2025-08-01—Qwen3-Coder-30B-A3B-InstructRetiredqwen3-coder-30b-a3b-instructAlibabaChatchat262.1K204.8K65.5KNo$0.45 / $2.25——Retired2025-07-31—Command A Visioncommand-a-vision-07-2025CohereChatchat128K—8K————Active2025-07-312024-06 Qwen3-30B-A3B-Thinking-2507Retiredqwen3-30b-a3b-thinking-2507AlibabaChatchat———Yes$0.2 / $2.4—streamingRetired2025-07-30—Kling Image 2.1kling-v2-1KuaishouImageimages————— / $0.014 / image——Active2025-07-30—Codestralcodestral-2508Mistral AIChatchat · batch131.1K———$0.3 / $0.9$0.03 / —tools · structured_output · caching · batchActive2025-07-30—Qwen3-30B-A3B-Instruct-2507Retiredqwen3-30b-a3b-instruct-2507AlibabaChatchat———No$0.2 / $0.8—structured_output · streamingRetired2025-07-29—Qwen3-Coder-Flashqwen3-coder-flashAlibabaChatchat · messages1M998K65.5KNo$0.3 / $1.5—streaming · cachingActive2025-07-29—HyperCLOVA X HCX-007hcx-007NaverChatchat128K128K32.8Knone · low · medium · high——tools · structured_output · streamingActive2025-07-29—Wan2.2-I2V-Pluswan2.2-i2v-plusAlibabaVideovideo———No— / $0.02 / second——Active2025-07-28—Wan2.2-T2I-Flashwan2.2-t2i-flashAlibabaImageimages———No— / $0.025 / image——Active2025-07-28—Wan2.2-T2I-Pluswan2.2-t2i-plusAlibabaImageimages———No— / $0.05 / image——Active2025-07-28—Wan2.2-T2V-Pluswan2.2-t2v-plusAlibabaVideovideo———No— / $0.02 / second——Active2025-07-28—HY-Vision-Videohunyuan-turbos-vision-video-20250728TencentChatchat32.8K24.6K8.2K—¥3 / ¥9——Active2025-07-28—GLM-4.5glm-4.5Zhipu AIChatchat131.1K—98.3KYes$0.6 / $2.2$0.11 / —tools · structured_output · streaming · cachingDeprecated2025-07-28—GLM-4.5-Airglm-4.5-airZhipu AIChatchat131.1K—98.3KYes$0.2 / $1.1$0.03 / —tools · structured_output · streaming · cachingActive2025-07-28—Intern-S1intern-s1Shanghai AI LabChatchat———Yes——tools · streamingActive2025-07-26—Qwen3-235B-A22B-Thinking-2507Retiredqwen3-235b-a22b-thinking-2507AlibabaChatchat———Yes$0.23 / $2.3—streamingRetired2025-07-25—Magistral Medium 1.1Retiredmagistral-medium-2507Mistral AIChatchat · batch41K——Yes——tools · batchRetired2025-07-24—Magistral Small 1.1Retiredmagistral-small-2507Mistral AIChatchat · batch41K——Yes——tools · batchRetired2025-07-24—Qwen-Doc-Turboqwen-doc-turboAlibabaChatchat262.1K254K8.2K—¥0.6 / ¥1¥0.06 / ¥0.75cachingActive2025-07-23—Qwen3-Coder-480B-A35B-InstructRetiredqwen3-coder-480b-a35b-instructAlibabaChatchat262.1K204.8K65.5KNo$1.5 / $7.5——Retired2025-07-23—Voyage Context 3voyage-context-3Voyage AIEmbeddingembeddings32K———$0.18 / ———Active2025-07-23—Qwen-MT-Plusqwen-mt-plusAlibabaChatchat16.4K8.2K8.2KNo$2.46 / $7.37—streamingActive2025-07-22—Qwen-MT-TurboRetiredqwen-mt-turboAlibabaChatchat16.4K8.2K8.2KNo$0.16 / $0.49—streamingRetired2025-07-22—Qwen3-235B-A22B-Instruct-2507Retiredqwen3-235b-a22b-instruct-2507AlibabaChatchat———No$0.23 / $0.92—structured_output · streamingRetired2025-07-22—Qwen3-Coder-PlusRetiredqwen3-coder-plusAlibabaChatchat1M998K65.5KNo$1 / $5—streaming · cachingRetired2025-07-22—Gemini 2.5 Flash-Litegemini-2.5-flash-liteGoogleChatgenerate · batch1.05M1.05M65.5KYes$0.1 / $0.4$0.01 / —tools · structured_output · streaming · caching · batchActive2025-07-222025-01 Qwen-Plus-Character-JAqwen-plus-character-jaAlibabaChatchat8.2K8.2K4.1K—$0.5 / $1.4—streamingActive2025-07-21—Act-Twoact_twoRunwayVideovideo————— / $0.05 / second——Active2025-07-21—Voxtral MiniRetiredvoxtral-mini-2507Mistral AIChatchat · batch32.8K—————structured_output · batchRetired2025-07-15—Voxtral Smallvoxtral-small-2507Mistral AIChatchat · batch32.8K———$0.1 / $0.4—tools · structured_output · batchActive2025-07-15—CogVideoX-3cogvideox-3Zhipu AIVideovideo————— / $0.2 / request——Active2025-07-15—Gemini Embeddinggemini-embedding-001GoogleEmbeddingembeddings—2K—No———Deprecated2025-07-14—Devstral Medium 1.0Retireddevstral-medium-2507Mistral AIChatchat · batch131.1K—————tools · structured_output · batchRetired2025-07-10—Devstral Small 1.1Retireddevstral-small-2507Mistral AIChatchat · batch131.1K—————tools · structured_output · batchRetired2025-07-10—Jamba Large 1.7jamba-large-1.7AI21 LabsChatchat262.1K—4.1KNo$2 / $8—tools · streamingActive2025-07-032024-08-22 Jamba Mini 1.7Retiredjamba-mini-1.7AI21 LabsChatchat———————Retired2025-07-03—Hunyuan-A13Bhunyuan-a13bTencentChatchat—229.4K32.8KYes¥0.5 / ¥2—streamingActive2025-06-25—Imagen 4 FastRetiredimagen-4.0-fast-generate-001GoogleImageimages—480—No———Retired2025-06-24—Imagen 4Retiredimagen-4.0-generate-001GoogleImageimages—480—No———Retired2025-06-24—Imagen 4 UltraRetiredimagen-4.0-ultra-generate-001GoogleImageimages—480—No———Retired2025-06-24—Jina Embeddings v4jina-embeddings-v4Jina AIEmbeddingembeddings32.8K32.8K——$0.05 / ———Active2025-06-24—Mistral Small 3.2Retiredmistral-small-2506Mistral AIChatchat · batch131.1K—————tools · structured_output · batchRetired2025-06-20—Kling 2.1Retiredkling-video-v2-1KuaishouVideovideo———————Retired2025-06-19—Kling 2.1 MasterRetiredkling-video-v2-1-masterKuaishouVideovideo———————Retired2025-06-19—MiniMax-Hailuo-02minimax-hailuo-02MiniMaxVideovideo———No— / $0.1 / request——Active2025-06-18—Gemini 2.5 Flashgemini-2.5-flashGoogleChatgenerate · batch1.05M1.05M65.5KYes$0.3 / $2.5$0.03 / —tools · structured_output · streaming · caching · batchActive2025-06-172025-01 Gemini 2.5 Progemini-2.5-proGoogleChatgenerate · batch1.05M1.05M65.5KYes$1.25 / $10$0.125 / —tools · structured_output · streaming · caching · batchActive2025-06-172025-01 Magistral Medium 1.0Retiredmagistral-medium-2506Mistral AIChatchat · batch41K——Yes——tools · batchRetired2025-06-10—Magistral Small 1.0Retiredmagistral-small-2506Mistral AIChatchat · batch41K——Yes——tools · batchRetired2025-06-10—o3-proo3-proOpenAIChatresponses · batch200K—100KYes$20 / $80—tools · structured_output · batchActive2025-06-102024-06-01 Hunyuan-Translation-Litehunyuan-translation-liteTencentChatchat—4.1K4.1K—¥1 / ¥3—streamingActive2025-06-06—Text Embedding V4text-embedding-v4AlibabaEmbeddingembeddings—8.2K—No$0.07 / ———Active2025-06-05—Ink Whisperink-whisperCartesiaChataudio · realtime———————Active2025-06-04—QVQ-PlusRetiredqvq-plusAlibabaChatchat131.1K106.5K8.2KYes——streamingRetired2025-06-03—FLUX.1 Kontext [max]flux-kontext-maxBlack Forest LabsImageimages————— / $0.08 / image——Active2025-05-29—FLUX.1 Kontext [pro]flux-kontext-proBlack Forest LabsImageimages————— / $0.04 / image——Active2025-05-29—Codestral Embedcodestral-embed-2505Mistral AIEmbeddingembeddings · batch8.2K———$0.15 / ——batchActive2025-05-28—CosyVoice-V2cosyvoice-v2AlibabaAudioaudio———No¥200 / — / 1M characters——Active2025-05-27—Wan2.1-T2I-Pluswan2.1-t2i-plusAlibabaImageimages————— / $0.05 / image——Active2025-05-22—Wan2.1-T2I-Turbowan2.1-t2i-turboAlibabaImageimages————— / $0.025 / image——Active2025-05-22—Claude Opus 4Retiredclaude-opus-4AnthropicChatmessages · batch200K—32KYes$15 / $75$1.5 / $18.75tools · caching · batchRetired2025-05-222025-03 Claude Sonnet 4Retiredclaude-sonnet-4AnthropicChatmessages · batch200K—64KYes$3 / $15$0.3 / $3.75tools · caching · batchRetired2025-05-222025-03 OCR 2Retiredmistral-ocr-2505Mistral AIChatocr · batch——————batchRetired2025-05-22—Devstral Small 1.0Retireddevstral-small-2505Mistral AIChatchat · batch131.1K—————tools · structured_output · batchRetired2025-05-21—Gemini 2.5 Flash Preview 05-20Retiredgemini-2.5-flash-preview-05-20GoogleChatgenerate1.05M1.05M65.5KYes——tools · structured_output · cachingRetired2025-05-202025-01 Gemini 2.5 Flash TTSgemini-2.5-flash-preview-ttsGoogleAudioaudio · batch—8.2K16.4KNo$0.5 / $10——Deprecated2025-05-20—Gemini 2.5 Pro TTSgemini-2.5-pro-preview-ttsGoogleAudioaudio · batch—8.2K16.4KNo$1 / $20——Deprecated2025-05-20—Lyria RealTimelyria-realtime-expGoogleAudiorealtime———No———Preview2025-05-20—Llama 3.2 NeMo Retriever 1B VLM Embed v1llama-3.2-nemoretriever-1b-vlm-embed-v1NVIDIAEmbeddingembeddings8.2K——————Active2025-05-20—Voyage 3.5voyage-3.5Voyage AIEmbeddingembeddings32K———$0.06 / ———Active2025-05-20—Voyage 3.5 Litevoyage-3.5-liteVoyage AIEmbeddingembeddings32K———$0.02 / ———Active2025-05-20—Gen-4 Imagegen4_imageRunwayImageimages————— / $0.05 / image——Active2025-05-16—Wan2.1-VACE-Pluswan2.1-vace-plusAlibabaVideovideo————— / $0.1 / second——Active2025-05-14—Kling 2.0 MasterRetiredkling-video-v2-masterKuaishouVideovideo———————Retired2025-05-13—Qwen-Omni-Turbo-RealtimeRetiredqwen-omni-turbo-realtimeAlibabaChatrealtime32.8K30.7K2KNo——streamingRetired2025-05-08—Gemini 2.0 Flash Preview Image GenerationRetiredgemini-2.0-flash-preview-image-generationGoogleChatgenerate32K32K8.2KNo——structured_output · cachingRetired2025-05-072024-08 Mistral Medium 3Retiredmistral-medium-2505Mistral AIChatchat · batch131.1K—————tools · structured_output · batchRetired2025-05-07—Gemini 2.5 Pro Preview 05-06Retiredgemini-2.5-pro-preview-05-06GoogleChatgenerate1.05M1.05M65.5KYes——tools · structured_output · cachingRetired2025-05-062025-01 Typhoon v2.1 12B Instructtyphoon-v2.1-12b-instructSCB 10X TyphoonChatchat———Yes——streamingActive2025-05-05—Qwen3-235B-A22BRetiredqwen3-235b-a22bAlibabaChatchat131.1K129K16.4KYes$0.7 / $2.8—streamingRetired2025-04-29—Qwen3-30B-A3BRetiredqwen3-30b-a3bAlibabaChatchat131.1K98.3K8.2KYes$0.2 / $0.8—structured_output · streamingRetired2025-04-29—Qwen3-32BRetiredqwen3-32bAlibabaChatchat131.1K98.3K8.2KYes$0.16 / $0.64—structured_output · streamingRetired2025-04-29—Qwen3-8BRetiredqwen3-8bAlibabaChatchat131.1K98.3K8.2KYes$0.18 / $0.7—structured_output · streamingRetired2025-04-29—Qwen3-14BRetiredqwen3-14bAlibabaChatchat131.1K98.3K8.2KYes$0.35 / $1.4—structured_output · streamingRetired2025-04-28—Palmyra X5palmyra-x5WriterChatchat1M—8.2KYes$0.6 / $6—tools · structured_output · streamingDeprecated2025-04-28—ERNIE 4.5 Turbo 128Kernie-4.5-turbo-128kBaiduChatchat · messages131.1K126K12.3K—¥0.8 / ¥3.2¥0.2 / —streaming · cachingDeprecated2025-04-24—ERNIE 4.5 Turbo 32Kernie-4.5-turbo-32kBaiduChatchat · messages32.8K27.6K12.3K—¥0.8 / ¥3.2¥0.2 / —streaming · cachingDeprecated2025-04-24—ERNIE 4.5 Turbo VL 32Kernie-4.5-turbo-vl-32kBaiduChatchat · messages32.8K27.6K12.3K—¥3 / ¥9—streamingDeprecated2025-04-24—GPT-Image-1gpt-image-1OpenAIImageimages · responses · batch————$5 / $40$1.25 / —batchDeprecated2025-04-23—Solar Minisolar-miniUpstageChatchat32.8K——No$0.15 / $0.15—tools · structured_outputDeprecated2025-04-222024-09 HyperCLOVA X HCX-005hcx-005NaverChatchat128K128K4.1KNo——tools · streamingActive2025-04-17—HyperCLOVA X HCX-DASH-002hcx-dash-002NaverChatchat32K32K4.1KNo——tools · streamingActive2025-04-17—o3o3OpenAIChatchat · responses · batch200K—100KYes$2 / $8$0.5 / —tools · structured_output · streaming · caching · batchActive2025-04-162024-06-01 o4-minio4-miniOpenAIChatchat · responses · batch200K—100KYes$1.1 / $4.4$0.275 / —tools · structured_output · streaming · caching · batchDeprecated2025-04-162024-06-01 Llama-SEA-LION v3.5 70B Rllama-sea-lion-v3.5-70b-rAI SingaporeChatchat131.1K——Yes———Active2025-04-15—Embed v4.0embed-v4.0CohereEmbeddingembeddings128K——————Active2025-04-15—Aura-2aura-2DeepgramAudioaudio————$30 / — / 1M characters——Active2025-04-15—GPT-4.1gpt-4.1OpenAIChatchat · responses · batch1.05M—32.8KNo$2 / $8$0.5 / —tools · structured_output · streaming · caching · batchActive2025-04-142024-06-01 GPT-4.1 Minigpt-4.1-miniOpenAIChatchat · responses · batch1.05M—32.8KNo$0.4 / $1.6$0.1 / —tools · structured_output · streaming · caching · batchActive2025-04-142024-06-01 GPT-4.1 nanogpt-4.1-nanoOpenAIChatchat · responses · batch1.05M—32.8KNo$0.1 / $0.4$0.025 / —tools · structured_output · streaming · caching · batchDeprecated2025-04-142024-06-01 GLM-4-Flash-250414glm-4-flash-250414Zhipu AIChatchat131.1K———¥0 / ¥0—tools · structured_output · streamingActive2025-04-14—GLM-Z1-AirRetiredglm-z1-airZhipu AIChatchat131.1K—32.8KYes¥0.5 / ¥0.5——Retired2025-04-14—GLM-Z1-AirXRetiredglm-z1-airxZhipu AIChatchat32.8K—30.7KYes¥5 / ¥5——Retired2025-04-14—GLM-Z1-FlashRetiredglm-z1-flashZhipu AIChatchat131.1K—32.8KYes¥0 / ¥0——Retired2025-04-14—Gemini 2.0 Flash LiveRetiredgemini-2.0-flash-live-001GoogleChatrealtime1.05M1.05M8.2KNo——tools · structured_outputRetired2025-04-092024-08 Veo 2Retiredveo-2.0-generate-001GoogleVideovideo———No———Retired2025-04-09—Jina Reranker m0jina-reranker-m0Jina AIRerankrerank————$0.05 / ———Active2025-04-08—Wan2.1-KF2V-Pluswan2.1-kf2v-plusAlibabaVideovideo————— / $0.1 / second——Active2025-04-07—Llama 3.1 Nemotron Ultra 253B v1llama-3.1-nemotron-ultra-253b-v1NVIDIAChatchat131.1K—16.4KYes———Active2025-04-07—speech-02-hdspeech-02-hdMiniMaxAudioaudio———No$100 / — / 1M characters—streamingActive2025-04-02—speech-02-turbospeech-02-turboMiniMaxAudioaudio———No$60 / — / 1M characters—streamingActive2025-04-02—QVQ-MaxRetiredqvq-maxAlibabaChatchat131.1K106.5K8.2KYes$1.2 / $4.8—streamingRetired2025-03-26—Qwen2.5-Omni-7BRetiredqwen2.5-omni-7bAlibabaChatchat32.8K30.7K2KNo——streamingRetired2025-03-26—Wanx2.1-ImageEditwanx2.1-imageeditAlibabaImageimages———No— / ¥0.14 / image——Active2025-03-25—GTE-Rerank-V2gte-rerank-v2AlibabaRerankrerank4K4K—No¥0.8 / ———Active2025-03-20—GPT-4o Mini Transcribegpt-4o-mini-transcribeOpenAIChataudio · realtime16K—2K—$1.25 / $5——Deprecated2025-03-202024-06-01 GPT-4o Mini TTSgpt-4o-mini-ttsOpenAIAudioaudio—2K——$0.6 / $12——Active2025-03-20—GPT-4o Transcribegpt-4o-transcribeOpenAIChataudio · realtime16K—2K—$2.5 / $10——Deprecated2025-03-202024-06-01 o1-proo1-proOpenAIChatresponses · batch200K—100KYes$150 / $600—tools · structured_output · batchDeprecated2025-03-192023-10-01 Mistral Small 3.1Retiredmistral-small-2503Mistral AIChatchat · batch131.1K—————tools · structured_output · batchRetired2025-03-17—Command Acommand-a-03-2025CohereChatchat256K—8K—$2.5 / $10—tools · structured_outputActive2025-03-132024-06 mxbai-rerank-large-v2mxbai-rerank-large-v2MixedbreadRerankrerank———————Active2025-03-13—Contextual AI Reranker v1 Instructctxl-rerank-v1-instructContextual AIRerankrerank8K——————Active2025-03-11—Reka Flash 3reka-flash-3Reka AIChatchat———Yes$0.1 / $0.2—structured_outputActive2025-03-10—Sonic 2sonic-2CartesiaAudioaudio———————Deprecated2025-03-07—Sonic Turbosonic-turboCartesiaAudioaudio———————Deprecated2025-03-07—Jamba Large 1.6Retiredjamba-large-1.6AI21 LabsChatchat262.1K——————Retired2025-03-062024-03-05 Jamba Mini 1.6Retiredjamba-mini-1.6AI21 LabsChatchat262.1K——————Retired2025-03-062024-03-05 OCRRetiredmistral-ocr-2503Mistral AIChatocr———————Retired2025-03-06—QwQ-PlusRetiredqwq-plusAlibabaChatchat131.1K98.3K8.2KYes$0.8 / $2.4—streamingRetired2025-03-05—Aya Vision 32Bc4ai-aya-vision-32bCohereChatchat16K—4K————Active2025-03-04—Gemini 2.0 Flash-LiteRetiredgemini-2.0-flash-liteGoogleChatgenerate1.05M1.05M8.2KNo$0.075 / $0.3—structured_outputRetired2025-02-252024-08 Claude Sonnet 3.7Retiredclaude-3-7-sonnetAnthropicChatmessages · batch200K—64KYes$3 / $15$0.3 / $3.75tools · caching · batchRetired2025-02-242024-11 Mistral SabaRetiredmistral-saba-2502Mistral AIChatchat32.8K——————Retired2025-02-17—image-01image-01MiniMaxImageimages———No— / $0.0035 / image——Active2025-02-15—Nova-3nova-3DeepgramChataudio————$0.0043 / — / minute——Active2025-02-12—Pegasus 1.2Retiredpegasus1.2Twelve LabsChatgenerate———————Retired2025-02-11—Imagen 3Retiredimagen-3.0-generate-002GoogleImageimages———No— / $0.03 / image——Retired2025-02-06—Gemini 2.0 FlashRetiredgemini-2.0-flashGoogleChatgenerate1.05M1.05M8.2KNo$0.1 / $0.4$0.025 / —tools · structured_outputRetired2025-02-052024-08 o3-minio3-miniOpenAIChatchat · responses · batch200K—100KYes$1.1 / $4.4$0.55 / —tools · structured_output · streaming · batchDeprecated2025-01-312023-10-01 Mistral Small 3.0Retiredmistral-small-2501Mistral AIChatchat · batch32.8K—————tools · structured_output · batchRetired2025-01-30—SonarsonarPerplexityChatchat————$1 / $1—structured_output · streamingDeprecated2025-01-21—Sonar Prosonar-proPerplexityChatchat————$3 / $15—structured_output · streamingDeprecated2025-01-21—ReaderLM-v2readerlm-v2Jina AIChatocr512.8K———$0.05 / ———Active2025-01-16—CodestralRetiredcodestral-2501Mistral AIChatchat · batch131.1K—————tools · structured_output · batchRetired2025-01-13—Wan2.1-T2V-Pluswan2.1-t2v-plusAlibabaVideovideo————— / $0.1 / second——Active2025-01-09—Wan2.1-T2V-Turbowan2.1-t2v-turboAlibabaVideovideo————— / $0.036 / second——Active2025-01-09—Kling 1.6Retiredkling-video-v1-6KuaishouVideovideo———————Retired2025-01-07—Voyage 3 Largevoyage-3-largeVoyage AIEmbeddingembeddings32K———$0.18 / ———Active2025-01-07—Paraformer-Realtime-8K-V2paraformer-realtime-8k-v2AlibabaChatrealtime———No¥0.0002 / — / second——Active2024-12-31—Paraformer-8K-V2paraformer-8k-v2AlibabaChataudio———No¥0.0001 / — / second——Active2024-12-19—Granite Embedding 278M Multilingualgranite-embedding-278m-multilingualIBMEmbeddingembeddings512512——$0.106 / ———Active2024-12-18—o1o1OpenAIChatchat · responses · batch200K—100KYes$15 / $60$7.5 / —tools · structured_output · streaming · batchDeprecated2024-12-172023-10-01 Command R7Bcommand-r7b-12-2024CohereChatchat128K—4K—$0.0375 / $0.15—tools · structured_outputActive2024-12-132024-06 Tongyi-Intent-Detect-V3tongyi-intent-detect-v3AlibabaChatchat8.2K8.2K4.1K—¥0.4 / ¥1——Active2024-12-12—Amazon Nova Litenova-liteAmazonChatchat · batch300K—10KNo$0.06 / $0.24$0.015 / —tools · streaming · caching · batchActive2024-12-052024-10 Amazon Nova Micronova-microAmazonChatchat · batch128K—10KNo$0.035 / $0.14$0.0088 / —tools · streaming · caching · batchActive2024-12-052024-10 Amazon Nova Pronova-proAmazonChatchat · batch300K—10KNo$0.8 / $3.2$0.2 / —tools · streaming · caching · batchActive2024-12-052024-10 Voyage Code 3voyage-code-3Voyage AIEmbeddingembeddings32K———$0.18 / ———Active2024-12-04—Amazon Nova CanvasRetirednova-canvasAmazonImageimages———————Retired2024-12-03—Amazon Nova ReelRetirednova-reelAmazonVideovideo———————Retired2024-12-03—Rerank v3.5rerank-v3.5CohereRerankrerank4.1K——————Active2024-12-02—Marengo 2.7Retiredmarengo2.7Twelve LabsEmbeddingembeddings———————Retired2024-12-02—FLUX.1 Fill [pro]flux-pro-1.0-fillBlack Forest LabsImageimages————— / $0.05 / image——Active2024-11-21—Mistral Large 2.1Retiredmistral-large-2411Mistral AIChatchat · batch131.1K—————tools · structured_output · batchRetired2024-11-18—Pixtral LargeRetiredpixtral-large-2411Mistral AIChatchat · batch131.1K—————tools · structured_output · batchRetired2024-11-18—Voyage Multimodal 3voyage-multimodal-3Voyage AIEmbeddingembeddings32K——————Active2024-11-12—FLUX1.1 [pro] Ultraflux-pro-1.1-ultraBlack Forest LabsImageimages————— / $0.06 / image——Active2024-11-06—Mistral ModerationRetiredmistral-moderation-2411Mistral AIChatmoderation · batch8.2K—————batchRetired2024-11-06—Jina CLIP v2jina-clip-v2Jina AIEmbeddingembeddings8.2K8.2K——$0.05 / ———Active2024-11-05—Stable