AI Observatory / Model Radar
Stepfun / stepfun/step-3.5-flash
StepFun: Step 3.5 Flash
Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token....
262,144
Context
65,536
Max output
$0.10 / 1M
Prompt price
2026-01-29
Created
01 / Snapshot
Pricing, context, modalities, and parameters.
Model Radar detail pages stay neutral and operator-readable: core metadata first, then workflow fit.
| Provider | Stepfun | Input modalities | text |
|---|---|---|---|
| Output modalities | text | Prompt price | $0.10 / 1M |
| Completion price | $0.30 / 1M | Request price | N/A |
| Context length | 262,144 | Max completion tokens | 65,536 |
| Supported parameters | frequency_penalty, include_reasoning, logit_bias, max_tokens, min_p, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, temperature, tool_choice, tools, top_k, top_p | ||
Best for
stepfun/step-3.5-flash
StepFun: Step 3.5 Flash
Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token....
Long context
High-volume usage
Coding workflows
new
tool-capable
long-context
low-cost
03 / Colophon
Routes and exits.
Each model page stays simple: overview, compare, related models, then back to the public hub.