MCP / Models / Language models

Step 5 Preview MCP: agents and coding with no API key

StepFun Step 5 Preview is an open-weight 600B mixture-of-experts model for agents and coding, with image input, function tools and a 262K-token context. Run it from Claude Code, Codex, Cursor or any MCP client through one FlyMy.AI MCP, or call its API.

No API key$1.00 / $2.70 per 1M tokensChat modelStepFunCommercial use
Step 5 Preview sample from the FlyMy.AI catalog

$ YOUR NEXT RUN

Claude CodeCodexCursorAny agent

Use Step 5 Preview in your assistant

Paste this prompt into Claude Code, Codex, Cursor or any agent. It reads the guide and helps you connect.

Read https://flymy.ai/skill.md and https://flymy.ai/mcp/models/step-5-preview.md. Help me connect the FlyMy.AI MCP to this assistant, then run Step 5 Preview (flymyai/step-5-preview) for this task: Ask Step 5 Preview: review this function for bugs and explain the fix.
Open FlyMy.AIDownload brief

What Step 5 Preview does

Send a prompt, or a chat history in messages with images as image_url parts, and get a text answer from a 262K-token context. reasoning_effort is low, medium or high (medium by default), and reasoning tokens are billed as output; system_prompt and max_tokens (up to 32,768) work as usual, and private_mode keeps the prompt and answer out of FlyMy.AI storage and logs on synchronous calls. Call it with your FlyMy.AI key in two ways: the FlyMy.AI API, or the OpenAI-compatible Chat Completions endpoint, where it also calls your function tools and takes their results back. A request with function tools is served by a host that takes 262,144 tokens of context and answers up to 32,768 tokens; a request without tools may reach the model's own host, which takes a 1M-token context. It answers in text only; use the image, video and audio models to create media.

Step 5 Preview inputs

Every input of flymyai/step-5-preview as its live schema lists them. Returns output (string), finish_reason (string), service_tier (string), reasoning (string), stream_details (string).

InputType, values and default
# prompt
string required What to ask Step 5 Preview
# messages
string optional Chat history as a JSON array of {role, content}; used instead of the prompt
# system_prompt
string optional Instructions for the whole chat
# reasoning_effort
string optional Allowed: low, medium, high Default: medium How hard Step 5 Preview thinks before answering
# max_tokens
integer optional Allowed: 1 to 32768 Most tokens to generate, reasoning included
# private_mode
boolean optional Default: false Keep the prompt and the answer out of FlyMyAI storage and logs (synchronous requests only)

Ask your agent

Requests to paste as they are, once the FlyMy.AI MCP is connected.

“Ask Step 5 Preview: review this function for bugs and explain the fix.”runs flymyai/step-5-preview
“Summarize this contract into five bullet points with Step 5 Preview.”runs flymyai/step-5-preview
“With Step 5 Preview, draft a friendly reply to this customer email.”runs flymyai/step-5-preview

Step 5 Preview price

$1.00 per 1M input tokens, $2.70 per 1M output tokens, cached input $0.10 per 1M. Cached input is $0.10 per 1M tokens. Billed to your FlyMy.AI balance; no seats, no subscription and no minimum.

Call Step 5 Preview from code

The same model, from an agent or from your own code. Keys stay in your FlyMy.AI account.

From an agent, through the MCP

The agent calls get_model_schema, then run_model with:

{
  "endpoint_id": "flymyai/step-5-preview",
  "input": {
    "prompt": "Explain in two sentences what an MCP server is."
  }
}

From your code, over HTTP

Form fields, not JSON; files go as uploads or public URLs. Text models answer on the streaming route.

curl -X POST https://api.flymy.ai/api/v1/flymyai/step-5-preview/predict/stream/ \
  -H "X-API-KEY: $FLYMYAI_API_KEY" \
  -F 'prompt=Explain in two sentences what an MCP server is.'

With the OpenAI SDK

Step 5 Preview also answers the OpenAI Chat Completions protocol.

from openai import OpenAI

client = OpenAI(base_url="https://api.flymy.ai/api/v1/flymyai/step-5-preview/openai/v1", api_key="YOUR_FLYMYAI_KEY")
reply = client.chat.completions.create(
    model="flymyai/step-5-preview",
    messages=[{"role": "user", "content": "Explain in two sentences what an MCP server is."}],
)
print(reply.choices[0].message.content)

Questions about Step 5 Preview

Do I need a StepFun API key for Step 5 Preview?

No. Step 5 Preview runs on FlyMy.AI's account, so you need no StepFun key or plan: sign in to FlyMy.AI once and each run is billed to your FlyMy.AI balance.

How much does Step 5 Preview cost?

$1.00 per 1M input tokens, $2.70 per 1M output tokens, cached input $0.10 per 1M. There is no subscription or minimum; the price comes from FlyMy.AI billing and was checked on 2026-11-18.

How do I use Step 5 Preview in Claude Code, Codex or Cursor?

Add the FlyMy.AI MCP with one command and sign in, then ask in plain words, for example: "Ask Step 5 Preview: review this function for bugs and explain the fix." Your agent reads the inputs with get_model_schema and runs flymyai/step-5-preview with run_model.

What does Step 5 Preview need as input?

Step 5 Preview requires prompt; it also takes 5 optional inputs, each listed on this page with its allowed values and default.

Can I call Step 5 Preview from my own code?

Yes. Send form fields to https://api.flymy.ai/api/v1/flymyai/step-5-preview/predict/stream/ with your FlyMy.AI API key in the X-API-KEY header; it also answers the OpenAI Chat Completions protocol at https://api.flymy.ai/api/v1/flymyai/step-5-preview/openai/v1.

Go to the source

From the FlyMy.AI model catalog of 2026-11-18: inputs from the model's live schema, prices from FlyMy.AI billing. Requests are examples to paste, not recorded runs.