LLM Reference

Step 3.5 Flash vs Step 3.7 Flash

Step 3.5 Flash (2026) and Step 3.7 Flash (2026) are frontier-tier reasoning models from StepFun. Step 3.5 Flash ships a 256k-token context window, while Step 3.7 Flash ships a 256k-token context window. On pricing, Step 3.5 Flash costs $0.10/1M input tokens versus $0.20/1M for the alternative. This comparison covers specs, pricing, capabilities, benchmarks, provider availability, and production fit. It focuses on practical selection signals rather than broad model-family marketing.

Step 3.5 Flash is ~100% cheaper at $0.10/1M; pay for Step 3.7 Flash only for vision-heavy evaluation.

Decision scorecard

Local evidence first
SignalStep 3.5 FlashStep 3.7 Flash
Best forreasoning-heavy appsreasoning-heavy apps, multimodal apps, and tool-calling agents
Decision fitLong contextCoding, RAG, and Agents
Context window256k256k
Cheapest output$0.30/1M tokens$1.15/1M tokens
Provider routes1 tracked3 tracked
Shared benchmarks0 rows0 rows

Decision tradeoffs

Choose Step 3.5 Flash when...
  • Step 3.5 Flash has the lower cheapest tracked output price at $0.30/1M tokens.
  • Local decision data tags Step 3.5 Flash for Long context.
Choose Step 3.7 Flash when...
  • Step 3.7 Flash has broader tracked provider coverage for fallback and procurement flexibility.
  • Step 3.7 Flash uniquely exposes Vision, Multimodal, and Function calling in local model data.
  • Local decision data tags Step 3.7 Flash for Coding, RAG, and Agents.

Monthly cost at traffic

Estimate token spend from the cheapest tracked input and output route or tier on this page.

Lower estimate Step 3.5 Flash

Step 3.5 Flash

$155

Cheapest tracked route/tier: OpenRouter

Step 3.7 Flash

$448

Cheapest tracked route/tier: StepFun

Estimated monthly gap: $293. Batch, cache, alternate speed tiers, and negotiated pricing are excluded from this local estimate.

Switch friction

Step 3.5 Flash -> Step 3.7 Flash
  • Provider overlap exists on OpenRouter; start route-level A/B tests there.
  • Step 3.7 Flash is $0.85/1M tokens higher on cheapest tracked output pricing, so quality gains need to justify the spend.
  • Step 3.7 Flash adds Vision, Multimodal, and Function calling in local capability data.
Step 3.7 Flash -> Step 3.5 Flash
  • Provider overlap exists on OpenRouter; start route-level A/B tests there.
  • Step 3.5 Flash is $0.85/1M tokens lower on cheapest tracked output pricing before cache, batch, or negotiated discounts.
  • Check replacement coverage for Vision, Multimodal, and Function calling before moving production traffic.

Specs

Specification
Released2026-01-292026-05-29
Context window256k256k
Parameters196B (11B active)198B (11B active)
Architecturemixture of expertsmixture of experts
LicenseOpen SourceApache 2.0
Knowledge cutoff--

Pricing and availability

Pricing attributeStep 3.5 FlashStep 3.7 Flash
Input price$0.10/1M tokens$0.20/1M tokens
Output price$0.30/1M tokens$1.15/1M tokens
Providers

Capabilities

CapabilityStep 3.5 FlashStep 3.7 Flash
VisionNoYes
MultimodalNoYes
ReasoningYesYes
Function callingNoYes
Tool useNoYes
Structured outputsNoYes
Code executionNoNo
IDE integrationNoNo
Computer useNoNo
Parallel agentsNoNo

Benchmarks

No shared benchmark rows are currently sourced for this pair.

Deep dive

The capability footprint differs most on vision: Step 3.7 Flash, multimodal input: Step 3.7 Flash, function calling: Step 3.7 Flash, tool use: Step 3.7 Flash, and structured outputs: Step 3.7 Flash. Both models share reasoning mode, so the practical split is not just feature count. Use those differences to decide whether the page is about raw model quality, agentic coding support, multimodal ingestion, or predictable structured API behavior.

For cost, Step 3.5 Flash lists $0.10/1M input and $0.30/1M output tokens on the cheapest tracked provider, while Step 3.7 Flash lists $0.20/1M input and $1.15/1M output tokens on the cheapest tracked provider. A 70/30 input-output blend puts Step 3.5 Flash lower by about $0.33 per million blended tokens. Availability is 1 providers versus 3, so concentration risk also matters.

Choose Step 3.5 Flash when provider fit and lower input-token cost are central to the workload. Choose Step 3.7 Flash when vision-heavy evaluation and broader provider choice are more important. For production, rerun your own prompts through the exact provider, region, and tool stack you plan to ship. This keeps the decision grounded in measurable tradeoffs instead of brand-level assumptions.

FAQ

Which has a larger context window, Step 3.5 Flash or Step 3.7 Flash?

Step 3.5 Flash supports 256k tokens, while Step 3.7 Flash supports 256k tokens. That gap matters most for long documents, large codebases, retrieval-heavy agents, and conversations where earlier context must remain visible.

Which is cheaper, Step 3.5 Flash or Step 3.7 Flash?

Step 3.5 Flash is cheaper on tracked token pricing. Step 3.5 Flash costs $0.10/1M input and $0.30/1M output tokens. Step 3.7 Flash costs $0.20/1M input and $1.15/1M output tokens. Provider discounts or batch pricing can still change the final bill.

Is Step 3.5 Flash or Step 3.7 Flash open source?

Step 3.5 Flash is listed under Open Source. Step 3.7 Flash is listed under Apache 2.0. License labels affect whether you can self-host, redistribute weights, or rely only on hosted APIs, so confirm the upstream license before deployment.

Which is better for vision, Step 3.5 Flash or Step 3.7 Flash?

Step 3.7 Flash has the clearer documented vision signal in this comparison. If vision is mission-critical, validate it against the provider endpoint because model-level support and API-level exposure can differ.

Which is better for multimodal input, Step 3.5 Flash or Step 3.7 Flash?

Step 3.7 Flash has the clearer documented multimodal input signal in this comparison. If multimodal input is mission-critical, validate it against the provider endpoint because model-level support and API-level exposure can differ.

Where can I run Step 3.5 Flash and Step 3.7 Flash?

Step 3.5 Flash is available on OpenRouter. Step 3.7 Flash is available on StepFun, OpenRouter, and NVIDIA NIM. Provider coverage can affect latency, region availability, compliance posture, and fallback options.

Continue comparing

Last reviewed: 2026-05-29. Data sourced from public model cards and provider documentation.