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-M2.5 pricing and specs
MiniMax-M2.5 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
- Input / 1M
- $0.30
- Output / 1M
- $1.20
- Context
- 205K tokens
- Weights
- Open
Pricing per 1M tokens
| Item | Price / 1M tokens |
|---|---|
| Input | $0.30 |
| Output | $1.20 |
| Cache read | $0.03 |
| Cache write (5 minutes) | $0.375 |
Note: Listed under Legacy Models on the pricing page but still in the Available Models list. Being retired: unavailable to new users from 2026-10-19 and retired on 2026-11-18 per MiniMax's models page; re-check or remove after 2026-11-18. release date is from the launch post (dated 2026.2.12); the release notes say only 'Feb. 2026' and the weights LICENSE-MODEL says version release date 2026-02-13. Text and tool-call input only. max output is the documented max_tokens ceiling for non-M3 models and includes thinking tokens. The repo's LICENSE-MODEL is titled MiniMax Model License while the Hugging Face card tags it modified-mit.
Specs
- Context window
- 204,800 tokens
- Max output
- 204,800 tokens
- Release date
- Provider
- MiniMax
- API model id
MiniMax-M2.5- Vercel AI Gateway id
minimax/minimax-m2.5- Weights
- Open weights
- License
- MiniMax Model License (Hugging Face license tag: other / modified-mit)
- Weights download
- huggingface.co
What MiniMax-M2.5 costs in practice
Worked from the standard list rates above, with the math shown so you can swap in your own token counts.
A chat app
10,000 requests a day at 2K input and 500 output tokens each.
- Input20M x $0.30 = $6.00
- Output5M x $1.20 = $6.00
$12.00per day
$360.00 per 30-day month
The same session at a 90% cache hit
90% of the input is read from the prompt cache. The one-time cache write premium is not included.
- Cached input0.9M x $0.03 = $0.027
- Uncached input0.1M x $0.30 = $0.03
- Output0.1M x $1.20 = $0.12
$0.177per session
Compare with
| Model | Input / 1M | Output / 1M |
|---|---|---|
| MiniMax-M2.5 (this page) | $0.30 | $1.20 |
| DeepSeek V4.1 FlashDeepSeek | $0.30 | $1.20 |
| GPT-5.6 LunaOpenAI | $0.20 | $1.20 |
| MiniMax-M2.7MiniMax | $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 |
Related reading
- MiniMax M2.5 for Developers: The Anthropic-Compatible Budget Frontier ModelMiniMax M2.5 hits 80.2% on SWE-bench Verified and plugs into the Anthropic SDK with two environment variables. Here is what you need to know before switching.
- MiniMax H3: An Omni-Modal Video Model With Native Audio, 2K Output, and Open Weights ComingMiniMax H3 turns text, image, video and audio input into 2K video with native stereo sound at 0.80 CNY per second, with open weights promised to follow.
FAQ
How much does MiniMax-M2.5 cost per million tokens?
MiniMax-M2.5 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 $0.03.
What is MiniMax-M2.5's context window?
MiniMax-M2.5 has a 204,800-token context window and returns up to 204,800 output tokens per response.
Are MiniMax-M2.5's weights open?
Yes. MiniMax-M2.5's weights are published at https://huggingface.co/MiniMaxAI/MiniMax-M2.5 under the MiniMax Model License (Hugging Face license tag: other / modified-mit).
When was MiniMax-M2.5 released?
MiniMax released MiniMax-M2.5 on February 12, 2026.
Sources
Last verified from platform.minimax.io.
- https://platform.minimax.io/docs/guides/pricing
- https://platform.minimax.io/docs/pricing/overview
- https://platform.minimax.io/docs/guides/text-generation
- https://platform.minimax.io/docs/faq/models
- https://platform.minimax.io/docs/api-reference/text-anthropic-api
- https://platform.minimax.io/docs/api-reference/text-chat-anthropic
- https://platform.minimax.io/docs/release-notes/models
- https://www.minimax.io/news/minimax-m25
- https://huggingface.co/MiniMaxAI/MiniMax-M2.5
- https://huggingface.co/MiniMaxAI/MiniMax-M2.5/raw/main/LICENSE-MODEL
Newsletter
Get model price changes as they ship
One email per week. New model releases, price cuts and what they mean for your bill.