Step 3.7 Flash API

Model details

Context window

262K tokens

Max output

256K tokens

Input

Text, images

Output

Text

Capabilities

Reasoning, Vision, Tool calling, Streaming

Interfaces

OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses

Why teams pick it

• Step 3.7 Flash for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses.

Call Step 3.7 Flash

Step 3.7 Flash answers on any of the APIs below — pick the one your code already speaks and just swap in your Inferray key.

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

curl https://api.inferray.com/v1/messages \
  -H "Authorization: Bearer inferray_..." \
  -H "Content-Type: application/json" \
  -d '{
  "model": "step-3.7-flash",
  "max_tokens": 1024,
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ]
}'

curl https://api.inferray.com/v1/responses \
  -H "Authorization: Bearer inferray_..." \
  -H "Content-Type: application/json" \
  -d '{
  "model": "step-3.7-flash",
  "input": "Hello"
}'

Use Step 3.7 Flash in your tools

Every coding agent below has a setup guide. Set the model to step-3.7-flash.

• Claude Code
• Codex
• opencode
• Cline
• Roo Code
• Aider
• Continue

More from Stepfun

Alternatives to Step 3.7 Flash

• CodestralCodestral for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses.Mistral
• GLM-4.6VGLM-4.6V for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses.Z.ai
• GPT-5.6 LunaCost-optimized GPT-5.6 for high-volume tasks.OpenAI

Questions about this model

How much does the Step 3.7 Flash API cost?

Step 3.7 Flash costs $0.2 per 1M input tokens and $1.15 per 1M output tokens on Inferray, and cached input is $0.04 per 1M. That is the list price, with no gateway fee on top.

Is there a free tier for Step 3.7 Flash?

No. You add credit and pay Step 3.7 Flash's list rate for each request — seats, projects, and API keys are free, and pay-as-you-go credit never expires.

Am I charged for failed requests?

No. A request that fails without returning a result is not billed. If a response fails part-way, the tokens already processed before the failure are charged.

Is Step 3.7 Flash included in Token Plans?

No. Step 3.7 Flash is pay-as-you-go only; Token Plans cover the other text models in the catalog.

Can I use Step 3.7 Flash in Claude Code?

Yes. Set ANTHROPIC_BASE_URL to https://api.inferray.com, ANTHROPIC_AUTH_TOKEN to your Inferray key, and ANTHROPIC_MODEL to step-3.7-flash. The same key works in Codex, opencode, Cline, and other agents.

Does Step 3.7 Flash support tool calling and vision?

Step 3.7 Flash supports tool calling, image input, reasoning and streaming on Inferray.

Is it the real Step 3.7 Flash?

Yes. A request for step-3.7-flash is answered by Step 3.7 Flash from Stepfun, billed at its published list price. Inferray never substitutes a different or smaller model.