🐫 CaMeL Hub
中文 Console

MiniMax-M2.5 API

MiniMax-M2.5 is MiniMax's agentic-coding text model with a 204,800-token context window. Call it on CaMeL Hub via the OpenAI-compatible API — set base_url to https://api.camel-hub.com/v1 — at $1.575 per 1M input and $6.30 per 1M output tokens.

Pricing

per 1M input tokensper 1M output tokens
CaMeL Hub$1.575$6.3
Provider list price$0.3$1.2

Prices are the public default-group rate in USD per 1M tokens; input and output are billed separately. · Provider list price · verified 2026-07-11

Specifications

Provider
MiniMax
Context window
204800 tokens
Endpoints
anthropic, openai
MiniMax-M2.5 is the mainline text model from MiniMax, pitched in the company's own documentation as "Peak Performance. Ultimate Value." It is built for complex, multi-step work rather than one-shot Q&A: the M2 model family made its name in agentic coding, where a model has to plan a change, edit several files, read tool output, and keep going without losing the thread. Two specs matter most in practice. The context window is 204,800 tokens — enough to hold a mid-sized repository, a long tool-call transcript, or several large documents in a single request. MiniMax's model docs list output speed at roughly 60 tokens per second for the standard variant, which keeps interactive sessions responsive even on long generations. On CaMeL Hub the model is metered per token at $1.575 per 1M input and $6.30 per 1M output tokens, with streaming supported on both the OpenAI-compatible and Anthropic-compatible endpoints. Because input is priced well below output, M2.5 is at its most economical on input-heavy jobs: feeding it large codebases, logs, or document sets and asking for comparatively compact answers. You call it with the same API key and base_url as every other model on the platform, so switching to or away from it is a one-line change.

What it is good for

Quickstart

OpenAI-compatible: set base_url to https://api.camel-hub.com/v1 and use your CaMeL Hub API key. No SDK changes needed.

cURL

curl https://api.camel-hub.com/v1/chat/completions \
  -H "Authorization: Bearer $CAMEL_HUB_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "MiniMax-M2.5",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Python

from openai import OpenAI

client = OpenAI(
    api_key="$CAMEL_HUB_KEY",
    base_url="https://api.camel-hub.com/v1",  # <-- the only change vs. the OpenAI default
)

resp = client.chat.completions.create(
    model="MiniMax-M2.5",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)

Node.js

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.CAMEL_HUB_KEY,
  baseURL: "https://api.camel-hub.com/v1", // <-- the only change vs. the OpenAI default
});

const resp = await client.chat.completions.create({
  model: "MiniMax-M2.5",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(resp.choices[0].message.content);

Get an API key Browse integration guides

Frequently asked questions

How is MiniMax-M2.5 billed on CaMeL Hub?

Per token, with input and output priced separately: $1.575 per 1M input tokens and $6.30 per 1M output tokens on the public default group. There is no per-request fee — you pay only for the tokens the model actually processes.

Does MiniMax-M2.5 support streaming?

Yes. Pass "stream": true in your request and tokens arrive incrementally over server-sent events, exactly as with the official OpenAI SDK. Streaming works on both the OpenAI-compatible and Anthropic-compatible endpoints.

What is the context window of MiniMax-M2.5?

204,800 tokens, per MiniMax's official model documentation. Prompt and completion share this window, so leave headroom for the answer when you pack in large inputs.

Which API formats can I use to call it?

Both the OpenAI-compatible endpoint (/v1/chat/completions) and the Anthropic-compatible endpoint (/v1/messages). Point your client's base_url at https://api.camel-hub.com/v1, keep your existing SDK, and set the model name to MiniMax-M2.5.

How do I get started with MiniMax-M2.5?

Register at the CaMeL Hub console (https://api.camel-hub.com/console), create an API key, then set base_url to https://api.camel-hub.com/v1 in any OpenAI-compatible SDK. No other code changes are needed — the same key works for every model on the platform.

Compare with other models