StepFun flash lane for quick multimodal reasoning and coding assistance
Step 3.5 Flash by stepfun is offered by 15 providers on this page. Public prices are shown for 11 of them. Its official list price is $0.10 per 1M input tokens and $0.30 per 1M output tokens. 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.
Artificial Analysis rates it 16.6 on the Intelligence Index. Against its lowest blended price of $0.142 per 1M, that is roughly 116 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 105 tokens per second, with 3.38s to the first token.
The context window is 256,000 tokens at the reference host, but hosts report different limits, from 64,000 to 262,144, so the usable window depends on the provider you pick. It supports reasoning and tool use. Accepted input modalities are Text and Image. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2025-01.
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 |
|---|---|---|---|---|---|---|---|---|
| Nvidia | Cloud | Free | — | — | 256,000 | 16,384 | deprecated | |
| Vercel AI Gateway | Cloud | $0.09 | $0.30 | $0.02 | — | 262,114 ⚠ | 262,114 | |
| EmpirioLabs AI step-3-5-flash | Gateway | $0.10 | $0.30 | $0.02 | — | 256,000 | 131,072 | |
| NanoGPT | Gateway | $0.10 | $0.30 | $0.05 | — | 262,144 ⚠ | 65,536 | |
| Kilo Gateway | Gateway | $0.10 | $0.30 | — | — | 262,144 ⚠ | 65,536 | |
| OpenRouter | Gateway | $0.10 | $0.30 | — | — | 262,144 ⚠ | 65,536 | |
| ZenMux | Gateway | $0.10 | $0.30 | — | — | 256,000 | 64,000 | |
| Hugging Face stepfun-ai/Step-3.5-Flash | Cloud | $0.10 | $0.30 | — | — | 262,144 ⚠ | 256,000 | |
| StepFun (Global)Official | First-party | $0.10 | $0.30 | $0.02 | — | 256,000 | 256,000 | |
| StepFun (China)Official | First-party | $0.10 | $0.30 | $0.02 | — | 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 4 of 15 providers.
5 / 15 providers expose no reasoning control (reasoning_options: []).
1 more channels offer $0 (Nvidia); free tiers usually have rate limits and no SLA, excluded from ranking.
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| Artificial Analysis Coding Index | — | 31.6 | index | Source ↗ |
| SciCode | — | 40.4 | percent correct | Source ↗ |
| Terminal-Bench Hard | — | 27.3 | success rate | Source ↗ |
| SWE-Bench Verified | — | 74.4 | resolved | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.
Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and harness, so rows are not comparable with one another. The Intelligence Index above draws on a different, newer set of evaluations.