Diffusion 3.5 Mediumsd3.5-mediumStability AIImageimages————— / $0.035 / image——Active2024-10-29—Aya Expanse 32Bc4ai-aya-expanse-32bCohereChatchat128K—4K—$0.5 / $1.5——Active2024-10-24—Claude Sonnet 3.5 (Oct 2024)Retiredclaude-3-5-sonnet-20241022AnthropicChatmessages · batch200K—8.2KNo$3 / $15$0.3 / $3.75tools · caching · batchRetired2024-10-222024-04 Stable Diffusion 3.5 Largesd3.5-largeStability AIImageimages————— / $0.065 / image——Active2024-10-22—Stable Diffusion 3.5 Large Turbosd3.5-large-turboStability AIImageimages————— / $0.04 / image——Active2024-10-22—SonicRetiredsonicCartesiaAudioaudio———————Retired2024-10-19—Ministral 3BRetiredministral-3b-2410Mistral AIChatchat · batch131.1K—————tools · structured_output · batchRetired2024-10-09—Ministral 8BRetiredministral-8b-2410Mistral AIChatchat · batch131.1K—————tools · structured_output · batchRetired2024-10-09—Palmyra X4palmyra-x4WriterChatchat——4.1K—$2.5 / $10—tools · structured_output · streamingDeprecated2024-10-09—FLUX1.1 [pro]flux-pro-1.1Black Forest LabsImageimages————— / $0.04 / image——Active2024-10-02—omni-moderation-latestomni-moderation-latestOpenAIChatmoderation · batch———No$0 / ——batchActive2024-09-26—Jina Embeddings v3jina-embeddings-v3Jina AIEmbeddingembeddings8.2K8.2K——$0.05 / ———Deprecated2024-09-18—Mistral Small 2.0Retiredmistral-small-2409Mistral AIChatchat · batch32.8K—————tools · structured_output · batchRetired2024-09-17—Pixtral 12BRetiredpixtral-12b-2409Mistral AIChatchat · batch131.1K—————tools · structured_output · batchRetired2024-09-11—Paraformer-Realtime-V2paraformer-realtime-v2AlibabaChatrealtime———No¥0.0002 / — / second——Active2024-09-06—Paraformer-V2paraformer-v2AlibabaChataudio———No¥0.0001 / — / second——Active2024-09-06—Jina ColBERT v2jina-colbert-v2Jina AIRerankrerank8.2K8.2K——$0.05 / ———Active2024-08-31—Command Rcommand-r-08-2024CohereChatchat128K—4K—$0.15 / $0.6—tools · structured_outputActive2024-08-302024-06 Command R+command-r-plus-08-2024CohereChatchat128K—4K—$2.5 / $10—tools · structured_outputActive2024-08-302024-06 Jamba Large 1.5Retiredjamba-large-1.5AI21 LabsChatchat262.1K——————Retired2024-08-22—Jamba Mini 1.5Retiredjamba-mini-1.5AI21 LabsChatchat262.1K——————Retired2024-08-22—Mistral Large 2.0Retiredmistral-large-2407Mistral AIChatchat131.1K——————Retired2024-07-24—Mistral Nemo 12BRetiredopen-mistral-nemo-2407Mistral AIChatchat · batch131.1K—————tools · structured_output · batchRetired2024-07-18—GPT-4o Minigpt-4o-miniOpenAIChatchat · responses · batch128K—16.4K—$0.15 / $0.6$0.075 / —tools · structured_output · streaming · caching · batchActive2024-07-182023-10-01 Codestral Mamba 7BRetiredopen-codestral-mambaMistral AIChatchat262.1K——————Retired2024-07-16—Text Embedding V3text-embedding-v3AlibabaEmbeddingembeddings—8.2K—No$0.07 / ———Active2024-07-12—Pegasus 1.1Retiredpegasus1.1Twelve LabsChatgenerate———————Retired2024-07-07—Jina Reranker v2 Base Multilingualjina-reranker-v2-base-multilingualJina AIRerankrerank1K———$0.05 / ———Deprecated2024-06-25—Stable Image Ultrastable-image-ultraStability AIImageimages————— / $0.08 / image——Active2024-06-05—Voyage Finance 2voyage-finance-2Voyage AIEmbeddingembeddings32K———$0.12 / ———Active2024-06-03—CodestralRetiredcodestral-2405Mistral AIChatchat32.8K——————Retired2024-05-29—Gemini 1.5 FlashRetiredgemini-1.5-flashGoogleChatgenerate1.05M1.05M8.2K—$0.075 / $0.3$0.0187 / —tools · structured_output · cachingRetired2024-05-24—Gemini 1.5 ProRetiredgemini-1.5-proGoogleChatgenerate2.1M2.1M8.2K—$1.25 / $5$0.3125 / —tools · structured_output · cachingRetired2024-05-24—Mistral 7BRetiredopen-mistral-7bMistral AIChatchat32.8K——————Retired2024-05-22—GPT-4ogpt-4oOpenAIChatchat · responses · batch128K—16.4K—$2.5 / $10$1.25 / —tools · structured_output · streaming · caching · batchActive2024-05-132023-10-01 Amazon Titan Text Embeddings V2titan-embed-text-v2AmazonEmbeddingembeddings———No$0.02 / ———Active2024-04-30—Mixtral 8x22BRetiredopen-mixtral-8x22bMistral AIChatchat65.5K——————Retired2024-04-17—Voyage Law 2voyage-law-2Voyage AIEmbeddingembeddings16K———$0.12 / ———Active2024-04-15—Rerank English v3.0rerank-english-v3.0CohereRerankrerank4.1K——————Active2024-04-09—Rerank Multilingual v3.0rerank-multilingual-v3.0CohereRerankrerank4.1K——————Active2024-04-09—Text Embedding 004Retiredtext-embedding-004GoogleEmbeddingembeddings—2K—No———Retired2024-04-09—GPT-4 Turbogpt-4-turboOpenAIChatchat · responses · batch128K—4.1K—$10 / $30—tools · streaming · batchDeprecated2024-04-092023-12-01 Command R+ (04-2024)Retiredcommand-r-plus-04-2024CohereChatchat128K—4K———toolsRetired2024-04-04—Stable Image Corestable-image-coreStability AIImageimages————— / $0.03 / image——Active2024-03-21—Command R (03-2024)Retiredcommand-r-03-2024CohereChatchat128K—4K———toolsRetired2024-03-11—Claude Opus 3Retiredclaude-3-opusAnthropicChatmessages · batch200K—4.1KNo$15 / $75$1.5 / $18.75tools · caching · batchRetired2024-03-042023-08 Claude Sonnet 3Retiredclaude-3-sonnetAnthropicChatmessages200K—4.1K—$3 / $15——Retired2024-03-042023-08 Mistral Large 1.0Retiredmistral-large-2402Mistral AIChatchat32.8K——————Retired2024-02-26—Mistral Small 1.0Retiredmistral-small-2402Mistral AIChatchat32.8K——————Retired2024-02-26—Gemini 1.0 ProRetiredgemini-1.0-proGoogleChatgenerate——————toolsRetired2024-02-15—Nomic Embed Text v1.5nomic-embed-text-v1.5NomicEmbeddingembeddings8.2K——————Active2024-02-14—Nomic Embed Text v1nomic-embed-text-v1NomicEmbeddingembeddings8.2K——————Active2024-02-01—text-embedding-3-largetext-embedding-3-largeOpenAIEmbeddingembeddings · batch—8.2K——$0.13 / ——batchActive2024-01-252021-09 text-embedding-3-smalltext-embedding-3-smallOpenAIEmbeddingembeddings · batch—8.2K——$0.02 / ——batchActive2024-01-252021-09 Hunyuan-Embeddinghunyuan-embeddingTencentEmbeddingembeddings———No¥0.7 / ———Active2024-01-05—Mistral Embedmistral-embed-2312Mistral AIEmbeddingembeddings · batch8.2K———$0.1 / ——batchActive2023-12-11—Mistral Medium 1.0Retiredmistral-medium-2312Mistral AIChatchat32.8K——————Retired2023-12-11—Mixtral 8x7BRetiredopen-mixtral-8x7bMistral AIChatchat32.8K——————Retired2023-12-11—Amazon Titan Multimodal Embeddings G1titan-embed-image-v1AmazonEmbeddingembeddings———No$0.8 / ———Active2023-11-29—Claude 2.1Retiredclaude-2.1AnthropicChatmessages · completions200K—4.1K—$8 / $24——Retired2023-11-21—Amazon Titan Embeddings G1 - Texttitan-embed-text-v1AmazonEmbeddingembeddings———No$0.1 / ———Active2023-09-28—Nova-2nova-2DeepgramChataudio———————Active2023-09-19—Claude Instant 1.2Retiredclaude-instant-1.2AnthropicChatmessages · completions100K—4.1K—$0.8 / $2.4——Retired2023-08-09—Claude 2Retiredclaude-2.0AnthropicChatmessages · completions100K—4.1K—$8 / $24——Retired2023-07-11—SEA-Guardsea-guardAI SingaporeChatmoderation131.1K——————Active——Fun-ASRfun-asrAlibabaChataudio———No$0 / — / second——Active——GTE-RerankRetiredgte-rerankAlibabaRerankrerank———————Retired——Qwen-Audio-3.0-ASR-Flashqwen-audio-3.0-asr-flashAlibabaChataudio———No$0 / — / second——Active——Qwen-Audio-3.0-ASR-Flash-Filetransqwen-audio-3.0-asr-flash-filetransAlibabaChataudio———No$0 / — / second——Active——Qwen-Audio-3.1-ASR-Flashqwen-audio-3.1-asr-flashAlibabaChataudio8.2K7.2K1KNo$0.15 / $0.47——Active——Qwen-Audio-3.1-ASR-Flash-Filetransqwen-audio-3.1-asr-flash-filetransAlibabaChataudio8.2K8.2K1KNo$0.15 / $0.47——Active——Qwen-Audio-3.1-ASR-Flash-Messageqwen-audio-3.1-asr-flash-messageAlibabaChataudio————$0.93 / $0.7——Active——Qwen-Audio-3.1-ASR-Flash-Streamingqwen-audio-3.1-asr-flash-streamingAlibabaChatrealtime8.2K—1KNo$0.93 / $0.7——Active——Qwen-Audio-3.1-TTS-Flashqwen-audio-3.1-tts-flashAlibabaAudioaudio———No¥1.5 / ¥12——Active——Qwen-Coder-PlusRetiredqwen-coder-plusAlibabaChatchat131.1K129K8.2K—$0.502 / $1.004——Retired——Qwen-Coder-TurboRetiredqwen-coder-turboAlibabaChatchat131.1K129K8.2K—$0.287 / $0.861——Retired——Qwen-Flash-Characterqwen-flash-characterAlibabaChatchat32.8K32.8K32.8K—$0.05 / $0.4—streaming · cachingActive——Qwen-Longqwen-longAlibabaChatchat10M10M32.8K—¥0.5 / ¥2—structured_output · batchActive——Qwen-Math-PlusRetiredqwen-math-plusAlibabaChatchat4.1K3.1K3.1K—$0.574 / $1.721——Retired——Qwen-Math-TurboRetiredqwen-math-turboAlibabaChatchat4.1K3.1K3.1K—$0.287 / $0.861——Retired——Qwen-Maxqwen-maxAlibabaChatchat32.8K30.7K8.2KNo$1.6 / $6.4—structured_output · streaming · cachingActive——Qwen-Omni-TurboRetiredqwen-omni-turboAlibabaChatchat32.8K30.7K2KNo——streamingRetired——Qwen-Plusqwen-plusAlibabaChatchat · messages1M998K32.8KYes$0.4 / $1.2$0.04 / $0.5tools · structured_output · streaming · cachingActive——Qwen-Plus-Characterqwen-plus-characterAlibabaChatchat131.1K131.1K32.8K—$0.5 / $1.4—streaming · cachingActive——Qwen-TTSRetiredqwen-ttsAlibabaAudioaudio———————Retired——Qwen-TTS-RealtimeRetiredqwen-tts-realtimeAlibabaAudiorealtime———————Retired——Qwen-TurboRetiredqwen-turboAlibabaChatchat131.1K98.3K16.4KYes$0.05 / $0.2—structured_output · streaming · cachingRetired——Qwen-VL-MaxRetiredqwen-vl-maxAlibabaChatchat131.1K129K8.2KNo$0.8 / $3.2—structured_output · streaming · cachingRetired——Qwen-VL-OCRRetiredqwen-vl-ocrAlibabaChatchat——8.2KNo$0.07 / $0.16—streamingRetired——Qwen-VL-PlusRetiredqwen-vl-plusAlibabaChatchat131.1K129K8.2KNo$0.21 / $0.63—streamingRetired——Qwen1.5-110B-ChatRetiredqwen1.5-110b-chatAlibabaChatchat8K6K2K————Retired——Qwen1.5-14B-ChatRetiredqwen1.5-14b-chatAlibabaChatchat8K6K2K————Retired——Qwen1.5-32B-ChatRetiredqwen1.5-32b-chatAlibabaChatchat8K6K2K————Retired——Qwen1.5-72B-ChatRetiredqwen1.5-72b-chatAlibabaChatchat8K6K2K————Retired——Qwen1.5-7B-ChatRetiredqwen1.5-7b-chatAlibabaChatchat8K6K2K————Retired——Qwen2-57B-A14B-InstructRetiredqwen2-57b-a14b-instructAlibabaChatchat65.5K63.5K6.1K————Retired——Qwen2-72B-InstructRetiredqwen2-72b-instructAlibabaChatchat131.1K128K6.1K————Retired——Qwen2-7B-InstructRetiredqwen2-7b-instructAlibabaChatchat131.1K128K6.1K————Retired——Qwen2.5-14B-InstructRetiredqwen2.5-14b-instructAlibabaChatchat131.1K129K8.2K—$0.35 / $1.4——Retired——Qwen2.5-14B-Instruct-1MRetiredqwen2.5-14b-instruct-1mAlibabaChatchat1.01M1M8.2K—$0.805 / $3.22——Retired——Qwen2.5-32B-InstructRetiredqwen2.5-32b-instructAlibabaChatchat131.1K129K8.2K—$0.7 / $2.8——Retired——Qwen2.5-72B-InstructRetiredqwen2.5-72b-instructAlibabaChatchat131.1K129K8.2K—$1.4 / $5.6——Retired——Qwen2.5-7B-InstructRetiredqwen2.5-7b-instructAlibabaChatchat131.1K129K8.2K—$0.175 / $0.7——Retired——Qwen2.5-7B-Instruct-1MRetiredqwen2.5-7b-instruct-1mAlibabaChatchat1.01M1M8.2K—$0.368 / $1.47——Retired——Qwen2.5-VL-32B-InstructRetiredqwen2.5-vl-32b-instructAlibabaChatchat131.1K129K8.2K—$1.4 / $4.2——Retired——Qwen2.5-VL-3B-InstructRetiredqwen2.5-vl-3b-instructAlibabaChatchat131.1K129K8.2K—$0.21 / $0.63——Retired——Qwen2.5-VL-72B-InstructRetiredqwen2.5-vl-72b-instructAlibabaChatchat131.1K129K8.2K—$2.8 / $8.4——Retired——Qwen2.5-VL-7B-InstructRetiredqwen2.5-vl-7b-instructAlibabaChatchat131.1K129K8.2K—$0.35 / $1.05——Retired——Qwen3-0.6BRetiredqwen3-0.6bAlibabaChatchat32.8K30.7K8.2KYes$0.11 / $0.42——Retired——Qwen3-1.7BRetiredqwen3-1.7bAlibabaChatchat32.8K30.7K8.2KYes$0.11 / $0.42——Retired——Qwen3-4BRetiredqwen3-4bAlibabaChatchat131.1K129K8.2KYes$0.11 / $0.42——Retired——Qwen3-Omni-30B-A3B-CaptionerRetiredqwen3-omni-30b-a3b-captionerAlibabaChatchat65.5K32.8K32.8K—$3.81 / $3.06——Retired——Qwen3-Omni-Flashqwen3-omni-flashAlibabaChatchat65.5K49.2K16.4KYes——tools · streamingActive——Qwen3-Omni-Flash-RealtimeRetiredqwen3-omni-flash-realtimeAlibabaChatrealtime65.5K49.2K16.4KNo——streamingRetired——Qwen3-TTS-Flashqwen3-tts-flashAlibabaAudioaudio———No$10 / — / 1M characters——Active——Qwen3-TTS-Flash-Realtimeqwen3-tts-flash-realtimeAlibabaAudiorealtime———No$13 / — / 1M characters——Active——Qwen3.7-Text-Embedding-Flashqwen3.7-text-embedding-flashAlibabaEmbeddingembeddings131.1K131.1K—No¥0.125 / ———Active——Qwen3.7-Text-Rerankqwen3.7-text-rerankAlibabaRerankrerank30K30K—No¥0.5 / ———Active——SenseVoice V1Retiredsensevoice-v1AlibabaChataudio———————Retired——Amazon Nova SonicRetirednova-sonicAmazonAudiorealtime———————Retired——Ling-1TRetiredling-1tAnt GroupChatchat———————Retired——Ling-2.5-1Tling-2.5-1tAnt GroupChatchat———————Deprecated——Ling-3.1-flashling-3.1-flashAnt GroupChatchat262.1K——Yes——tools · streamingActive——Ring-1TRetiredring-1tAnt GroupChatchat———Yes———Retired——Ring-2.5-1Tring-2.5-1tAnt GroupChatchat———Yes———Deprecated——Claude 1.0Retiredclaude-1.0AnthropicChatcompletions———————Retired——Claude 1.1Retiredclaude-1.1AnthropicChatcompletions———————Retired——Claude 1.2Retiredclaude-1.2AnthropicChatcompletions———————Retired——Claude 1.3Retiredclaude-1.3AnthropicChatcompletions———————Retired——Claude Haiku 3.5Retiredclaude-3-5-haikuAnthropicChatmessages · batch200K—8.2KNo$0.8 / $4$0.08 / $1tools · caching · batchRetired—2024-07 Claude Sonnet 3.5 (Jun 2024)Retiredclaude-3-5-sonnet-20240620AnthropicChatmessages · batch200K—8.2KNo$3 / $15$0.3 / $3.75tools · caching · batchRetired——Claude Haiku 3Retiredclaude-3-haikuAnthropicChatmessages · batch200K—4.1KNo$0.25 / $1.25$0.03 / $0.3tools · caching · batchRetired—2023-08 Claude Instant 1.0Retiredclaude-instant-1.0AnthropicChatcompletions———————Retired——Claude Instant 1.1Retiredclaude-instant-1.1AnthropicChatcompletions———————Retired——Universal-2universal-2AssemblyAIChataudio————$0.15 / — / hour——Active——Universal-3.6 Pro Streaminguniversal-3-6-proAssemblyAIChatrealtime————$0.45 / — / hour——Active——Universal-Streaming Englishuniversal-streaming-englishAssemblyAIChatrealtime————$0.15 / — / hour——Active——Universal-Streaming Multilingualuniversal-streaming-multilingualAssemblyAIChatrealtime————$0.15 / — / hour——Active——Baichuan-M2-Plusbaichuan-m2-plusBaichuanChatchat32K—32KNo¥10 / ¥30—streamingActive——Baichuan-M3-Plusbaichuan-m3-plusBaichuanChatchat32K—32KNo¥5 / ¥9—streamingActive——Baichuan2-Turbo-192kRetiredbaichuan2-turbo-192kBaichuanChatchat————¥16 / ¥16——Retired——Embedding-V1embedding-v1BaiduEmbeddingembeddings384——No¥0.5 / ———Active——ERNIE-3.5-4K-0205Retiredernie-3.5-4k-0205BaiduChatchat———————Retired——ERNIE-3.5-8KRetiredernie-3.5-8kBaiduChatchat———————Retired——ERNIE-3.5-8K-0613Retiredernie-3.5-8k-0613BaiduChatchat———————Retired——ERNIE-3.5-8K-0701Retiredernie-3.5-8k-0701BaiduChatchat———————Retired——ERNIE-3.5-8K-1222Retiredernie-3.5-8k-1222BaiduChatchat———————Retired——ERNIE-4.0-8KRetiredernie-4.0-8kBaiduChatchat———————Retired——ERNIE-4.0-Turbo-128KRetiredernie-4.0-turbo-128kBaiduChatchat———————Retired——ERNIE-4.0-Turbo-8KRetiredernie-4.0-turbo-8kBaiduChatchat———————Retired——ERNIE-4.5-0.3BRetiredernie-4.5-0.3bBaiduChatchat———————Retired——ERNIE-4.5-21B-A3BRetiredernie-4.5-21b-a3bBaiduChatchat———————Retired——ERNIE-4.5-21B-A3B-ThinkingRetiredernie-4.5-21b-a3b-thinkingBaiduChatchat———Yes———Retired——ERNIE-4.5-8K-PreviewRetiredernie-4.5-8k-previewBaiduChatchat———————Retired——ERNIE-4.5-Turbo-128K-PreviewRetiredernie-4.5-turbo-128k-previewBaiduChatchat———————Retired——ERNIE 4.5 Turbo (20260402)ernie-4.5-turbo-20260402BaiduChatchat · messages131.1K126K12.3K—¥0.8 / ¥3.2¥0.2 / —streaming · cachingDeprecated——ERNIE-4.5-Turbo-LatestRetiredernie-4.5-turbo-latestBaiduChatchat———————Retired——ERNIE-4.5-Turbo-VL-32K-PreviewRetiredernie-4.5-turbo-vl-32k-previewBaiduChatchat———————Retired——ERNIE-4.5-Turbo-VL-LatestRetiredernie-4.5-turbo-vl-latestBaiduChatchat———————Retired——ERNIE-4.5-Turbo-VL-PreviewRetiredernie-4.5-turbo-vl-previewBaiduChatchat———————Retired——ERNIE-4.5-VL-28B-A3BRetiredernie-4.5-vl-28b-a3bBaiduChatchat———————Retired——ERNIE 5.0 Thinking Expernie-5.0-thinking-expBaiduChatchat · messages131.1K121.9K65.5K—¥6 / ¥24—streamingPreview——ERNIE-Character-8KRetiredernie-character-8kBaiduChatchat———————Retired——ERNIE-Character-Fiction-8KRetiredernie-character-fiction-8kBaiduChatchat———————Retired——ERNIE-Character-Fiction-8K-PreviewRetiredernie-character-fiction-8k-previewBaiduChatchat———————Retired——ERNIE-Functions-8KRetiredernie-functions-8kBaiduChatchat———————Retired——ERNIE-Image-TurboRetiredernie-image-turboBaiduImageimages———————Retired——ERNIE-Lite-8KRetiredernie-lite-8kBaiduChatchat———————Retired——ERNIE-Lite-8k-0922Retiredernie-lite-8k-0922BaiduChatchat———————Retired——ERNIE-Lite-Pro-128KRetiredernie-lite-pro-128kBaiduChatchat———————Retired——ERNIE-Novel-8KRetiredernie-novel-8kBaiduChatchat———————Retired——ERNIE-Speed-128KRetiredernie-speed-128kBaiduChatchat———————Retired——ERNIE-Speed-8KRetiredernie-speed-8kBaiduChatchat———————Retired——ERNIE-Speed-Pro-128KRetiredernie-speed-pro-128kBaiduChatchat———————Retired——ERNIE-Tiny-8KRetiredernie-tiny-8kBaiduChatchat———————Retired——ERNIE-X1-Turbo-32KRetiredernie-x1-turbo-32kBaiduChatchat———————Retired——ERNIE-X1-Turbo-32K-PreviewRetiredernie-x1-turbo-32k-previewBaiduChatchat———————Retired——ERNIE-X1-Turbo-LatestRetiredernie-x1-turbo-latestBaiduChatchat———————Retired——MuseSteamer-2.0-Lite-I2VRetiredmusesteamer-2.0-lite-i2vBaiduVideovideo———————Retired——MuseSteamer-2.0-Pro-I2VRetiredmusesteamer-2.0-pro-i2vBaiduVideovideo———————Retired——MuseSteamer-2.0-Turbo-I2VRetiredmusesteamer-2.0-turbo-i2vBaiduVideovideo———————Retired——MuseSteamer-2.0-Turbo-I2V-AudioRetiredmusesteamer-2.0-turbo-i2v-audioBaiduVideovideo———————Retired——MuseSteamer-2.1-Lite-I2VRetiredmusesteamer-2.1-lite-i2vBaiduVideovideo———————Retired——MuseSteamer-2.1-Turbo-I2VRetiredmusesteamer-2.1-turbo-i2vBaiduVideovideo———————Retired——MuseSteamer Air Imagemusesteamer-air-imageBaiduImageimages———No— / ¥0.05 / image——Active——Qianfan-70BRetiredqianfan-70bBaiduChatchat———————Retired——Qianfan-8BRetiredqianfan-8bBaiduChatchat———————Retired——Qianfan-Agent-Intent-32KRetiredqianfan-agent-intent-32kBaiduChatchat———————Retired——Qianfan-Agent-Lite-8KRetiredqianfan-agent-lite-8kBaiduChatchat———————Retired——Qianfan-Agent-Speed-32KRetiredqianfan-agent-speed-32kBaiduChatchat———————Retired——Qianfan-Agent-Speed-8KRetiredqianfan-agent-speed-8kBaiduChatchat———————Retired——Qianfan-BLOOMZ-7B-compressedRetiredqianfan-bloomz-7b-compressedBaiduChatchat———————Retired——Qianfan-Check-VLRetiredqianfan-check-vlBaiduChatchat———————Retired——Qianfan-Chinese-Llama-2-13BRetiredqianfan-chinese-llama-2-13bBaiduChatchat———————Retired——Qianfan-Chinese-Llama-2-70BRetiredqianfan-chinese-llama-2-70bBaiduChatchat———————Retired——Qianfan-Chinese-Llama-2-7BRetiredqianfan-chinese-llama-2-7bBaiduChatchat———————Retired——Qianfan-CompositionRetiredqianfan-compositionBaiduChatchat———————Retired——Qianfan-CorrectRetiredqianfan-correctBaiduChatchat———————Retired——Qianfan-Dynamic-8kRetiredqianfan-dynamic-8kBaiduChatchat———————Retired——Qianfan-EngCard-VLRetiredqianfan-engcard-vlBaiduChatchat———————Retired——Qianfan-Lightning-128B-A19BRetiredqianfan-lightning-128b-a19bBaiduChatchat———————Retired——Qianfan-Llama-VL-8BRetiredqianfan-llama-vl-8bBaiduChatchat———————Retired——Qianfan-MultiPicOCRRetiredqianfan-multipicocrBaiduChatchat———————Retired——Qianfan-OCRqianfan-ocrBaiduChatocr · chat · messages32.8K32.8K28.7KYes¥0.45 / ¥1.8——Active——Qianfan-OCR-FastRetiredqianfan-ocr-fastBaiduChatchat———————Retired——Qianfan-PublicOpinion-ClassificationRetiredqianfan-publicopinion-classificationBaiduChatchat———————Retired——Qianfan-QI-VLRetiredqianfan-qi-vlBaiduChatchat———————Retired——Qianfan-SinglePicOCRRetiredqianfan-singlepicocrBaiduChatchat———————Retired——Qianfan-Sug-8KRetiredqianfan-sug-8kBaiduChatchat———————Retired——Qianfan-ToyTalkRetiredqianfan-toytalkBaiduChatchat———————Retired——Qianfan-VL-1.5-FlashRetiredqianfan-vl-1.5-flashBaiduChatchat———————Retired——Qianfan-VL-70BRetiredqianfan-vl-70bBaiduChatchat———————Retired——Qianfan-VL-8BRetiredqianfan-vl-8bBaiduChatchat———————Retired——FLUX.1 Expand [pro]flux-pro-1.0-expandBlack Forest LabsImageimages———————Active——Doubao-1.5-lite-32kRetireddoubao-1-5-lite-32kByteDanceChatchat———————Retired——Doubao-1.5-pro-256kRetireddoubao-1-5-pro-256kByteDanceChatchat———————Retired——Doubao-1.5-pro-32kRetireddoubao-1-5-pro-32kByteDanceChatchat———————Retired——Doubao-1.5-pro-32k-characterRetireddoubao-1-5-pro-32k-characterByteDanceChatchat———————Retired——Doubao-1.5-thinking-proRetireddoubao-1-5-thinking-proByteDanceChatchat———Yes———Retired——Doubao-1.5-thinking-pro-mRetireddoubao-1-5-thinking-pro-mByteDanceChatchat———Yes———Retired——Doubao-1.5-thinking-vision-proRetireddoubao-1-5-thinking-vision-proByteDanceChatchat———Yes———Retired——Doubao-1.5-UI-TARSRetireddoubao-1-5-ui-tarsByteDanceChatchat———————Retired——Doubao-1.5-vision-liteRetireddoubao-1-5-vision-liteByteDanceChatchat———————Retired——Doubao-1.5-vision-proRetireddoubao-1-5-vision-proByteDanceChatchat———————Retired——Doubao-1.5-vision-pro-32kRetireddoubao-1-5-vision-pro-32kByteDanceChatchat———————Retired——Doubao-Embedding-Visiondoubao-embedding-visionByteDanceEmbeddingembeddings131.1K——No¥0.7 / ———Active——Doubao-lite-128kRetireddoubao-lite-128kByteDanceChatchat———————Retired——Doubao-lite-32kRetireddoubao-lite-32kByteDanceChatchat———————Retired——Doubao-lite-32k-characterRetireddoubao-lite-32k-characterByteDanceChatchat———————Retired——Doubao-lite-4kRetireddoubao-lite-4kByteDanceChatchat———————Retired——Doubao-lite-4k-characterRetireddoubao-lite-4k-characterByteDanceChatchat———————Retired——Doubao-pro-128kRetireddoubao-pro-128kByteDanceChatchat———————Retired——Doubao-pro-256kRetireddoubao-pro-256kByteDanceChatchat———————Retired——Doubao-pro-32kRetireddoubao-pro-32kByteDanceChatchat———————Retired——Doubao-pro-32k-browsingRetireddoubao-pro-32k-browsingByteDanceChatchat———————Retired——Doubao-pro-32k-characterRetireddoubao-pro-32k-characterByteDanceChatchat———————Retired——Doubao-pro-32k-functioncallRetireddoubao-pro-32k-functioncallByteDanceChatchat———————Retired——Doubao-pro-4kRetireddoubao-pro-4kByteDanceChatchat———————Retired——Doubao-pro-4k-browsingRetireddoubao-pro-4k-browsingByteDanceChatchat———————Retired——Doubao-pro-4k-characterRetireddoubao-pro-4k-characterByteDanceChatchat———————Retired——Doubao-pro-4k-functioncallRetireddoubao-pro-4k-functioncallByteDanceChatchat———————Retired——Doubao-SeaweedRetireddoubao-seaweedByteDanceVideovideo———————Retired——Doubao-Seed-1.6Retireddoubao-seed-1-6ByteDanceChatchat———————Retired——Doubao-Seed-1.6-flashRetireddoubao-seed-1-6-flashByteDanceChatchat———————Retired——Doubao-Seed-1.6-liteRetireddoubao-seed-1-6-liteByteDanceChatchat———————Retired——Doubao-Seed-1.6-thinkingRetireddoubao-seed-1-6-thinkingByteDanceChatchat———Yes———Retired——Doubao-Seed-1.6-visionRetireddoubao-seed-1-6-visionByteDanceChatchat———————Retired——Doubao-Seed-2.1-Litedoubao-seed-2-1-liteByteDanceChatchat · responses1.05M1.05M262.1Knone · minimal · low · medium · high · xhigh · max¥0.8 / ¥2.7¥0.16 / —tools · structured_output · streaming · caching · batchActive——Doubao-Seed-Characterdoubao-seed-characterByteDanceChatchat · responses131.1K98.3K32.8Knone · minimal · low · medium · high · xhigh · max¥0.8 / ¥2¥0.16 / —tools · structured_output · streaming · caching · batchActive——Doubao-Seed-Code-previewRetireddoubao-seed-code-previewByteDanceChatchat———————Retired——Doubao-Seed-Evolvingdoubao-seed-evolvingByteDanceChatchat · responses1.05M1.05M262.1Knone · minimal · low · medium · high · xhigh · max¥6 / ¥30¥1.2 / —tools · structured_output · streaming · cachingActive——Doubao-Seed-Translationdoubao-seed-translationByteDanceChatchat · responses4.1K1K3.1KNo¥1.2 / ¥3.6—streaming · batchActive——Doubao-Seed3D-1.0Retireddoubao-seed3d-1-0ByteDance3D3d———————Retired——Doubao-Seed3D-2.0doubao-seed3d-2-0ByteDance3D3d———No— / ¥2.4 / request——Active——Doubao-Seedance-1.0-liteRetireddoubao-seedance-1-0-liteByteDanceVideovideo———————Retired——Doubao-Seedance-1.0-Prodoubao-seedance-1-0-proByteDanceVideovideo———No— / ¥15——Deprecated——Doubao-Seedance-1.0-Pro-Fastdoubao-seedance-1-0-pro-fastByteDanceVideovideo———No— / ¥4.2——Deprecated——Doubao-Seedance-1.5-proRetireddoubao-seedance-1-5-proByteDanceVideovideo———————Retired——Doubao-Seedance-2.0doubao-seedance-2-0ByteDanceVideovideo———No— / ¥16——Active——Doubao-Seedance-2.0-Fastdoubao-seedance-2-0-fastByteDanceVideovideo———No— / ¥22——Active——Doubao-Seedance-2.0-Minidoubao-seedance-2-0-miniByteDanceVideovideo———No— / ¥14——Active——Doubao-Seedance-2.5doubao-seedance-2-5ByteDanceVideovideo———No— / ¥42——Active——Doubao-SeedEdit-3.0-i2iRetireddoubao-seededit-3-0-i2iByteDanceImageimages———————Retired——Doubao-Seedream-3.0-t2iRetireddoubao-seedream-3-0-t2iByteDanceImageimages———————Retired——Doubao-Seedream-4.0doubao-seedream-4-0ByteDanceImageimages———No— / ¥0.2 / image——Deprecated——Doubao-Seedream-4.5doubao-seedream-4-5ByteDanceImageimages———No— / ¥0.25 / image——Deprecated——Doubao-Seedream-5.0doubao-seedream-5-0ByteDanceImageimages———No— / ¥0.22 / image——Deprecated——Doubao-Seedream-5.0-Flashdoubao-seedream-5-0-flashByteDanceImageimages———No— / ¥0.12 / image——Active——Doubao-Seedream-5.0-Prodoubao-seedream-5-0-proByteDanceImageimages———No— / ¥0.3 / image——Active——Doubao-vision-lite-32kRetireddoubao-vision-lite-32kByteDanceChatchat———————Retired——Doubao-vision-pro-32kRetireddoubao-vision-pro-32kByteDanceChatchat———————Retired——Aya Expanse 8BRetiredc4ai-aya-expanse-8bCohereChatchat8K—4K————Retired——Aya Vision 8BRetiredc4ai-aya-vision-8bCohereChatchat16K—4K————Retired——CommandRetiredcommandCohereChatchat4K—4K————Retired——Command LightRetiredcommand-lightCohereChatchat4K—4K————Retired——Embed English Light v2.0Retiredembed-english-light-v2.0CohereEmbeddingembeddings512——————Retired——Embed English Light v3.0embed-english-light-v3.0CohereEmbeddingembeddings512——————Active——Embed English v2.0Retiredembed-english-v2.0CohereEmbeddingembeddings512——————Retired——Embed English v3.0embed-english-v3.0CohereEmbeddingembeddings512——————Active——Embed Multilingual Light v3.0embed-multilingual-light-v3.0CohereEmbeddingembeddings512——————Active——Embed Multilingual v2.0Retiredembed-multilingual-v2.0CohereEmbeddingembeddings256——————Retired——Embed Multilingual v3.0embed-multilingual-v3.0CohereEmbeddingembeddings512——————Active——Rerank English v2.0Retiredrerank-english-v2.0CohereRerankrerank512——————Retired——Rerank Multilingual v2.0Retiredrerank-multilingual-v2.0CohereRerankrerank512——————Retired——Flux General (Multilingual)flux-general-multiDeepgramChataudio————$0.0078 / — / minute——Active——Nova-2 Air Traffic Controlnova-2-atcDeepgramChataudio———————Active——Nova-2 Automotivenova-2-automotiveDeepgramChataudio———————Active——Nova-2 Conversational AInova-2-conversationalaiDeepgramChataudio———————Active——Nova-2 Drive-Thrunova-2-drivethruDeepgramChataudio———————Active——Nova-2 Financenova-2-financeDeepgramChataudio———————Active——Nova-2 Medicalnova-2-medicalDeepgramChataudio———————Active——Nova-2 Meetingnova-2-meetingDeepgramChataudio———————Active——Nova-2 Phone Callnova-2-phonecallDeepgramChataudio———————Active——Nova-2 Videonova-2-videoDeepgramChataudio———————Active——Nova-2 Voicemailnova-2-voicemailDeepgramChataudio———————Active——Nova-3 Medicalnova-3-medicalDeepgramChataudio———————Active——DeepSeek-ChatRetireddeepseek-chatDeepSeekChatchat131.1K—8.2KNo$0.28 / $0.42$0.028 / —tools · structured_output · cachingRetired——DeepSeek-ReasonerRetireddeepseek-reasonerDeepSeekChatchat131.1K—65.5KYes$0.28 / $0.42$0.028 / —tools · structured_output · cachingRetired——Eleven English Voice Changer v2eleven_english_sts_v2ElevenLabsAudioaudio————$0.12 / — / minute——Active——Eleven Flash v2eleven_flash_v2ElevenLabsAudioaudio————$40 / — / 1M characters——Active——Eleven Flash v2.5eleven_flash_v2_5ElevenLabsAudioaudio————$40 / — / 1M characters——Active——Eleven Multilingual Voice Changer v2eleven_multilingual_sts_v2ElevenLabsAudioaudio————$0.12 / — / minute——Active——Eleven Multilingual Text to Voice v2eleven_multilingual_ttv_v2ElevenLabsAudioaudio———————Active——Eleven Multilingual v2eleven_multilingual_v2ElevenLabsAudioaudio————$80 / — / 1M characters——Active——Eleven Text to Sound Effects v2eleven_text_to_sound_v2ElevenLabsAudioaudio————$0.12 / — / minute——Active——Eleven Text to Voice v3eleven_ttv_v3ElevenLabsAudioaudio———————Active——Eleven v3eleven_v3ElevenLabsAudioaudio————$80 / — / 1M characters——Active——Eleven v3 Conversationaleleven_v3_conversationalElevenLabsAudioaudio · realtime————$40 / — / 1M characters—streamingActive——Eleven Music