Newer StepFun flash model for faster agents, coding, and multimodal promptsStep 3.7 Flash by stepfun is offered by 21 providers on this page. Public prices are shown for 18 of them. Its official list price is $0.202 per 1M input tokens and $1.21 per 1M output tokens. Prices vary about 1.2× across the providers that host it. It also has 1 free ($0) channel and 2 covered by a paid subscription; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.
Median output speed is 198 tokens per second, with 2.45s to the first token.
The context window is 256,000 tokens at the reference host, but hosts report different limits, from 256,000 to 262,144, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. Accepted input modalities are Text, Image, and Video. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Its training knowledge cuts off at 2026-03-01.
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| UnoRouter step-3.7-flash:free | Gateway | Free | — | — | 256,000 | 256,000 | deprecated | |
| StepFun (Global)Official | First-party | $0.20 | $1.15 | $0.04 | — | 256,000 | 256,000 | |
| LLM Gateway | Gateway | $0.20 | $1.15 | $0.04 | — | 262,144 ⚠ | 256,000 | |
| CommandCode stepfun/Step-3.7-Flash | Gateway | $0.20 | $1.15 | $0.04 | — | 256,000 | 256,000 | |
| Requesty | Gateway | $0.20 | $1.15 | $0.04 | — | 262,144 ⚠ | 256,000 | |
| NanoGPT stepfun/step-3.7-flash:thinking | Gateway | $0.20 | $1.15 | $0.04 | — | 262,144 ⚠ | 256,000 | |
| DevPass (LLM Gateway) | Gateway | $0.20 | $1.15 | $0.04 | — | 262,144 ⚠ | 256,000 | |
| Novita AI | Gateway | $0.20 | $1.15 | $0.04 | — | 262,144 ⚠ | 256,000 | |
| OpenRouter | Gateway | $0.20 | $1.15 | $0.04 | — | 262,144 ⚠ | 230,400 | |
| ZenMux | Gateway | $0.20 | $1.15 | $0.04 | — | 256,000 | 256,000 |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Interleaved thinking (reasoning between tool calls) is declared by 6 of 21 providers.
2 / 21 providers expose no reasoning control (reasoning_options: []).
1 more channels offer $0 (UnoRouter); free tiers usually have rate limits and no SLA, excluded from ranking.
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| SWE-Bench Pro | — | 56.3 | resolve rate | Source ↗ |
| SWE-Bench Verified | — | 76.5 | resolved | Source ↗ |
| Terminal-Bench | v2.1 | 59.6 | success rate | Source ↗ |
| Humanity's Last Exam | variant: with tools | 47.2 | accuracy | Source ↗ |
| BrowseComp | — | 75.8 | accuracy | Source ↗ |
| Toolathlon | — | 49.5 | success rate | Source ↗ |
| GDPval | — | 45.8 | wins or ties | Source ↗ |
| ClawEval | v1.1 | 67.1 | pass^3 | Source ↗ |
| Artificial Analysis Coding Index | — | 37.1 | index | Source ↗ |
| SciCode | — | 40 | percent correct | Source ↗ |
| Terminal-Bench Hard | — | 35.6 | success rate | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.