MiniMax · October 2026
MiniMax API pricing, every model
9 MiniMax models, from $0.15 to $0.55 per million input tokens. MiniMax text models with very long context.
Prices from OpenRouter’s models API, updated October 29, 2026
MiniMax M3.1 Flash
$0.15 in · $0.60 outAbout $13.95 a month for a 1,000-chats-a-day support bot.
MiniMax M3.1 Flash
$0.15 in · $0.60 outReleased 2026-10-19, 1.05M tokens of context.
MiniMax M3.1 Flash
−90%Cached input costs $0.015 instead of $0.15 per 1M tokens.
All MiniMax models and prices
| Model | Released | Input /1M | Output /1M | Cache read /1M | Context | Chatbot, per month* |
|---|---|---|---|---|---|---|
| MiniMax M3.1 Flash | 2026-10-19 | $0.15 | $0.60 | $0.015 | 1.05M | $13.95 |
| MiniMax M3 | 2026-05-31 | $0.30 | $1.20 | $0.06 | 1.05M | $27.90 |
| MiniMax M2.7 | 2026-03-18 | $0.30 | $1.20 | $0.06 | 205K | $27.90 |
| MiniMax M2.5 | 2026-02-12 | $0.30 | $1.20 | $0.03 | 205K | $27.90 |
| MiniMax M2-her | 2026-01-23 | $0.30 | $1.20 | $0.03 | 66K | $27.90 |
| MiniMax M2.1 | 2025-12-23 | $0.30 | $1.20 | $0.03 | 205K | $27.90 |
| MiniMax M2 | 2025-10-23 | $0.255 | $1.02 | – | 205K | $23.71 |
| MiniMax M1 | 2025-06-17 | $0.55 | $2.20 | – | 1M | $51.15 |
| MiniMax-01 | 2025-01-15 | $0.20 | $1.10 | – | 1M | $22.20 |
* Support chatbot: 1,000 chats a day, 1,500 tokens in, 400 out, 30 days, no caching. Prices in US dollars per 1M tokens.
What three real workloads cost a month
| Model | Support chatbot | Daily summaries | Coding agent |
|---|---|---|---|
| MiniMax M3.1 Flash | $13.95 | $189 | $44.64 |
| MiniMax-01 | $22.20 | $279 | $170 |
| MiniMax M2 | $23.71 | $321 | $208 |
| MiniMax M3 | $27.90 | $378 | $107 |
| MiniMax M2.7 | $27.90 | $378 | $107 |
| MiniMax M2.5 | $27.90 | $378 | $89.28 |
| MiniMax M2-her | $27.90 | $378 | $89.28 |
| MiniMax M2.1 | $27.90 | $378 | $89.28 |
Support chatbot: 1,000 chats a day, 1,500 tokens in, 400 out · Daily summaries: 10,000 a day, 3,000 tokens in, 300 out · Coding agent: 400 calls a day, 60,000 tokens in (80% cached), 2,000 out. Cached share billed at the cache-read price where the model has one.
Compare with other providers
MiniMax pricing questions
How much does the MiniMax API cost?
MiniMax’s models range from $0.15 per 1M input tokens and $0.60 per 1M output tokens (MiniMax M3.1 Flash) to $0.55 and $2.20 (MiniMax M1). The newest, MiniMax M3.1 Flash, costs $0.15 in and $0.60 out.
Which MiniMax model is the cheapest?
MiniMax M3.1 Flash, at $0.15 per 1M input tokens. A support chatbot doing 1,000 chats a day would cost about $13.95 a month on it.
Does MiniMax discount cached prompts?
Yes. On MiniMax M3.1 Flash, cached input costs $0.015 per 1M tokens instead of $0.15, 90% less. Long, repeated system prompts and agent loops benefit most.
How do I track my MiniMax spend per product?
Route it through OpenRouter with one API key per product and connect OpenRouter to Glow: you get spend by model, API key and product every day, with cache hit rate. Track AI spend.
See your real MiniMax bill.
Glow shows what you actually spend by model, API key and product, every day, and which cheaper model would do the same job.
- Read-only keys
- Never shown again
- 2FA + Face ID
- 7-day trial