v1music_v1ElevenLabsAudioaudio———————Active——Eleven Music v2music_v2ElevenLabsAudioaudio———————Active——Eleven Music v2.5music_v2_5ElevenLabsAudioaudio———————Active——Scribe v2scribe_v2ElevenLabsChataudio————$0.22 / — / hour——Active——Scribe v2 Realtimescribe_v2_realtimeElevenLabsChataudio · realtime————$0.39 / — / hour—streamingActive——PaLM 2 for Chat (chat-bison)Retiredchat-bisonGoogleChatchat———————Retired——Embedding 001Retiredembedding-001GoogleEmbeddingembeddings—2K—No———Retired——Gemini 3.5 Live Translate Previewgemini-3.5-live-translate-previewGoogleChatrealtime—131.1K65.5KNo$3.5 / $21——Preview—2025-01 Gemini Embedding Experimental 03-07Retiredgemini-embedding-exp-03-07GoogleEmbeddingembeddings—8.2K—No———Retired——PaLM 2 for Text (text-bison)Retiredtext-bisonGoogleChatcompletions———————Retired——openPangu-2.0-Flashopenpangu-2.0-flashHuaweiChatchat · messages524.3K512K131.1KYes¥0.8 / ¥1.6¥0.2 / —tools · streaming · cachingActive——openPangu-2.0-Proopenpangu-2.0-proHuaweiChatchat · messages524.3K512K131.1KYes¥3.2 / ¥14.5¥0.8 / —tools · streaming · cachingActive——Granite 13B Instruct v2Retiredgranite-13b-instruct-v2IBMChatchat———————Retired——Granite 3.2 8B InstructRetiredgranite-3-2-8b-instructIBMChatchat———————Retired——Granite 3.3 8B InstructRetiredgranite-3-3-8b-instructIBMChatchat———————Retired——Granite 3 8B InstructRetiredgranite-3-8b-instructIBMChatchat———————Retired——Granite 8B Code InstructRetiredgranite-8b-code-instructIBMChatchat———————Retired——Granite Embedding 107M MultilingualRetiredgranite-embedding-107m-multilingualIBMEmbeddingembeddings———————Retired——Granite Guardian 3 8BRetiredgranite-guardian-3-8bIBMChatchat———————Retired——Slate 125M English RetrieverRetiredslate-125m-english-rtrvrIBMEmbeddingembeddings———————Retired——Slate 30M English RetrieverRetiredslate-30m-english-rtrvrIBMEmbeddingembeddings———————Retired——Ideogram 2aideogram-2aIdeogramImageimages———————Active——Ideogram 3.0ideogram-3IdeogramImageimages———————Active——Ideogram 4.0ideogram-4IdeogramImageimages————— / $0.03 / image——Active——Ideogram 4.5ideogram-4-5IdeogramImageimages———————Active——Spark 4.0 Ultra4.0ultraiFlytekChatchat—32.8K32.8KNo——tools · streamingActive——Spark Progeneralv3iFlytekChatchat—8.2K8.2K———streamingActive——Spark LiteliteiFlytekChatchat—8.2K4.1K———streamingActive——Spark Pro-128Kpro-128kiFlytekChatchat—131.1K————streamingActive——Spark X2spark-xiFlytekChatchat—65.5K131.1KYes¥3 / ¥3—tools · streamingActive——Spark X2-Flashxsparkx2flashiFlytekChatchat262.1K——————Active——KAT-Coder-Pro V2.5kat-coder-pro-v2.5KuaishouChatchat————¥5 / ¥20¥1 / ——Active——Kling Image 1.0Retiredkling-image-v1KuaishouImageimages———————Retired——Kling Image 1.5Retiredkling-image-v1-5KuaishouImageimages———————Retired——Kling Image 2.0Retiredkling-image-v2KuaishouImageimages———————Retired——Kling 1.0Retiredkling-video-v1KuaishouVideovideo———————Retired——Kling 1.5Retiredkling-video-v1-5KuaishouVideovideo———————Retired——Lucid Realismlucid-realismLeonardo.AiImageimages———————Active——LTX-2 FastRetiredltx-2-fastLightricks (LTX)Videovideo———————Retired——LTX-2 ProRetiredltx-2-proLightricks (LTX)Videovideo———————Retired——Uni-1uni-1Luma AIImageimages————— / $0.0404 / image——Active——Uni-1 Maxuni-1-maxLuma AIImageimages————— / $0.1 / image——Active——Muse Spark 1.2 (Contributor)muse-spark-1.2-contributorMetaChatchat · responses1.05M——minimal · low · medium · high · xhigh$0.1 / $0.2$0.002 / —tools · structured_output · streaming · cachingActive——Muse Spark 1.3 (Contributor)muse-spark-1.3-contributorMetaChatchat · responses1.05M——minimal · low · medium · high · xhigh$0.1 / $0.2$0.002 / —tools · structured_output · streaming · cachingActive——MAI-Voice-2.1mai-voice-2.1MicrosoftAudioaudio———————Preview——MAI-Voice-2.1-Flashmai-voice-2.1-flashMicrosoftAudioaudio———————Preview——MiniMax-M2.1minimax-m2.1MiniMaxChatchat · messages204.8K—204.8KYes$0.3 / $1.2$0.03 / $0.375tools · streaming · cachingActive——MiniMax-M2.1-highspeedminimax-m2.1-highspeedMiniMaxChatchat · messages204.8K—204.8KYes$0.6 / $2.4$0.03 / $0.375tools · streaming · cachingActive——Music-2.6 FreeRetiredmusic-2.6-freeMiniMaxAudioaudio———————Retired——Music-3.0 FreeRetiredmusic-3.0-freeMiniMaxAudioaudio———————Retired——Music-Cover FreeRetiredmusic-cover-freeMiniMaxAudioaudio———————Retired——Kimi K2 0711 PreviewRetiredkimi-k2-0711-previewMoonshot AIChatchat131.1K—————tools · structured_output · cachingRetired——Kimi K2 0905 PreviewRetiredkimi-k2-0905-previewMoonshot AIChatchat262.1K—————tools · structured_output · cachingRetired——Kimi K2 ThinkingRetiredkimi-k2-thinkingMoonshot AIChatchat262.1K——Yes——tools · structured_output · cachingRetired——Kimi K2 Thinking TurboRetiredkimi-k2-thinking-turboMoonshot AIChatchat262.1K——Yes——tools · structured_output · cachingRetired——Kimi K2 Turbo PreviewRetiredkimi-k2-turbo-previewMoonshot AIChatchat262.1K—————tools · structured_output · cachingRetired——Kimi K2.5Retiredkimi-k2.5Moonshot AIChatchat262.1K——Yes——tools · structured_output · cachingRetired——Kimi K2.7 Code High-Speedkimi-k2.7-code-highspeedMoonshot AIChatchat262.1K——Yes$1.9 / $8$0.38 / —tools · cachingActive——Kimi LatestRetiredkimi-latestMoonshot AIChatchat———————Retired——Kimi Thinking PreviewRetiredkimi-thinking-previewMoonshot AIChatchat———————Retired——Moonshot V1 128KRetiredmoonshot-v1-128kMoonshot AIChatchat131.1K——————Retired——Moonshot V1 128K Vision PreviewRetiredmoonshot-v1-128k-vision-previewMoonshot AIChatchat131.1K——————Retired——Moonshot V1 32KRetiredmoonshot-v1-32kMoonshot AIChatchat32.8K——————Retired——Moonshot V1 32K Vision PreviewRetiredmoonshot-v1-32k-vision-previewMoonshot AIChatchat32.8K——————Retired——Moonshot V1 8KRetiredmoonshot-v1-8kMoonshot AIChatchat8.2K——————Retired——Moonshot V1 8K Vision PreviewRetiredmoonshot-v1-8k-vision-previewMoonshot AIChatchat8.2K——————Retired——Moonshot V1 AutoRetiredmoonshot-v1-autoMoonshot AIChatchat———————Retired——Embed QA 4embed-qa-4NVIDIAEmbeddingembeddings512——————Active——Llama 3.1 NemoGuard 8B ContentSafetyllama-3.1-nemoguard-8b-content-safetyNVIDIAChatmoderation———————Active——Llama 3.1 NemoGuard 8B TopicControlllama-3.1-nemoguard-8b-topic-controlNVIDIAChatmoderation———————Active——Llama 3.2 NV EmbedQA 1B v1llama-3.2-nv-embedqa-1b-v1NVIDIAEmbeddingembeddings512——————Active——NeVA 22Bneva-22bNVIDIAChatchat———————Active——NV-CLIPnvclipNVIDIAEmbeddingembeddings———————Active——VILAvilaNVIDIAChatchat———————Active——adaRetiredadaOpenAIChatcompletions————$0.4 / $0.4——Retired——babbageRetiredbabbageOpenAIChatcompletions————$0.5 / $0.5——Retired——babbage-002Retiredbabbage-002OpenAIChatcompletions——16.4K—$0.4 / $0.4——Retired—2021-09-01 ChatGPT-4oRetiredchatgpt-4o-latestOpenAIChatchat · responses128K—16.4K—$5 / $15—streamingRetired—2023-10-01 code-davinci-002Retiredcode-davinci-002OpenAIChatcompletions———————Retired——codex-mini-latestRetiredcodex-mini-latestOpenAIChatresponses200K—100KYes$1.5 / $6$0.375 / —tools · structured_output · streaming · cachingRetired—2024-06-01 computer-use-previewRetiredcomputer-use-previewOpenAIChatresponses · batch8.2K—1KYes$3 / $12—tools · batchRetired—2023-10-01 curieRetiredcurieOpenAIChatcompletions————$2 / $2——Retired——DALL·E 2Retireddall-e-2OpenAIImageimages———————Retired——DALL·E 3Retireddall-e-3OpenAIImageimages———————Retired——davinciRetireddavinciOpenAIChatcompletions————$20 / $20——Retired——davinci-002Retireddavinci-002OpenAIChatcompletions——16.4K—$2 / $2——Retired—2021-09-01 GPT-3.5 Turbogpt-3.5-turboOpenAIChatchat · responses · batch16.4K—4.1K—$0.5 / $1.5—batchDeprecated—2021-09-01 gpt-3.5-turbo-0301Retiredgpt-3.5-turbo-0301OpenAIChatchat————$15 / $20——Retired——gpt-3.5-turbo-0613Retiredgpt-3.5-turbo-0613OpenAIChatchat————$1.5 / $2——Retired——gpt-3.5-turbo-1106Retiredgpt-3.5-turbo-1106OpenAIChatchat———————Retired——gpt-3.5-turbo-16k-0613Retiredgpt-3.5-turbo-16k-0613OpenAIChatchat————$3 / $4——Retired——gpt-3.5-turbo-instructRetiredgpt-3.5-turbo-instructOpenAIChatcompletions4.1K—4.1K—$1.5 / $2——Retired—2021-09-01 GPT-4gpt-4OpenAIChatchat · responses · batch8.2K—8.2K—$30 / $60—streaming · batchDeprecated—2023-12-01 gpt-4-32kRetiredgpt-4-32kOpenAIChatchat————$60 / $120——Retired——GPT-4 Turbo PreviewRetiredgpt-4-turbo-previewOpenAIChatchat · responses128K—4.1K—$10 / $30——Retired—2023-12-01 gpt-4-vision-previewRetiredgpt-4-vision-previewOpenAIChatchat————$10 / $30——Retired——GPT-4.5 PreviewRetiredgpt-4.5-previewOpenAIChatchat · responses · batch128K—16.4K—$75 / $150$37.5 / —tools · structured_output · streaming · caching · batchRetired—2023-10-01 GPT-4o AudioRetiredgpt-4o-audio-previewOpenAIChatchat128K—16.4K———tools · streamingRetired—2023-10-01 GPT-4o Mini AudioRetiredgpt-4o-mini-audio-previewOpenAIChatchat128K—16.4K———tools · streamingRetired—2023-10-01 GPT-4o Mini RealtimeRetiredgpt-4o-mini-realtime-previewOpenAIChatrealtime16K—4.1K———tools · cachingRetired—2023-10-01 GPT-4o Mini Search PreviewRetiredgpt-4o-mini-search-previewOpenAIChatchat128K—16.4K—$0.15 / $0.6—structured_output · streamingRetired—2023-10-01 GPT-4o RealtimeRetiredgpt-4o-realtime-previewOpenAIChatrealtime32K—4.1K———tools · cachingRetired—2023-10-01 GPT-4o Search PreviewRetiredgpt-4o-search-previewOpenAIChatchat128K—16.4K—$2.5 / $10—structured_output · streamingRetired—2023-10-01 GPT-4o Transcribe Diarizegpt-4o-transcribe-diarizeOpenAIChataudio16K—2K—$2.5 / $10——Deprecated—2024-06-01 