MiniMax · LLMs & Coding
MiniMax-M3
Catalog data · checked Nov 16, 2026
MiniMax-M3 is a language model from MiniMax, released in June 2026. It reads text, images and video and writes text, with a context window of 1M tokens and up to 524.3K output tokens per answer. It costs $0.3 per million input tokens and $1.2 per million output tokens. That makes it cheaper than 70% of the 185 paid language models we track.
What it can do
- Tool calling
- Structured output
- Reasoning mode
- Image input
- File input
- Audio input
- Video input
- Image output
- Audio output
- Prompt caching
More prices
| Cached input (read) | $0.06 /1M |
| Above 200K input tokens | $0.6 in · $2.4 out |
What it costs in practice
| 1,000 support replies1,000 chats with 800 input and 250 output tokens each | $0.54 |
| Summarize a 300-page reportabout 150,000 input tokens in one request, 2,000 tokens out | $0.047 |
| 10,000 product descriptions300 input and 200 output tokens per text | $3.3 |
| One day of agentic codingabout 3M input and 150K output tokens across many calls | $1.08 |
Calculated from the list prices above. Your bill depends on your real token counts. Use your own numbers →
Compare MiniMax-M3 with
Questions & answers
How much does MiniMax-M3 cost?
MiniMax-M3 costs $0.3 per 1 million input tokens and $1.2 per 1 million output tokens (USD, list price checked Nov 16, 2026).
How large is the context window of MiniMax-M3?
MiniMax-M3 can process up to 1,000,000 tokens per request and return up to 524,288 tokens. As a rule of thumb, 1,000 tokens are about 750 English words.
Does MiniMax-M3 support tool calling?
Yes. The API accepts tool (function) definitions.
Can MiniMax-M3 read images?
Yes, image input is supported.
