StepFun: Step 5 Preview
stepfun/step-5-preview
Model weightsStep 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). It performs strongly in software engineering and professional knowledge work, with particular strength in finance.
It is designed for extended tasks that span large codebases and documents, using tools and refining results over multiple steps.
Providers
Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick: Balanced (price + speed), Nitro (fastest), or Floor (cheapest).
| $1.00 | $2.70 | $0.10 | 4.68s | 20 tok/s | ||
| $1.00 | $2.70 | $0.10 | 3.50s | 104 tok/s |
- Input $1.00 / Output $2.7020 tok/s6.52% uptime
- Input $1.00 / Output $2.70104 tok/s99.92% uptime
Pricing
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.
Weighted average
Step 5 Preview — Price history
| $0.145 | $2.70 | 95.0% | 100.0% | ||
| $0.593 | $2.70 | 45.2% | 0.0% |
- Effective in $0.145 / Effective out $2.70Token share100.0%
- Effective in $0.593 / Effective out $2.70Token share0.0%
Performance
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).
P50, best across providers
P50, best provider
Uptime
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.
Availability over the last 3 days
Last 72 hoursAvailability over the last 24 hours
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 provider routing options.
Benchmarks
Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.
| Source | Benchmark | Score |
|---|---|---|
| Artificial Analysis | Step 5 Preview Intelligence Index | 28.5 |
| Artificial Analysis | Step 5 Preview HLE | 46.5% |
| Artificial Analysis | Step 5 Preview AA-LCR | 88.3% |
| Artificial Analysis | Step 5 Preview GDPval-AA | 54.6% |
| Artificial Analysis | Step 5 Preview CritPt | 20.9% |
| Artificial Analysis | Step 5 Preview SciCode | 58.9% |
| Artificial Analysis | Step 5 Preview Terminal-Bench 4.0 | 33.3% |
| Artificial Analysis | Step 5 Preview AA-Omniscience Accuracy | 36.4% |
| Artificial Analysis | Step 5 Preview AA-Omniscience Non-Hallucination Rate | 68.7% |
| Vals AI | Step 5 Preview BioMysteryBench | 67.4% |
| Vals AI | Step 5 Preview Code Migration v1.1 | 47.0% |
| Vals AI | Step 5 Preview EMB v1.1 | 69.6% |
| Vals AI | Step 5 Preview Finance Agent v2.1 | 58.9% |
| Vals AI | Step 5 Preview Vals Finance Index | 55.4% |
| Vals AI | Step 5 Preview HLAB-Vals-1.1 | 12.9% |
| Vals AI | Step 5 Preview IOI | 38.1% |
| Vals AI | Step 5 Preview Vals Legal Index | 70.2% |
| Vals AI | Step 5 Preview Legal Research Bench | 40.4% |
| Vals AI | Step 5 Preview MysteryMechanism | 18.5% |
| Vals AI | Step 5 Preview ProofBench v1.1 | 42.0% |
| Vals AI | Step 5 Preview Public Benefits Bench v1.1 | 58.1% |
| Vals AI | Step 5 Preview Vals Science Index | 29.6% |
| Vals AI | Step 5 Preview SRE Bench | 0.4% |
| Vals AI | Step 5 Preview SWE-bench Multimodal | 40.8% |
| Vals AI | Step 5 Preview Tax Agent Bench | 27.3% |
| Vals AI | Step 5 Preview Terminal-Bench 4.0 | 31.8% |
| Vals AI | Step 5 Preview Terminal-Bench-Science | 2.9% |
| Vals AI | Step 5 Preview Vals Index | 54.8% |
| Vals AI | Step 5 Preview Vibe Code Bench v1.1 | 70.4% |
Apps
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.

Activity
Token volume and request traffic to this model over time.
API
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.
Not currently available through EU in-region routing. In-region routing docs
Frequently asked questions
Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). It performs strongly in software engineering and professional knowledge work, with particular strength in finance. It is designed for extended tasks that span large codebases and documents, using tools and refining results over multiple steps.
Step 5 Preview costs $1.00/M input tokens and $2.70/M output tokens, with separate rates for Cache Read at $0.10/M tokens.
Step 5 Preview has a 1,000,000 token context window. It supports up to 32,768 completion tokens.
Yes. Step 5 Preview accepts tools for function calling. It also supports structured outputs via a JSON schema in response_format.
Step 5 Preview accepts text, images, and video as input and returns text.
Step 5 Preview is served by 2 providers on OpenRouter: Featherless and StepFun. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.
Step 5 Preview was released on October 8, 2026.