GPT-5 ChatRetiredgpt-5-chat-latestOpenAIChatchat · responses128K272K16.4K—$1.25 / $10$0.125 / —tools · structured_output · streamingRetired—2024-09-30 GPT-5-CodexRetiredgpt-5-codexOpenAIChatresponses400K272K128KYes$1.25 / $10$0.125 / —tools · structured_output · streaming · cachingRetired—2024-09-30 GPT-5.1 ChatRetiredgpt-5.1-chat-latestOpenAIChatchat · responses128K272K16.4K—$1.25 / $10$0.125 / —tools · structured_output · streamingRetired—2024-09-30 GPT-5.1-CodexRetiredgpt-5.1-codexOpenAIChatresponses400K—128KYes$1.25 / $10$0.125 / —tools · structured_output · streaming · cachingRetired—2024-09-30 GPT-5.1-Codex-MaxRetiredgpt-5.1-codex-maxOpenAIChatresponses400K—128KYes$1.25 / $10$0.125 / —tools · structured_output · streaming · cachingRetired—2024-09-30 GPT-5.1-Codex MiniRetiredgpt-5.1-codex-miniOpenAIChatresponses400K—128KYes$0.25 / $2$0.025 / —tools · structured_output · streaming · cachingRetired—2024-09-30 GPT-5.2 ChatRetiredgpt-5.2-chat-latestOpenAIChatchat · responses128K272K16.4K—$1.75 / $14$0.175 / —tools · structured_output · streamingRetired—2025-08-31 GPT-5.2-CodexRetiredgpt-5.2-codexOpenAIChatresponses400K272K128Klow · medium · high · xhigh$1.75 / $14$0.175 / —tools · structured_output · streaming · cachingRetired—2025-08-31 GPT-5.3 ChatRetiredgpt-5.3-chat-latestOpenAIChatchat · responses128K272K16.4K—$1.75 / $14$0.175 / —tools · structured_output · streamingRetired—2025-08-31 o1-miniRetiredo1-miniOpenAIChatchat128K—65.5KYes$1.1 / $4.4$0.55 / —streamingRetired—2023-10-01 o1 PreviewRetiredo1-previewOpenAIChatchat128K—32.8KYes$15 / $60$7.5 / —tools · structured_output · streamingRetired—2023-10-01 o3-deep-researchRetiredo3-deep-researchOpenAIChatresponses · batch200K—100KYes$10 / $40$2.5 / —streaming · caching · batchRetired—2024-06-01 o4-mini-deep-researchRetiredo4-mini-deep-researchOpenAIChatresponses · batch200K—100KYes$2 / $8$0.5 / —streaming · caching · batchRetired—2024-06-01 Sora 2Retiredsora-2OpenAIVideovideo————— / $0.1 / second——Retired——Sora 2 ProRetiredsora-2-proOpenAIVideovideo————— / $0.3 / second——Retired——text-ada-001Retiredtext-ada-001OpenAIChatcompletions————$0.4 / $0.4——Retired——text-babbage-001Retiredtext-babbage-001OpenAIChatcompletions————$0.5 / $0.5——Retired——text-curie-001Retiredtext-curie-001OpenAIChatcompletions————$2 / $2——Retired——text-davinci-001Retiredtext-davinci-001OpenAIChatcompletions————$20 / $20——Retired——text-davinci-002Retiredtext-davinci-002OpenAIChatcompletions————$20 / $20——Retired——text-davinci-003Retiredtext-davinci-003OpenAIChatcompletions————$20 / $20——Retired——text-embedding-ada-002text-embedding-ada-002OpenAIEmbeddingembeddings · batch—8.2K——$0.1 / ——batchActive——text-moderationRetiredtext-moderation-latestOpenAIChatmoderation——32.8K————Retired—2021-09-01 Whisperwhisper-1OpenAIChataudio————$0.006 / — / minute——Deprecated——Llama 3 Sonar Large 32k ChatRetiredllama-3-sonar-large-32k-chatPerplexityChatchat32.8K——————Retired——Llama 3 Sonar Large 32k OnlineRetiredllama-3-sonar-large-32k-onlinePerplexityChatchat28K——————Retired——Llama 3 Sonar Small 32k ChatRetiredllama-3-sonar-small-32k-chatPerplexityChatchat32.8K——————Retired——Llama 3 Sonar Small 32k OnlineRetiredllama-3-sonar-small-32k-onlinePerplexityChatchat28K——————Retired——Llama 3.1 Sonar Huge 128k OnlineRetiredllama-3.1-sonar-huge-128k-onlinePerplexityChatchat127.1K——————Retired——Llama 3.1 Sonar Large 128k OnlineRetiredllama-3.1-sonar-large-128k-onlinePerplexityChatchat127.1K——————Retired——Llama 3.1 Sonar Small 128k OnlineRetiredllama-3.1-sonar-small-128k-onlinePerplexityChatchat127.1K——————Retired——PPLX 7B ChatRetiredpplx-7b-chatPerplexityChatchat———————Retired——PPLX 7B OnlineRetiredpplx-7b-onlinePerplexityChatchat———————Retired——R1 1776Retiredr1-1776PerplexityChatchat———————Retired——Sonar Deep Researchsonar-deep-researchPerplexityChatchat————$2 / $8—structured_output · streamingDeprecated——Sonar ReasoningRetiredsonar-reasoningPerplexityChatchat———Yes———Retired——Sonar Reasoning Prosonar-reasoning-proPerplexityChatchat————$2 / $8—structured_output · streamingDeprecated——Recraft V2recraftv2RecraftImageimages————— / $0.022 / image——Active——Recraft V2 Vectorrecraftv2_vectorRecraftImageimages————— / $0.044 / image——Active——Recraft V3recraftv3RecraftImageimages————— / $0.04 / image——Active——Recraft V3 Vectorrecraftv3_vectorRecraftImageimages————— / $0.08 / image——Active——Recraft V4recraftv4RecraftImageimages————— / $0.04 / image——Active——Recraft V4.1recraftv4_1RecraftImageimages————— / $0.035 / image——Active——Recraft V4.1 Flashrecraftv4_1_flashRecraftImageimages————— / $0.007 / image——Active——Recraft V4.1 Prorecraftv4_1_proRecraftImageimages————— / $0.21 / image——Active——Recraft V4.1 Pro Vectorrecraftv4_1_pro_vectorRecraftImageimages————— / $0.3 / image——Active——Recraft V4.1 Utilityrecraftv4_1_utilityRecraftImageimages————— / $0.035 / image——Active——Recraft V4.1 Utility Prorecraftv4_1_utility_proRecraftImageimages————— / $0.21 / image——Active——Recraft V4.1 Utility Pro Vectorrecraftv4_1_utility_pro_vectorRecraftImageimages————— / $0.3 / image——Active——Recraft V4.1 Utility Vectorrecraftv4_1_utility_vectorRecraftImageimages————— / $0.08 / image——Active——Recraft V4.1 Vectorrecraftv4_1_vectorRecraftImageimages————— / $0.08 / image——Active——Recraft V4 Prorecraftv4_proRecraftImageimages————— / $0.25 / image——Active——Recraft V4 Pro Vectorrecraftv4_pro_vectorRecraftImageimages————— / $0.3 / image——Active——Recraft V4 Stylesrecraftv4_stylesRecraftImageimages————— / $0.035 / image——Active——Recraft V4 Styles Prorecraftv4_styles_proRecraftImageimages————— / $0.1 / image——Active——Recraft V4 Styles Pro Vectorrecraftv4_styles_pro_vectorRecraftImageimages————— / $0.12 / image——Active——Recraft V4 Styles Vectorrecraftv4_styles_vectorRecraftImageimages————— / $0.05 / image——Active——Recraft V4 Vectorrecraftv4_vectorRecraftImageimages————— / $0.08 / image——Active——Gen-3 Alpha TurboRetiredgen3a_turboRunwayVideovideo————— / $0.05 / second——Retired——Gen-4 AlephRetiredgen4_alephRunwayVideovideo————— / $0.15 / second——Retired——Gen-4 Turbogen4_turboRunwayVideovideo————— / $0.05 / second——Active——Runway Charactersgwm1_avatarsRunwayVideovideo———————Active——Bulbul v3bulbul-v3Sarvam AIAudioaudio————INR 3000 / — / 1M characters——Active——Bulbul v4 Flashbulbul-v4-flashSarvam AIAudioaudio———————Active——Mayura v1mayura-v1Sarvam AIChatcompletions————INR 2000 / — / 1M characters——Active——Saaras v3saaras-v3Sarvam AIChataudio————INR 30 / — / hour——Active——Sarvam-105Bsarvam-105bSarvam AIChatchat131.1K——YesINR 15 / INR 60INR 5 / —streamingActive——Sarvam-105B Conversationssarvam-105b-conversationsSarvam AIChatchat32.8K———INR 15 / INR 60INR 5 / —streamingActive——Sarvam-MRetiredsarvam-mSarvam AIChatchat8.2K——Yes———Retired——Sarvam-Translate v1sarvam-translate-v1Sarvam AIChatcompletions————INR 2000 / — / 1M characters——Active——SenseAudio-A1senseaudio-a1SenseTimeAudioaudio————— / ¥0.017 / second——Active——SenseAudio-ASR-1.5senseaudio-asr-1.5-260319SenseTimeChataudio————¥1.8 / — / hour——Active——SenseAudio-ASR-Check-1.5senseaudio-asr-check-1.5-260319SenseTimeChataudio————¥3.6 / — / hour——Active——SenseAudio-ASR-DeepThink-1.5senseaudio-asr-deepthink-1.5-260319SenseTimeChataudio————¥3.6 / — / hour——Active——SenseAudio-ASR-Lite-1.5senseaudio-asr-lite-1.5-260319SenseTimeChataudio————¥0.9 / — / hour——Active——SenseAudio-ASR-Pro-1.5senseaudio-asr-pro-1.5-260319SenseTimeChataudio————¥3.6 / — / hour——Active——SenseAudio-ASR-Stream-1.5senseaudio-asr-stream-1.5-260910SenseTimeChataudio————¥3.6 / — / hour—streamingActive——SenseAudio-Image-2.0senseaudio-image-2.0-260319SenseTimeImageimages————— / ¥1 / image——Active——SenseAudio-Music-2.0senseaudio-music-2.0-260626SenseTimeAudioaudio————— / ¥1 / request——Active——SenseAudio-Realtime-1.0senseaudio-realtime-1.0SenseTimeChatrealtime————¥0.6 / — / minute—tools · streamingActive——SenseAudio-S2senseaudio-s2SenseTimeChatchat · messages————¥15 / ¥90—tools · streamingActive——SenseAudio-S2-Flashsenseaudio-s2-flashSenseTimeChatchat · messages————¥4 / ¥24—tools · streamingActive——SenseAudio-S2-Litesenseaudio-s2-liteSenseTimeChatchat · messages————¥2 / ¥12—tools · streamingActive——SenseAudio-Sound-Effect-1.0senseaudio-sfx-1.0-260626SenseTimeAudioaudio————— / ¥0.08 / request——Active——SenseAudio-TTS-1.5senseaudio-tts-1.5-260319SenseTimeAudioaudio————¥350 / — / 1M characters—streamingActive——SenseAudio-Voice-Isolation 1.0senseaudio-voice-isolation-1.0-260319SenseTimeAudioaudio————¥0.04 / — / second——Active——SenseAudio-Voice-Isolation-1.5senseaudio-voice-isolation-1.5SenseTimeAudioaudio————¥0.04 / — / second——Active——SenseNova 6.8 Flash Litesensenova-6.8-flash-liteSenseTimeChatchat———Yes¥15 / ¥90—tools · streamingPreview——SenseNova-LiveTranslate-1.0sensenova-livetranslate-1.0SenseTimeChatrealtime——————streamingActive——SenseNova-TTS-2.0sensenova-tts-2.0SenseTimeAudioaudio————¥350 / — / 1M characters—streamingActive——SenseNova U1 Fastsensenova-u1-fastSenseTimeImageimages————— / ¥0.5 / image——Active——Vidu 2.0vidu2.0Shengshu ViduVideovideo———————Active——Vidu Q1viduq1Shengshu ViduVideovideo · images———————Active——Vidu Q1 Classicviduq1-classicShengshu ViduVideovideo———————Active——Vidu Q2viduq2Shengshu ViduVideovideo · images———————Active——Vidu Q3 Adviduq3-adShengshu ViduVideovideo———————Active——Vidu Q3 Dramaviduq3-dramaShengshu