SunsetDiff

Replacement for MiniMax-M2.5-highspeed: what changes when you switch

The official replacement is MiniMax-M3.1-Flash. MiniMax-M2.5-highspeed shuts down on 2026-11-18 per MiniMax's deprecation page (checked 2026-11-12). Price, context window, and max output were left blank because the official pages we checked did not publish them.

MiniMax-M2.5-highspeed model page · MiniMax

Official replacement. Full diff page

MiniMax-M2.5-highspeed to MiniMax-M3.1-Flash

Some values not published Checked 2026-11-12.

Price per 1M tokens

Price comparison. Example monthly cost for 10M input tokens and 2M output tokens. Labeled example, not a bill.
FieldOldNewChange
Input Not published Not published Not published
Output Not published Not published Not published
Cached input Not published Not published Not published
Example monthly cost Not published Not published Example only

Context and max output

Token limits
LimitOldNewChange
Context window Not published Not published Not published
Max output Not published Not published Not published

Capabilities that differ

No differing capability values are published for both models.

Endpoint changes

  • The text generation guide shows an OpenAI-compatible client with base_url https://api.minimax.io/v1 and POST https://api.minimax.io/v1/chat/completions. This sample only changes the model field. Source

API changes

  • The model list says pay-as-you-go API requests stop working once M2.5 and M2.7 are retired. Starting October 19, 2026, M Plan and Token Plan requests are automatically routed to M3.1 Flash, and the existing model names keep working. The guide's sample for MiniMax-M3.1-Flash also sets reasoning_effort to max. This sample does not add that field. Source

Code

python before
from openai import OpenAI
client = OpenAI(base_url="https://api.minimax.io/v1", api_key="<MINIMAX_API_KEY>")
response = client.chat.completions.create(
    model="MiniMax-M2.5-highspeed",
    messages=[{"role": "user", "content": "Hi, how are you?"}],
)
python after
from openai import OpenAI
client = OpenAI(base_url="https://api.minimax.io/v1", api_key="<MINIMAX_API_KEY>")
response = client.chat.completions.create(
    model="MiniMax-M3.1-Flash",
    messages=[{"role": "user", "content": "Hi, how are you?"}],
)
typescript before
import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://api.minimax.io/v1", apiKey: "<MINIMAX_API_KEY>" });
const response = await client.chat.completions.create({
  model: "MiniMax-M2.5-highspeed",
  messages: [{ role: "user", content: "Hi, how are you?" }],
});
typescript after
import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://api.minimax.io/v1", apiKey: "<MINIMAX_API_KEY>" });
const response = await client.chat.completions.create({
  model: "MiniMax-M3.1-Flash",
  messages: [{ role: "user", content: "Hi, how are you?" }],
});
curl before
curl https://api.minimax.io/v1/chat/completions \
  -H "Authorization: Bearer <MINIMAX_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{"model":"MiniMax-M2.5-highspeed","messages":[{"role":"user","content":"Hi, how are you?"}]}'
curl after
curl https://api.minimax.io/v1/chat/completions \
  -H "Authorization: Bearer <MINIMAX_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{"model":"MiniMax-M3.1-Flash","messages":[{"role":"user","content":"Hi, how are you?"}]}'

Checklist

  1. Read the shutdown date for MiniMax-M2.5-highspeed on the MiniMax model list.
  2. Pay-as-you-go API requests stop working once these models are retired.
  3. M Plan and Token Plan requests are automatically routed to M3.1 Flash, and the existing model names keep working.
  4. Point your requests at MiniMax-M3.1-Flash and test before you send traffic.

Related models

Questions

What is the replacement for MiniMax-M2.5-highspeed?

The official replacement is MiniMax-M3.1-Flash. MiniMax-M2.5-highspeed shuts down on 2026-11-18 per MiniMax's deprecation page (checked 2026-11-12). Price, context window, and max output were left blank because the official pages we checked did not publish them.

Is MiniMax-M3.1-Flash cheaper than MiniMax-M2.5-highspeed?

A full price comparison is not published. One or both prices are missing from the official pages we checked.

Does MiniMax-M3.1-Flash have a bigger context window than MiniMax-M2.5-highspeed?

Context window sizes are not both published on the official pages we checked.

Sources

Deprecation alerts

We email you before models shut down. Unsubscribe anytime.

Deprecation alert signup
Providers (optional)