Step 3.5 Flash
Sparse MoE reasoning model (196B total, 11B active) for agents and long-horizon tasks.
Specs
- Context
- 262.1K
- Max output
- —
- Input price
- $0.1/ 1M tokens
- Output price
- $0.3/ 1M tokens
- Released
- —
Context
- Context window
- 262.1K
- Max input
- —
- Max output
- —
Pricing · USD / 1M tokens
- Input
- $0.1
- Output
- $0.3
- Cache read
- $0.02
- Cache write
- —
Modalities
- Input
- Text
- Output
- Text
API
- API types
Reasoning
- Reasoning
- Yes
- Levels
- —
Info
- Status
- Active
- Released
- —
- Knowledge cutoff
- —
Features
- Confirmed
How to call
1 provider
stepfunmodel = step-3.5-flash
chat
POSThttps://api.stepfun.ai/v1/chat/completions
messages
POSThttps://api.stepfun.ai/v1/messages
JSON
Standard format
{
"id": "step-3.5-flash",
"object": "model",
"created": null,
"owned_by": "stepfun",
"name": "Step 3.5 Flash",
"api": {
"types": [
"chat",
"messages"
]
},
"limits": {
"context": 262144,
"input": null,
"output": null
},
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"reasoning": {
"supported": true,
"efforts": []
},
"pricing": {
"currency": "USD",
"unit": "1M_tokens",
"input": 0.1,
"output": 0.3,
"cache_read": 0.02,
"cache_write": null
},
"features": [
"tools",
"streaming",
"caching"
],
"info": {
"status": "active",
"release_date": null,
"knowledge_cutoff": null,
"description": "Sparse MoE reasoning model (196B total, 11B active) for agents and long-horizon tasks.",
"docs": "https://platform.stepfun.ai/docs/en/guides/models/step-3.5-flash",
"verified_at": "2026-10-11"
}
}Official sources
5
Step Platform pricing | StepFun Documentationplatform.stepfun.ai2026-10-10Model overview | StepFun Documentationplatform.stepfun.ai2026-10-10Chat completion | StepFun API referenceplatform.stepfun.ai2026-10-10Step 3.5 Flash | StepFun Documentationplatform.stepfun.ai2026-10-10Messages API | StepFun Documentationplatform.stepfun.ai2026-10-11