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. It is a reasoning model that is incredibly speed efficient even at long contexts.
Modalities
In / Out Price
$0.10 / $0.30per 1M
Context
262K
Released
Jan 29, 2026
This model is hosted by one provider. OpenRouter forwards every request to it directly — no routing decisions to make.
The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.
Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).
Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.
Scores on standardized evaluations. Higher percentages are better — and rank percentile shows where this model lands among all models on OpenRouter.
| Source | Benchmark | Score |
|---|---|---|
| Artificial Analysis | Step 3.5 Flash 2603 GPQA Diamond | 82.6% |
| Artificial Analysis | Step 3.5 Flash 2603 HLE | 24.5% |
| Artificial Analysis | Step 3.5 Flash 2603 IFBench | 66.5% |
| Artificial Analysis | Step 3.5 Flash 2603 τ²-Bench Telecom | 87.4% |
| Artificial Analysis | Step 3.5 Flash 2603 AA-LCR | 63.0% |
| Artificial Analysis | Step 3.5 Flash 2603 CritPt | 2.3% |
| Artificial Analysis | Step 3.5 Flash 2603 Terminal-Bench Hard | 32.6% |
| Artificial Analysis | Step 3.5 Flash 2603 AA-Omniscience Accuracy | 24.6% |
| Artificial Analysis | Step 3.5 Flash 2603 AA-Omniscience Non-Hallucination Rate | 8.7% |
| Artificial Analysis | Step 3.5 Flash GPQA Diamond | 83.1% |
| Artificial Analysis | Step 3.5 Flash HLE | 21.1% |
| Artificial Analysis | Step 3.5 Flash IFBench | 64.6% |
| Artificial Analysis | Step 3.5 Flash τ²-Bench Telecom | 94.4% |
| Artificial Analysis | Step 3.5 Flash AA-LCR | 50.0% |
| Artificial Analysis | Step 3.5 Flash CritPt | 2.5% |
| Artificial Analysis | Step 3.5 Flash Terminal-Bench Hard | 27.3% |
| Artificial Analysis | Step 3.5 Flash AA-Omniscience Accuracy | 23.6% |
| Artificial Analysis | Step 3.5 Flash AA-Omniscience Non-Hallucination Rate | 14.3% |
Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.
Token volume and request traffic to this model over time.
Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.
| $0.10 | $0.30 | 1.29s | 66 tps |
Throughput
66tok/s
P50, best across providers
Latency
1.29s
P50, best provider
100.00%
97.92%
When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and customization options.
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. It is a reasoning model that is incredibly speed efficient even at long contexts.
Step 3.5 Flash costs $0.10/M input tokens and $0.30/M output tokens.
Step 3.5 Flash has a 262,144 token context window. It supports up to 65,536 completion tokens.
Yes. Step 3.5 Flash accepts tools and tool_choice for function calling. It does not support response_format, so JSON output is not enforced.
Step 3.7 Flash is another text model from StepFun.
Step 3.5 Flash was released on January 29, 2026.