Verified 2026-11-18 · rates follow the live catalog

MiniMax API: models, prices and how to call them

2 MiniMax models are in the catalog, from MiniMax M3 at $0.00072 for one request to MiniMax M2.7 at $0.0072, a 10.0× spread inside one family. Prices are what each model bills at its most expensive hour of the day. One request is a 20,000-token prompt with a 1,000-token reply and nothing cached, an illustration and not a measurement of your traffic.

MiniMax models and what a request costs

MiniMax models: rates per 1M tokens, and the cost of one request and of 1,000
ModelContextInput / 1MOutput / 1MCached input / 1MOne request (20,000 in, 1,000 out)1,000 requests
MiniMax M31.0M$0.03$0.12$0.006$0.00072$0.72
MiniMax M2.7200K$0.30$1.20—$0.0072$7.20

What each MiniMax model accepts

MiniMax models: what each one takes as input and how it reasons
ModelImage inputVideo inputTool callingReasoning tiersServing precision
MiniMax M3YesNoYesadaptiveFP8
MiniMax M2.7NoNoYes—FP8

Published MiniMax discounts

These models publish a discount against their list price:

Each model's page shows its list price, its rates and its schedule.

Calling a MiniMax model

Create an account, make a key in the dashboard and send it as a bearer token. Between model families, only the model field changes.

curl https://api.openference.com/v1/chat/completions \
  -H "Authorization: Bearer $OPENFERENCE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "MiniMax M3",
       "messages": [{"role": "user", "content": "Say hello"}]}'

Send MiniMax M3 exactly as written. OpenAI-format clients use https://api.openference.com/v1; Claude Code and other Anthropic-format clients use https://api.openference.com. The OpenAI-compatible API guide covers every endpoint.

Other model families

See also the cheap AI API guide, the model catalog and pricing.

Questions

How much does the MiniMax API cost?

Across the 2 billed MiniMax models, input runs $0.03 to $0.30 and output $0.12 to $1.20 per million tokens at the most expensive hour of the day. MiniMax M3 is the least expensive per request.

What is the MiniMax API base URL?

https://api.openference.com/v1 for OpenAI-format clients and https://api.openference.com for Anthropic-format clients.

Do MiniMax models accept images?

Some do: MiniMax M3 accepts image input, and the other one is text-only.

Is there a free MiniMax model?

Not at the moment. The least expensive billed MiniMax model is MiniMax M3, at $0.00072 for the request described above.

Model catalog · Pricing · Comparisons · Cost guides · Integration guides · FAQ
Guides: GLM coding plan alternative · Free AI API · LLM gateway · LLM proxy · Cheap AI API · OpenAI-compatible API
Model APIs: GLM API · DeepSeek API · Kimi API · Qwen API · MiniMax API