ViduVideovideo———————Active——Intern-S1-miniintern-s1-miniShanghai AI LabChatchat———Yes——tools · streamingActive——Intern-S2 Preview 397Bintern-s2-preview-397bShanghai AI LabChatchat262.1K——Yes——tools · streamingDeprecated——EnhancedenhancedSpeechmaticsChataudio · realtime————$0.75 / — / hour——Active——Oak 1oak-1SpeechmaticsChataudio————$0.3 / — / hour——Active——StandardstandardSpeechmaticsChataudio · realtime————$0.45 / — / hour——Active——Stable Diffusion 3.5 Flashsd3.5-flashStability AIImageimages————— / $0.025 / image——Active——Stable Audio 2.5stable-audio-2.5Stability AIAudioaudio————— / $0.08 / request——Active——Step-1 32KRetiredstep-1-32kStepFunChatchat32K———¥15 / ¥70¥3 / ——Retired——Step-1 8KRetiredstep-1-8kStepFunChatchat8K———¥5 / ¥20¥1 / ——Retired——Step-1o Audiostep-1o-audioStepFunChataudio————$3.57 / $8.57$0.71 / —toolsActive——Step-1o Turbo Visionstep-1o-turbo-visionStepFunChatchat32.8K———$0.36 / $1.15$0.07 / ——Active——Step-1o Vision 32KRetiredstep-1o-vision-32kStepFunChatchat32K———¥15 / ¥70¥3 / ——Retired——Step-1V 32KRetiredstep-1v-32kStepFunChatchat32K———¥15 / ¥70¥3 / ——Retired——Step-1V 8KRetiredstep-1v-8kStepFunChatchat8K———¥5 / ¥20¥1 / ——Retired——Step-1X EditRetiredstep-1x-editStepFunImageimages———————Retired——Step-1X MediumRetiredstep-1x-mediumStepFunImageimages————— / ¥0.1 / image——Retired——Step-2 16KRetiredstep-2-16kStepFunChatchat16K———¥38 / ¥120¥7.6 / ——Retired——Step-2 MiniRetiredstep-2-miniStepFunChatchat————¥1 / ¥2¥0.2 / ——Retired——Step-2X LargeRetiredstep-2x-largeStepFunImageimages————— / $0.02 / image——Retired——Step 3Retiredstep-3StepFunChatchat———Yes¥1.5 / ¥4¥0.3 / ——Retired——Step 3.5 Flashstep-3.5-flashStepFunChatchat · messages262.1K——Yes$0.1 / $0.3$0.02 / —tools · streaming · cachingActive——Step 3.5 Flash 2603step-3.5-flash-2603StepFunChatchat · messages262.1K——low · high$0.1 / $0.3$0.02 / —tools · streaming · cachingActive——Step 5 Previewstep-5-previewStepFunChatchat · messages1M1M65.5Klow · medium · high$1 / $2.7$0.1 / —tools · structured_output · streaming · cachingPreview——Step ASRstep-asrStepFunChataudio————$0.13 / — / hour——Active——Step ASR 1.1step-asr-1.1StepFunChataudio————$0.31 / — / hour——Active——Step ASR 1.1 Streamstep-asr-1.1-streamStepFunChataudio————$0.37 / — / hour——Active——Step Audio 2step-audio-2StepFunChataudio————$1.43 / $10$0.29 / —toolsActive——Step Audio R1.5step-audio-r1.5StepFunChataudio————$1.43 / $15$0.29 / ——Active——Step Image Edit 2Retiredstep-image-edit-2StepFunImageimages———————Retired——Step TTS 2step-tts-2StepFunAudioaudio————$40 / — / 1M characters——Active——Step TTS Ministep-tts-miniStepFunAudioaudio————$13 / — / 1M characters——Active——StepAudio 2 ASR Prostepaudio-2-asr-proStepFunChataudio————$0.29 / — / hour——Active——StepAudio 2.5 ASRstepaudio-2.5-asrStepFunChataudio————$0.022 / — / hour——Active——StepAudio 2.5 ASR Streamstepaudio-2.5-asr-streamStepFunChataudio————$0.18 / — / hour——Active——StepAudio 2.5 Chatstepaudio-2.5-chatStepFunChatchat————$1.5 / $3.5$0.3 / ——Active——StepAudio 2.5 Realtimestepaudio-2.5-realtimeStepFunChatrealtime————$1.5 / $10$0.3 / ——Active——StepAudio 2.5 TTSstepaudio-2.5-ttsStepFunAudioaudio————$85 / — / 1M characters——Active——StepAudio 3 ASR Maxstepaudio-3-asr-maxStepFunChataudio————$0.4 / — / hour——Active——StepAudio 3 Chat Previewstepaudio-3-chat-previewStepFunChatchat——————toolsPreview——StepAudio 3 Gen Previewstepaudio-3-gen-previewStepFunAudioaudio———————Preview——StepAudio 3 Music Previewstepaudio-3-music-previewStepFunAudioaudio———————Preview——StepAudio 3 Realtime Previewstepaudio-3-realtime-previewStepFunChatrealtime——————toolsPreview——StepAudio 3 TTSstepaudio-3-ttsStepFunAudioaudio———No$36 / — / 1M characters——Active——Hunyuan-2.0-InstructRetiredhunyuan-2.0-instructTencentChatchat———————Retired——Hunyuan-2.0-ThinkingRetiredhunyuan-2.0-thinkingTencentChatchat———Yes———Retired——Hunyuan-CodeRetiredhunyuan-codeTencentChatchat———————Retired——Hunyuan-LargeRetiredhunyuan-largeTencentChatchat———————Retired——Hunyuan-Large-longcontextRetiredhunyuan-large-longcontextTencentChatchat———————Retired——Hunyuan-Large-RoleRetiredhunyuan-large-roleTencentChatchat———————Retired——Hunyuan-LiteRetiredhunyuan-liteTencentChatchat———————Retired——Hunyuan-ProRetiredhunyuan-proTencentChatchat———————Retired——Hunyuan-RoleRetiredhunyuan-roleTencentChatchat———————Retired——Hunyuan-Standard-256KRetiredhunyuan-standard-256kTencentChatchat———————Retired——Hunyuan-Standard-32KRetiredhunyuan-standard-32kTencentChatchat———————Retired——Hunyuan-T1Retiredhunyuan-t1TencentChatchat———Yes———Retired——Hunyuan-TurboRetiredhunyuan-turboTencentChatchat———————Retired——Hunyuan-TurboSRetiredhunyuan-turbosTencentChatchat———————Retired——Hunyuan-TurboS-longtext-128kRetiredhunyuan-turbos-longtext-128kTencentChatchat———————Retired——Hy-ASR-3.0-Previewhy-asr-3.0-previewTencentChataudio———No¥0.0002 / — / second——Preview——Hy-Image-3.0hy-image-v3TencentImageimages———No— / ¥0.2 / image——Active——Hy-Image-3.5-previewhy-image-v3.5-previewTencentImageimages———No— / ¥0.15 / image——Preview——Hy-MT2-Litehy-mt2-liteTencentChatchat8.2K4.1K4.1K—¥0.3 / ¥1.2——Active——Hy-MT2-Plushy-mt2-plusTencentChatchat8.2K4.1K4.1K—¥0.5 / ¥2——Active——Hy-MT2-Prohy-mt2-proTencentChatchat8.2K4.1K4.1K—¥0.5 / ¥2——Active——Hy-Rolehy-roleTencentChatchat · messages32.8K28.7K4.1K—¥2.4 / ¥9.6——Active——Hy-Video-v1.5hy-video-v1.5TencentVideovideo————— / $1.6——Active——HY-Vision-2.0-Instructhy-vision-2.0-instructTencentChatchat45.1K24.6K16.4K—¥7.5 / ¥17.5——Active——Document Classifydocument-classifyUpstageChatocr————$0.004 / — / page——Active——Syn Prosyn-proUpstageChatchat65.5K——————Active——Grok 3Retiredgrok-3xAIChatchat131.1K——No$3 / $15$0.75 / —tools · structured_output · cachingRetired——Grok 4Retiredgrok-4-0709xAIChatchat256K——Yes$3 / $15$0.75 / —tools · structured_output · cachingRetired——Grok 4.1 Fast (Non-Reasoning)Retiredgrok-4-1-fast-non-reasoningxAIChatchat2M——No$0.2 / $0.5$0.05 / —tools · structured_output · cachingRetired——Grok 4.1 Fast (Reasoning)Retiredgrok-4-1-fast-reasoningxAIChatchat2M——Yes$0.2 / $0.5$0.05 / —tools · structured_output · cachingRetired——Grok 4 Fast (Non-Reasoning)Retiredgrok-4-fast-non-reasoningxAIChatchat2M——No$0.2 / $0.5$0.05 / —tools · structured_output · cachingRetired——Grok 4 Fast (Reasoning)Retiredgrok-4-fast-reasoningxAIChatchat2M——Yes$0.2 / $0.5$0.05 / —tools · structured_output · cachingRetired——Grok 4.3grok-4.3xAIChatchat · responses · batch1M——none · low · medium · high · xhigh$1.25 / $2.5$0.2 / —tools · structured_output · caching · batchActive——Grok Imagine Imagegrok-imagine-imagexAIImageimages · batch————— / $0.02 / image—batchActive——Grok Imagine Image 2.0grok-imagine-image-2.0xAIImageimages · batch————— / $0.04 / image—batchActive——Grok Imagine Image Qualitygrok-imagine-image-qualityxAIImageimages————— / $0.05 / image——Deprecated——Grok Imagine Video 1.5 Litegrok-imagine-video-1.5-litexAIVideovideo · batch————— / $0.02 / second—batchActive——Grok Voice Transcribe 1.0Retiredgrok-voice-transcribe-1.0xAIChataudio———————Retired——MiMo-V2-FlashRetiredmimo-v2-flashXiaomiChatchat———————Retired——MiMo-V2-ProRetiredmimo-v2-proXiaomiChatchat———————Retired——MiMo-V2-TTSRetiredmimo-v2-ttsXiaomiAudioaudio———————Retired——CogVideoX-Flashcogvideox-flashZhipu AIVideovideo————— / ¥0 / request——Active——CogView-3-Flashcogview-3-flashZhipu AIImageimages————— / ¥0 / image——Active——CogView-4cogview-4Zhipu AIImageimages————— / $0.01 / image——Active——Embedding-2embedding-2Zhipu AIEmbeddingembeddings8.2K———¥0.5 / ———Active——Embedding-3embedding-3Zhipu AIEmbeddingembeddings8.2K———¥0.5 / ———Active——GLM-4-0520Retiredglm-4-0520Zhipu AIChatchat———————Retired——GLM-4-32B-0414-128Kglm-4-32b-0414-128kZhipu AIChatchat131.1K—16.4K—$0.1 / $0.1——Active——GLM-4-FlashX-250414glm-4-flashx-250414Zhipu AIChatchat131.1K—16.4K—¥0.1 / ¥0.1¥0.05 / —tools · structured_output · streaming · cachingActive——GLM-4-Longglm-4-longZhipu AIChatchat1.05M—4.1K—¥1 / ¥1¥0.5 / ——Active——GLM-4-Voiceglm-4-voiceZhipu AIAudioaudio8.2K—4.1K—¥80 / ¥80——Active——GLM-4.1V-Thinking-Flashglm-4.1v-thinking-flashZhipu AIChatchat65.5K——Yes¥0 / ¥0—streamingActive——GLM-4.1V-Thinking-FlashXglm-4.1v-thinking-flashxZhipu AIChatchat65.5K—16.4KYes¥2 / ¥2—streamingActive——GLM-4.5-AirXglm-4.5-airxZhipu AIChatchat———Yes$1.1 / $4.5$0.22 / —tools · structured_output · streaming · cachingActive——GLM-4.5-FlashRetiredglm-4.5-flashZhipu AIChatchat131.1K—98.3KYes$0 / $0$0 / —tools · structured_output · streaming · cachingRetired——GLM-4.5-Xglm-4.5-xZhipu AIChatchat———Yes$2.2 / $8.9$0.45 / —tools · structured_output · streaming · cachingDeprecated——GLM-4.6V-Flashglm-4.6v-flashZhipu AIChatchat131.1K—32.8KYes$0 / $0—toolsActive——GLM-4.6V-FlashXglm-4.6v-flashxZhipu AIChatchat131.1K———$0.04 / $0.4$0.004 / —tools · cachingActive——GLM-4.7-FlashXglm-4.7-flashxZhipu AIChatchat202.8K—131.1KYes$0.07 / $0.4$0.01 / —tools · structured_output · streaming · cachingActive——GLM-4V-Flashglm-4v-flashZhipu AIChatchat——1K—¥0 / ¥0—streamingActive——GLM-5.3-FlashXglm-5.3-flashxZhipu AIChatchat1.05M—131.1KYes$0.37 / $1.25$0.075 / —tools · structured_output · streaming · cachingActive——GLM-Realtimeglm-realtimeZhipu AIAudiorealtime——1K———toolsActive——GLM-Z1-FlashXRetiredglm-z1-flashxZhipu AIChatchat131.1K—32.8KYes¥0.1 / ¥0.1——Retired——RerankrerankZhipu AIRerankrerank4.1K———¥0.8 / ———Active——