Compare models
Compare 2–6 models side by side: context, modalities, reasoning and pricing. The selection lives in the URL, so you can share it.
No matching models
VendorAll
Comparison
No models selected yet
Add models with the search above, or start from a common comparison below. You can also add models from the models list and model pages.
Common comparisons
- Latest chat models · global vendorsGPT-6.1 SolClaude Haiku 5.5Gemini 3.8 FlashGrok 4.7
- Latest chat models · Chinese vendorsDeepSeek-V4.1-FlashQwen3.8-Omni-FlashKimi K3GLM-5.3-Flash
- Anthropic · latest threeClaude Haiku 5.5Claude Sonnet 5.5Claude Opus 5.5
- OpenAI · latest threeGPT-6.1 SolGPT-6 LunaGPT-6 Sol
Add at least one more model to compare.
The selected models are identical in every field.
| Field |
|---|
| Overview |
| Vendor |
| Type |
| API |
| API types |
| Context |
| Context |
| Max input |
| Max output |
| Modalities |
| Input |
| Output |
| Reasoning |
| Reasoning |
| Efforts |
| Pricing |
| Currency / unit |
| Input |
| Output |
| Cache read |
| Cache write |
| Features |
| Features |
| Info |
| Status |
| Released |
| Knowledge cutoff |
| Docs |
“Best” marks the best value in a row: largest context, input and output limits; lowest price. Prices are only compared within the same currency and unit, never converted.
Token cost estimate
Estimated cost of one call at per-million-token prices, grouped by currency and never converted.
Accepts 1500, 200K, 1.5M · Cached tokens use the cache read price, or the input price when none is listed.
Add models to see estimated costs.
“—” means the model is not priced per million tokens or has no public price.