One agent session
1M input tokens and 100K output tokens, no caching.
- Input1M x $0.20 = $0.20
- Output0.1M x $1.15 = $0.115
$0.315per session
StepFun - Open weights
Step 3.7 Flash pricing and specs
Step 3.7 Flash is an open-weights model from StepFun that costs $0.20 per 1M input tokens and $1.15 per 1M output tokens on the first-party API, with a 256K-token context window.
Last verified from platform.stepfun.ai. All sources
- Input / 1M
- $0.20
- Output / 1M
- $1.15
- Context
- 256K tokens
- Weights
- Open
Pricing per 1M tokens
| Item | Price / 1M tokens |
|---|---|
| Input | $0.20 |
| Output | $1.15 |
| Cache read | $0.04 |
Note: StepFun international platform, priced in USD. 198B total / 11B active sparse MoE with native image and video input. Context listed as 256K tokens (recorded as 256,000). max output is not stated because no primary page states a fixed output cap; the Chat Completions reference says max_tokens defaults to no limit, bounded by the model's context length. No separate cache write or batch price published. release date from the dated launch post.
Specs
- Context window
- 256,000 tokens
- Release date
- Provider
- StepFun
- API model id
step-3.7-flash- Vercel AI Gateway id
stepfun/step-3.7-flash- Weights
- Open weights
- License
- Apache-2.0
- Weights download
- huggingface.co
What Step 3.7 Flash costs in practice
Worked from the standard list rates above, with the math shown so you can swap in your own token counts.
A chat app
10,000 requests a day at 2K input and 500 output tokens each.
- Input20M x $0.20 = $4.00
- Output5M x $1.15 = $5.75
$9.75per day
$292.50 per 30-day month
The same session at a 90% cache hit
90% of the input is read from the prompt cache. The one-time cache write premium is not included.
- Cached input0.9M x $0.04 = $0.036
- Uncached input0.1M x $0.20 = $0.02
- Output0.1M x $1.15 = $0.115
$0.171per session
Compare with
| Model | Input / 1M | Output / 1M |
|---|---|---|
| Step 3.7 Flash (this page) | $0.20 | $1.15 |
| Step-1o Turbo VisionStepFun | $0.36 | $1.15 |
| GLM-4.5-AirZ.ai | $0.20 | $1.10 |
| DeepSeek V4.1 FlashDeepSeek | $0.30 | $1.20 |
| GPT-5.6 LunaOpenAI | $0.20 | $1.20 |
| Step 3.5 FlashStepFun | $0.10 | $0.30 |
| Step 3.5 Flash 2603StepFun | $0.10 | $0.30 |
| Step 5 PreviewStepFun | $1 | $2.70 |
Related reading
- Step 5 Preview: Pricing, Benchmarks and the October 15 Open WeightsStep 5 Preview is StepFun's 600B MoE with 27B active and a 1M window. What it scores, what a session costs, and what to check before the October 15 weights.
- Build Your First Agent with Vercel eve: A Step-by-Step TutorialBuild your first AI agent with Vercel eve: scaffold a project, add a typed tool with defineTool, run it locally, call the session API and deploy to Vercel.
- Agent Architecture: Building Multi-Step AI Workflows That Survive ProductionAgent architecture for multi-step Claude workflows: loop patterns, state management, error recovery, and the production gotchas that break agents at scale.
- The Agent Reliability Cliff: Why Your 10-Step Chain Only Succeeds 20% of the TimeThe agent reliability cliff: 85% per-step success compounds to about 20% over 10 steps. Why long chains collapse, and six patterns that fight the decay.
FAQ
How much does Step 3.7 Flash cost per million tokens?
Step 3.7 Flash costs $0.20 per 1M input tokens and $1.15 per 1M output tokens on StepFun's first-party API, per platform.stepfun.ai on October 17, 2026. Per 1M tokens, cache reads cost $0.04.
What is Step 3.7 Flash's context window?
Step 3.7 Flash has a 256,000-token context window.
Are Step 3.7 Flash's weights open?
Yes. Step 3.7 Flash's weights are published at https://huggingface.co/stepfun-ai/Step-3.7-Flash under the Apache-2.0.
When was Step 3.7 Flash released?
StepFun released Step 3.7 Flash on May 29, 2026.
Sources
Last verified from platform.stepfun.ai.
Newsletter
Get model price changes as they ship
One email per week. New model releases, price cuts and what they mean for your bill.