197K context · — params · —
minimax/minimax-m2-5
MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...
Reachability & verification
Live reachability
Target (MiniMax): https://api.minimax.io/v1
Overseas reference latency (est.)
Live reachability probe
Measured in real time from the ModelHub gateway egress to this model's API endpoint. Green means reachable right now. Overseas reference latencies are estimates; the live probe is the proof of current reachability.
Official Path Verified by ModelHub
Pricing across providers
1Prices are shown in each provider's billing currency — ¥ (CNY) for Chinese providers, $ (USD) for overseas gateways.
| Provider | Input /1M | Output /1M | Blended | Ctx | p50 latency | API | Verified |
|---|---|---|---|---|---|---|---|
| MiniMaxminimax-m2.5 | ¥0.15 | ¥1.15 | ¥0.4 | 197K | — | OAI | 119d ago |
Works with
Any OpenAI-compatible client works — point the base URL at the provider endpoint.
Capabilities
Code samples
from openai import OpenAI
client = OpenAI(
base_url="https://api.minimax.io/v1",
api_key="YOUR_API_KEY",
)
resp = client.chat.completions.create(
model="minimax-m2.5",
messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)curl https://api.minimax.io/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "minimax-m2.5",
"messages": [{"role": "user", "content": "Hello!"}]
}'import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.minimax.io/v1",
apiKey: "YOUR_API_KEY",
});
const resp = await client.chat.completions.create({
model: "minimax-m2.5",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(resp.choices[0].message.content);Technical specs
Context
197K
Max output
197K
Parameters
—
Release
—
Training cutoff
—
License
—
Similar models
Frequently asked questions
How much does MiniMax M2.5 cost?
The cheapest tracked blended price is ¥0.4 per 1M tokens on MiniMax. See the pricing matrix above for input/output splits per provider.
Can I use MiniMax M2.5 from outside China?
Availability depends on the hosting provider. Use our Path Planner on the MiniMax page to map a verified official-vs-brokered access path, including payment and KYC constraints.
Is MiniMax M2.5 open source?
Yes — MiniMax M2.5 is open-weight under the — license. You can self-host it or use any listed inference provider.
Is MiniMax M2.5 OpenAI-compatible?
Yes — at least one tracked provider exposes an OpenAI-compatible endpoint, so Cursor, Cline, Aider and similar clients work with just a base-URL change.
What is the maximum context window?
MiniMax M2.5 supports up to 197K tokens of context with a maximum output of 197K tokens.
Need verified access to MiniMax M2.5?
We broker vetted intros to MiniMax — payment, KYC and endpoint verification handled.