MCP / Models / Language models

Claude Opus 5.5 MCP: complex coding with no API key

Anthropic Claude Opus 5.5 is the current Opus for complex coding, agents and analysis, with image input, a 1M-token context and reasoning from low to max. Run it from Claude Code, Codex, Cursor or any MCP client through one FlyMy.AI MCP, or call its API.

Use Claude Opus 5.5Inputs and price
No API key$4.00 / $20.00 per 1M tokensChat modelAnthropicCommercial use
Claude Opus 5.5 sample from the FlyMy.AI catalog

$ YOUR NEXT RUN

Claude CodeCodexCursorAny agent

Use Claude Opus 5.5 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/claude-opus-5-5.md. Help me connect the FlyMy.AI MCP to this assistant, then run Claude Opus 5.5 (flymyai/claude-opus-5-5) for this task: Ask Claude Opus 5.5: plan the steps to migrate this API to a new version.
Open FlyMy.AIDownload brief

What Claude Opus 5.5 does

Thinking cannot be turned off; reasoning_effort sets its depth. Send a prompt, or a chat history in messages with images as image_url parts, and get a text answer of up to 128K tokens from a 1M-token context. reasoning_effort is low, medium, high, xhigh or max (medium by default); system_prompt and max_tokens work as usual, and private_mode keeps the prompt and answer out of FlyMy.AI storage. Your FlyMy.AI key also works on the OpenAI-compatible Chat Completions endpoint and on Anthropic's Messages API at the model's FlyMy.AI address, so the official Anthropic SDK runs once you change its base URL; PDFs, prompt caching and reasoning_effort need the Messages API. Billing follows the tokens Anthropic reports, at Anthropic's own price. Tools Anthropic runs itself, such as web search, are not offered.

Guide: LLM API: GPT, Claude and Gemini with One Key

Claude Opus 5.5 inputs

Every input of flymyai/claude-opus-5-5 as its live schema lists them. Returns output (string), finish_reason (string), stream_details (string).

InputType, values and default
# prompt
string required What to ask Claude Opus 5.5
# 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, xhigh, max Default: medium How much effort Claude Opus 5.5 puts into the answer, reasoning included
# max_tokens
integer optional Allowed: 1 to 128000 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 Claude Opus 5.5: plan the steps to migrate this API to a new version.”runs flymyai/claude-opus-5-5
“Explain this stack trace and suggest a fix with Claude Opus 5.5.”runs flymyai/claude-opus-5-5
“With Claude Opus 5.5, turn these meeting notes into a list of action items with owners.”runs flymyai/claude-opus-5-5

Claude Opus 5.5 price

$4.00 per 1M input tokens, $20.00 per 1M output tokens, cached input $0.20 per 1M, cache writes $5.00 per 1M ($8.00 kept longer). Cached input is $0.20 per 1M tokens. Billed to your FlyMy.AI balance; no seats, no subscription and no minimum.

See usage pricing →

Call Claude Opus 5.5 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/claude-opus-5-5",
  "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/claude-opus-5-5/predict/stream/ \
  -H "X-API-KEY: $FLYMYAI_API_KEY" \
  -F 'prompt=Explain in two sentences what an MCP server is.'

With the OpenAI SDK

Claude Opus 5.5 also answers the OpenAI Chat Completions protocol.

from openai import OpenAI

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

Questions about Claude Opus 5.5

Do I need a Anthropic API key for Claude Opus 5.5?

No. Claude Opus 5.5 runs on FlyMy.AI's account, so you need no Anthropic key or plan: sign in to FlyMy.AI once and each run is billed to your FlyMy.AI balance.

How much does Claude Opus 5.5 cost?

$4.00 per 1M input tokens, $20.00 per 1M output tokens, cached input $0.20 per 1M, cache writes $5.00 per 1M ($8.00 kept longer). There is no subscription or minimum; the price comes from FlyMy.AI billing and was checked on 2026-11-12.

How do I use Claude Opus 5.5 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 Claude Opus 5.5: plan the steps to migrate this API to a new version." Your agent reads the inputs with get_model_schema and runs flymyai/claude-opus-5-5 with run_model.

What does Claude Opus 5.5 need as input?

Claude Opus 5.5 requires prompt; it also takes 5 optional inputs, each listed on this page with its allowed values and default.

Can I call Claude Opus 5.5 from my own code?

Yes. Send form fields to https://api.flymy.ai/api/v1/flymyai/claude-opus-5-5/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/claude-opus-5-5/openai/v1.

Go to the source

Claude Opus 5.5 in the playground →Claude Opus 5.5 guide in the docs →Model endpoints in the docs →Every model on FlyMy.AI →Every MCP in the catalog →Usage pricing →

From the FlyMy.AI model catalog of 2026-11-12: inputs from the model's live schema, prices from FlyMy.AI billing. Requests are examples to paste, not recorded runs.