GeniusRelay
Sign upConsole

StepFun: Step 3.7 Flash Thinking

step-3.7-flash:thinking

CompareAPIGet an API keyGet an API key

Step 3.7 Flash Thinking costs $0.260 per million input tokens and $1.50 per million output tokens, supports 262K context, and is available through the OpenAI-compatible API.

Step 3.7 Flash Thinking is StepFun's high-efficiency multimodal MoE model with visible reasoning enabled for deeper agentic coding, long-context reasoning, tool use, and native image/video understanding.

Modalities

Text + Image + Video → Text

Input / output price

$0.260 / $1.50 per 1M

Context

262K · max output 256K

Capabilities

ReasoningVisionTool callingLong contextOpen weights

Pricing

Billed per token actually used and deducted from your credits.

ItemUSD per 1M tokens
Input$0.260
Output$1.50
Cached input$0.052

Calculator

Drag the sliders to estimate what this model will cost.

Per request
$0.00198
Per day
$0.9880
Per month (30 days)
$29.64

Step 3.7 Flash Thinking: input $0.26/M · output $1.495/M · cached input $0.052/M

Request with these settings
curl https://api.geniusrelaygpt.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "step-3.7-flash:thinking", "max_tokens": 800,
       "messages": [{"role": "user", "content": "…"}]}'

Code samples

OpenAI-compatible. Set the base URL to https://api.geniusrelaygpt.com/v1 and the model to step-3.7-flash:thinking.

curl https://api.geniusrelaygpt.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "step-3.7-flash:thinking",
    "stream": true,
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Use it in a client: Cursor · Cline · SillyTavern · Codex

Parameters

Common OpenAI parameters can be passed as-is.

temperaturetop_pmax_tokensstreamstoppresence_penaltyfrequency_penaltyseed

FAQ

How is Step 3.7 Flash Thinking billed?
Input is $0.260 and output is $1.50 per million tokens; cached input is $0.052. The charge for every request is listed in Usage Logs in the console.
How long is the context window?
262K tokens. In a long conversation every turn is billed for the full input, so keep the history under control.
Does it support streaming?
Yes. Add "stream": true to the request to receive server-sent events in the OpenAI format.
Step 3.7 Flash Thinking API pricing · GeniusRelay