One agent session
1M input tokens and 100K output tokens, no caching.
- Input1M x $0.30 = $0.30
- Output0.1M x $1.20 = $0.12
$0.42per session
MiniMax - Open weights
MiniMax-M2.7 is an open-weights model from MiniMax that costs $0.30 per 1M input tokens and $1.20 per 1M output tokens on the first-party API, with a 205K-token context window.
Last verified from platform.minimax.io. All sources
| Item | Price / 1M tokens |
|---|---|
| Input | $0.30 |
| Output | $1.20 |
| Cache read | $0.06 |
| Cache write (5 minutes) | $0.375 |
Note: Being retired: MiniMax's models page says the M2.5 and M2.7 families stop being available to new users on 2026-10-19 and are retired on 2026-11-18 (M Plan and Token Plan requests get routed to M3.1 Flash Preview from 2026-10-19). Re-check or remove this entry after 2026-11-18. Text and tool-call input only (no image or video). Thinking cannot be turned off. max output is the documented max_tokens ceiling for non-M3 models (204800, recommended 65536) and thinking tokens count toward it. The weights license is non-commercial: commercial use needs prior written authorization from MiniMax. Pricing page shows a single Standard tier for this model.
MiniMax-M2.7minimax/minimax-m2.7Worked from the standard list rates above, with the math shown so you can swap in your own token counts.
1M input tokens and 100K output tokens, no caching.
$0.42per session
10,000 requests a day at 2K input and 500 output tokens each.
$12.00per day
$360.00 per 30-day month
90% of the input is read from the prompt cache. The one-time cache write premium is not included.
$0.204per session
| Model | Input / 1M | Output / 1M |
|---|---|---|
| MiniMax-M2.7 (this page) | $0.30 | $1.20 |
| DeepSeek V4.1 FlashDeepSeek | $0.30 | $1.20 |
| GPT-5.6 LunaOpenAI | $0.20 | $1.20 |
| MiniMax-M2.5MiniMax | $0.30 | $1.20 |
| MiniMax-M3MiniMax | $0.30 | $1.20 |
| MiniMax-M2.5-highspeedMiniMax | $0.60 | $2.40 |
| MiniMax-M2.7-highspeedMiniMax | $0.60 | $2.40 |
Side-by-side pages with both models' prices, specs, cost examples and like-for-like benchmark rows.
MiniMax-M2.7 costs $0.30 per 1M input tokens and $1.20 per 1M output tokens on MiniMax's first-party API, per platform.minimax.io on October 17, 2026. Per 1M tokens, cache reads cost $0.06.
MiniMax-M2.7 has a 204,800-token context window and returns up to 204,800 output tokens per response.
Yes. MiniMax-M2.7's weights are published at https://huggingface.co/MiniMaxAI/MiniMax-M2.7 under the MiniMax M2.7 Non-Commercial License (Hugging Face license tag: other).
MiniMax released MiniMax-M2.7 on March 18, 2026.
Last verified from platform.minimax.io.
Newsletter
One email per week. New model releases, price cuts and what they mean for your bill.