Skip to content
  • Models
  • Rankings
  • Ori
Sign Up
Sign Up
OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Collections
  • Providers
  • Tools
  • Pricing
  • Business
  • Enterprise
  • Labs

Company

  • About
  • Blog
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Trust Center
  • Support
  • Works With OR
  • Data
  • Brand

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status
  • AI Site Map

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
Favicon for stepfun

StepFun: Step 3.7 Flash

Going away October 1, 2026

stepfun/step-3.7-flash

Model weights
Compare

Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters per token. The model supports a 256K context window and exposes selectable reasoning levels (high/medium/low), letting callers trade off speed, cost, and depth of reasoning.

Designed for coding, agentic workflows, structured outputs, and long-context productivity tasks.

Modalities
In / Out Price
20% off
$0.16 / $0.92per 1M
Context
262K
Released
May 28, 2026
Compare
ProvidersPricingPerformanceUptimeBenchmarksAppsActivityFAQExplore

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), Floor (cheapest), or Exacto (highest tool-calling accuracy).

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.

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).

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.

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.

Benchmark score summary for StepFun: Step 3.7 Flash (Artificial Analysis and Design Arena)
SourceBenchmarkScore
Artificial AnalysisStep 3.7 Flash Coding Index39.6
Artificial AnalysisStep 3.7 Flash GPQA Diamond80.9%
Artificial AnalysisStep 3.7 Flash HLE21.4%
Artificial AnalysisStep 3.7 Flash IFBench67.3%
Artificial AnalysisStep 3.7 Flash τ²-Bench Telecom98.5%
Artificial AnalysisStep 3.7 Flash AA-LCR73.7%
Artificial AnalysisStep 3.7 Flash GDPval-AA17.2%
Artificial AnalysisStep 3.7 Flash CritPt2.3%
Artificial AnalysisStep 3.7 Flash SciCode43.9%
Artificial AnalysisStep 3.7 Flash Terminal-Bench Hard35.6%
Artificial AnalysisStep 3.7 Flash AA-Omniscience Accuracy25.8%
Artificial AnalysisStep 3.7 Flash AA-Omniscience Non-Hallucination Rate15.0%
Design ArenaStep 3.7 Flash Models Arena 3D Elo1147
Design ArenaStep 3.7 Flash Models Arena Asciiart Elo1163
Design ArenaStep 3.7 Flash Models Arena Code Categories Elo1191
Design ArenaStep 3.7 Flash Models Arena Data Visualization Elo1180
Design ArenaStep 3.7 Flash Models Arena Game Development Elo1171
Design ArenaStep 3.7 Flash Models Arena SVG Elo1077
Design ArenaStep 3.7 Flash Models Arena UI Component Elo1190
Design ArenaStep 3.7 Flash Models Arena Website Elo1203

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.

Explore more models

AI Models with Vision: Multimodal LLMs for Image UnderstandingCollectionAI Model RankingsRanking
20% off
$0.20$0.16$1.15$0.92$0.04$0.0320.45s98 tps
99.90%
$0.20$1.15$0.0402.07s8 tps
99.56%
$0.20$1.15$0.0403.42s91 tps
99.66%
Throughput
98tok/s

P50, best across providers

Latency
0.45s

P50, best provider

Uptime (3d)The model was reachable. Request routed to a provider.
100.00%
Availability (3d)The model returned inference from any provider. Errors and empty responses count against it.
99.66%

Availability over the last 3 days

Last 72 hours
Availability 99.66%
3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability
99.64%
Without Routing
99.17%

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.

1.
Favicon for https://nousresearch.com
Hermes Agent
Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.
588Btokens
2.
Favicon for https://portal.nousresearch.com/api-docs
Nous Research API
Nous Research is an AI research team focused on advancing open-source AI.
7.54Btokens
3.
Favicon for https://cline.bot
Cline
Cline is an open-source AI coding agent that lives inside your IDE, autonomously exploring your codebase, editing files, running terminal commands, and using browser automation.
2.65Btokens
4.
Favicon for https://kilocode.ai/
Kilo Code
Kilo Code is an open-source AI coding agent that works across VS Code, JetBrains, and CLI to help developers ship code faster with agentic workflows.
1.37Btokens
5.
Favicon for https://github.com/Zoo-Code-Org/Zoo-Code
Zoo Code
new
801Mtokens

Frequently asked questions

Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters per token.

Step 3.7 Flash costs $0.16/M input tokens and $0.92/M output tokens, with separate rates for Cache Read at $0.032/M tokens.

Step 3.7 Flash has a 262,144 token context window. It supports up to 32,768 completion tokens.

Yes. Step 3.7 Flash accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

Step 3.7 Flash accepts text, images, and video as input and returns text.

Step 3.7 Flash is served by 3 providers on OpenRouter: DeepInfra, NovitaAI, 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 3.7 Flash was released on May 28, 2026.

More models from stepfun

Step 3.7 Flash

Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters per token. The model supports a 256K context window and exposes selectable reasoning levels (high/medium/low), letting callers trade off speed, cost, and depth of reasoning.

Designed for coding, agentic workflows, structured outputs, and long-context productivity tasks.

Text262K context$0.16 / $0.92
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. It is a reasoning model that is incredibly speed efficient even at long contexts.

Text262K context$0.10 / $0.30