Model Library
StepFunReleased February 2, 2026Step 3.5 Flash
StepFun · Released February 2, 2026
Intelligence score
26
At a glance
- Intelligence
- 26
- Speed
- 181.7tokens/sec
- Latency
- 1.26stime to first token
- Input price
- $0.10per 1M tokens
- Output price
- $0.30per 1M tokens
- Context window
- 260Ktokens
- Parameters
- 196billions
Summary
Comparison summary
Step 3.5 Flash scores 26 (estimated) on the Artificial Analysis Intelligence Index, placing it above average among other open weight models of similar size (median: 25). Step 3.5 Flash generates output at 181.7 tokens per second (based on StepFun's API), which is well above average compared to other open weight models of similar size (median: 61.7 t/s). Step 3.5 Flash costs $0.10 per 1M input tokens (very competitive, median: $0.59) and $0.30 per 1M output tokens (very competitive, median: $2.20), based on StepFun's API.
Specifications
Technical specifications
| Model name | Step 3.5 Flash |
|---|---|
| Provider | StepFun |
| Release date | February 2, 2026 |
| Intelligence score | 26 |
| Speed | 181.7 tokens/sec |
| Latency (TTFT) | 1.26s |
| Input price | $0.10 / 1M tokens |
| Output price | $0.30 / 1M tokens |
| Context window | 260,000 tokens |
| Parameters | 196B |
| Reasoning | Yes |
| Input modalities | text |
| Output modalities | — |
| Open weights | Yes |
| License | Apache 2 |
| API availability | — |
| Source | Model Intelligence legacy profile: step-3-5-flash-0202 |
Pricing
Token prices
Price per 1M tokens
Step 3.5 Flash, as listed in the catalog record
- Input$0.10
- Output$0.30
| Token type | Price per 1M |
|---|---|
| Input | $0.10 |
| Output | $0.30 |
Model Intelligence legacy profile: step-3-5-flash-0202
FAQ · 20
Frequently asked questions
Step 3.5 Flash was released on February 2, 2026.
Step 3.5 Flash was created by StepFun.
Step 3.5 Flash scores 26 (estimated) on the Artificial Analysis Intelligence Index, placing it above average among other open weight models of similar size (median: 25).
Step 3.5 Flash generates output at 181.7 tokens per second (based on StepFun's API), which is well above average compared to other open weight models of similar size (median: 61.7 t/s).
Step 3.5 Flash has a time to first token (TTFT) of 1.26s (based on StepFun's API), which is very competitive compared to other open weight models of similar size (median: 2.01s).
Step 3.5 Flash costs $0.10 per 1M input tokens (very competitive, median: $0.59) and $0.30 per 1M output tokens (very competitive, median: $2.20), based on StepFun's API.
Step 3.5 Flash costs $0.10 per 1M input tokens and $0.30 per 1M output tokens (based on StepFun's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.12 per 1M tokens. Pricing may vary by provider.
Yes, Step 3.5 Flash is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.
Step 3.5 Flash supports text input.
Step 3.5 Flash supports text output.
No, Step 3.5 Flash does not support image input. It can only process text.
No, Step 3.5 Flash is not multimodal. It only supports text input.
Step 3.5 Flash has a context window of 260k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, Step 3.5 Flash is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Step 3.5 Flash has 196 billion parameters (11 billion active).
Step 3.5 Flash is a Mixture of Experts (MoE) model with 196 billion total parameters, but only 11 billion active parameters are used during inference.
Step 3.5 Flash is released under the Apache 2.0 license. This license allows commercial use.
Step 3.5 Flash achieves a score of 26 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, Step 3.5 Flash is available via API through 2 providers.
Step 3.5 Flash is available through 2 API providers.