MiniMax M2.5
$0.27 per 1M input tokens and $0.95 per 1M output tokens · 205K context · tools, reasoning, JSON, open weights.
Prices checked Oct 21, 2026 · tracked by LLM Cost Index since Oct 21, 2026
What MiniMax M2.5 costs per month
Estimated monthly bill for typical workloads, using the cached-input price for repeated context. Try your own numbers in the cost calculator.
| Workload | Per month |
|---|---|
| Customer chatbot 1,000 conversations a day, 8 turns each | $125 |
| Document Q&A (RAG) 500 questions a day over retrieved documents | $29.27 |
| Coding / tool-using agent 200 tasks a day, long tool-heavy contexts | $55.20 |
| Content generation 30 long articles a day | $2.87 |
| Classification / extraction 100,000 short items a day | $286 |
Price history
We started tracking MiniMax M2.5 on Oct 21, 2026; the chart appears as soon as there is a second data point. See all recent price changes.
Where to run MiniMax M2.5: 9 providers
StreamLake is the cheapest at $0.27 input / $1.08 output per 1M tokens. Uptime is the average over the last 30 days as reported by OpenRouter; see provider reliability.
| Provider | Input / 1M | Output / 1M | Context | Uptime | Notes |
|---|---|---|---|---|---|
| StreamLake | $0.27 | $1.08 | 200K | 99.9% | — |
| Venice | $0.27 | $0.95 | 198K | 91.8% | — |
| AtlasCloud | $0.295 | $1.20 | 197K | 100% | fp8 |
| DigitalOcean | $0.30 | $1.20 | 66K | 99.4% | — |
| Friendli | $0.30 | $1.20 | 197K | 100% | — |
| GMICloud | $0.30 | $1.20 | 197K | 100% | fp8 |
| Minimax | $0.30 | $1.20 | 205K | 100% | fp8 |
| Novita | $0.30 | $1.20 | 205K | 97.7% | fp8 |
| Minimax | $0.60 | $2.40 | 205K | 100% | priority tier, fp8 |
Cheaper alternatives to MiniMax M2.5
Models with the same tool calling, structured output for at least 20% less (3:1 input/output mix), most capable first.
| Model | Input / 1M | Output / 1M | Context | Capabilities |
|---|---|---|---|---|
| Claude Haiku 5.5 Anthropic | $0.10 | $0.50 | 1M | visiontoolsreasoningJSON |
| GLM 5.3 Flash Z.ai | $0.041 | $0.12 | 1.05M | visiontoolsreasoningJSONopen weights |
| Ling 3.1 Flash inclusionAI | $0.075 | $0.225 | 262K | toolsreasoningJSON |
| GPT-6 Luna OpenAI | $0.10 | $0.50 | 1.05M | visiontoolsreasoningJSON |
| MiMo-V2.6-Flash Xiaomi | $0.14 | $0.28 | 1.05M | visionaudiotoolsreasoningJSONopen weights |
How to pay less for MiniMax M2.5
For a customer chatbot (1,000 conversations a day, 8 turns each) that costs $177 a month at list price without caching:
| Option | Per month | You save |
|---|---|---|
| Move to Claude Haiku 5.5 (similar capabilities) | $58.56 | $118 (67%) |
| Use prompt caching (60% of input cached) | $125 | $51.84 (29%) |
Other workloads: cut-your-bill tool for MiniMax M2.5.
Specifications
| Model ID | minimax/minimax-m2.5 |
| Input | text |
| Output | text |
| Tool calling | Yes |
| Structured output | Yes |
| Reasoning mode | Yes |
| Open weights | Yes — MiniMaxAI/MiniMax-M2.5 |
| Released | Feb 12, 2026 |
FAQ
- How much does MiniMax M2.5 cost?
- $0.27 per million input tokens and $0.95 per million output tokens; cached input costs $0.03 per million. Prices as of Oct 21, 2026.
- What is the context window of MiniMax M2.5?
- 205K tokens, with up to 33K output tokens per response.
- Does MiniMax M2.5 support images, tools and structured output?
- Images as input: no. Tool calling: yes. Structured (JSON) output: yes. Reasoning mode: yes.
- What are cheaper alternatives to MiniMax M2.5?
- Models with the same key capabilities for at least 20% less include Claude Haiku 5.5 ($0.10 / $0.50), GLM 5.3 Flash ($0.041 / $0.12), Ling 3.1 Flash ($0.075 / $0.225).
More from MiniMax: all MiniMax models · how we collect prices