Step-3.7 Flash

by stepfun · family step

Facts

Release date	—
Retired date	—
Knowledge cutoff	—
Context (max)	262,144
Max output	—
Modalities	text, image → text
Aliases	`step-3.7-flash`
Open weights	yes (stepfun-ai/Step-3.7-Flash)
Description	198B sparse-MoE VLM, 256K ctx, Apache 2.0; three reasoning levels; Advisor Mode.

Unknown values are shown as —.

Intelligence Index v4.1.1: 31 · base · Source: Artificial Analysis (accessed 2026-08-20)

Offerings

Provider	Wire ID	Variant	Endpoint	Protocol	Status	Price (USD / Mtok)	Reasoning
NVIDIA NIM API	`stepfun-ai/step-3.7-flash`	flash	v1-chat-completions	openai-chat	retired	—	effort · default on · mandatory · returns reasoning_content
OpenRouter	`stepfun/step-3.7-flash`	flash	chat-completions	openai-chat	ga	0.20 / 1.15	effort · default on · mandatory · returns reasoning_content · round-trips reasoning_content
StepFun	`step-3.7-flash`	flash	chat-completions	openai-chat	ga	0.20 / 1.15	effort · default on · returns reasoning_content

Reasoning controls

NVIDIA NIM API· stepfun-ai/step-3.7-flash· v1-chat-completions effort

reasoning_effort lowmedium●high

effort · default on · mandatory · returns reasoning_content

OpenRouter· stepfun/step-3.7-flash· chat-completions effort

reasoning.effort lowmedium●high

effort · default on · mandatory · returns reasoning_content · round-trips reasoning_content

StepFun· step-3.7-flash· chat-completions effort

reasoning_effort lowmedium●high Default level not documented; verify.

effort · default on · returns reasoning_content

Example requests

NVIDIA NIM API · openai-chat · stepfun-ai/step-3.7-flash

curl 'https://integrate.api.nvidia.com/v1/chat/completions' \
  -H 'Authorization: Bearer <YOUR_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "stepfun-ai/step-3.7-flash",
  "messages": [
    {
      "role": "user",
      "content": "Tell me about the weather."
    }
  ],
  "reasoning_effort": "medium"
}'

Python (requests)

import requests

resp = requests.post(
    "https://integrate.api.nvidia.com/v1/chat/completions",
    headers={
      "Authorization": "Bearer <YOUR_API_KEY>",
      "Content-Type": "application/json"
    },
    json={
      "model": "stepfun-ai/step-3.7-flash",
      "messages": [
        {
          "role": "user",
          "content": "Tell me about the weather."
        }
      ],
      "reasoning_effort": "medium"
    },
)
print(resp.json())

TypeScript (fetch)

const resp = await fetch("https://integrate.api.nvidia.com/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <YOUR_API_KEY>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "model": "stepfun-ai/step-3.7-flash",
    "messages": [
      {
        "role": "user",
        "content": "Tell me about the weather."
      }
    ],
    "reasoning_effort": "medium"
  }),
})
console.log(await resp.json())

OpenRouter · openai-chat · stepfun/step-3.7-flash

curl 'https://openrouter.ai/api/v1/chat/completions' \
  -H 'Authorization: Bearer <YOUR_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "stepfun/step-3.7-flash",
  "messages": [
    {
      "role": "user",
      "content": "Tell me about the weather."
    }
  ],
  "reasoning": {
    "effort": "medium"
  }
}'

Python (requests)

import requests

resp = requests.post(
    "https://openrouter.ai/api/v1/chat/completions",
    headers={
      "Authorization": "Bearer <YOUR_API_KEY>",
      "Content-Type": "application/json"
    },
    json={
      "model": "stepfun/step-3.7-flash",
      "messages": [
        {
          "role": "user",
          "content": "Tell me about the weather."
        }
      ],
      "reasoning": {
        "effort": "medium"
      }
    },
)
print(resp.json())

TypeScript (fetch)

const resp = await fetch("https://openrouter.ai/api/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <YOUR_API_KEY>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "model": "stepfun/step-3.7-flash",
    "messages": [
      {
        "role": "user",
        "content": "Tell me about the weather."
      }
    ],
    "reasoning": {
      "effort": "medium"
    }
  }),
})
console.log(await resp.json())

⚠ Responses include reasoning_content artifacts — pass them back unmodified on subsequent turns (dropping them triggers 400s or quality loss).

StepFun · openai-chat · step-3.7-flash

curl 'https://api.stepfun.ai/v1/chat/completions' \
  -H 'Authorization: Bearer <YOUR_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "step-3.7-flash",
  "messages": [
    {
      "role": "user",
      "content": "Tell me about the weather."
    }
  ],
  "reasoning_effort": "medium"
}'

Python (requests)

import requests

resp = requests.post(
    "https://api.stepfun.ai/v1/chat/completions",
    headers={
      "Authorization": "Bearer <YOUR_API_KEY>",
      "Content-Type": "application/json"
    },
    json={
      "model": "step-3.7-flash",
      "messages": [
        {
          "role": "user",
          "content": "Tell me about the weather."
        }
      ],
      "reasoning_effort": "medium"
    },
)
print(resp.json())

TypeScript (fetch)

const resp = await fetch("https://api.stepfun.ai/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <YOUR_API_KEY>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "model": "step-3.7-flash",
    "messages": [
      {
        "role": "user",
        "content": "Tell me about the weather."
      }
    ],
    "reasoning_effort": "medium"
  }),
})
console.log(await resp.json())