Skip to navigation

Step 3.7 Flash

Step 3.7 Flash
StepFun · Text Generation
POST /v1/chat/completions

StepFun multimodal reasoning model with image and video input, tool calling, adjustable reasoning effort, and 256K context.

See Step 3.7 Flash pricing and specs or try it in the Playground.

At a glance

FieldValue
Model idstep-3-7-flash
Model release date2026-05-28
Input modalitiesText, Image, Video
Output modalitiesText
Context window256K
Weight precision-
Max output tokens131,072
RegionInternational
Featuresreasoning, function_calling, structured_output, vision, video, prompt_cache, agentic_coding, web_search
Native inferenceNo
NewNo
Structured outputJSON Mode
Supported endpointsPOST /v1/chat/completions, POST /v1/responses, POST /v1/messages, POST /v1beta/models/step-3-7-flash:generateContent
Alternate model idsstep-3.7-flash, stepfun/step-3-7-flash, stepfun/step-3.7-flash

Pricing

ChargeSpecRate
Inputper 1M prompt tokens$0.20
Outputper 1M generated tokens$1.15
Implicit cache readper 1M cached input tokens$0.04
Web Search (Linkup)per call when invoked$0.013

Example request

curl https://api.empiriolabs.ai/v1/chat/completions \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
-H 'Content-Type: application/json' \
-d '{"model": "step-3-7-flash", "messages": [{"role":"user","content":"Hello"}]}'

Parameters

ParameterTypeRequiredDefaultDescription
temperaturenumberno0.5Sampling temperature. · Range: 0 – 2
top_pnumberno0.9Nucleus sampling probability mass. · Range: 0.01 – 1
max_tokensintegerno4096Maximum output tokens. Reasoning tokens count toward this limit. · Range: 1 – 131072
stoparrayno-Stop sequences.
frequency_penaltynumberno0Penalty for repeated tokens. · Range: -2 – 2
reasoning_effortenumno"low"Controls how much the model reasons before it answers. Higher effort spends more tokens on reasoning. · Allowed: low, medium, high
response_formatobjectno-OpenAI-compatible response format. Use {“type”:“json_object”} for JSON object mode.
reasoning_formatenumno"general"Format of the reasoning trace returned alongside the answer. · Allowed: general, deepseek-style
toolsarrayno-OpenAI-compatible function tools.
tool_choicestringno-OpenAI-compatible tool choice.
web_search_linkupbooleannofalseOptional web search powered by Linkup. When enabled, recent web sources are retrieved using your latest user message as the query and provided to the model as additional context. Adds $0.013 per call when invoked on top of the model’s normal token cost. Disabled by default.
disable_formattingbooleannofalseReturn the answer without the Sources list that web search adds.

Notes

Supports text, image, and video input with 256K context, function tools, JSON object mode, reasoning_effort low, medium, or high, and optional Linkup web search. Video input supports MP4 under 128 MB, with clips under 5 minutes recommended.


Machine-readable schema: GET https://api.empiriolabs.ai/v1/models/step-3-7-flash.