MiniMax M2.5 API pricing
As of October 22, 2026, MiniMax M2.5 costs $0.30 per million input tokens and $1.20 per million output tokens on MiniMax's own API, with cached input at $0.03 per million.
MiniMax M2.5 benchmarks and specs · Every MiniMax model's price
- Input, per million tokens$0.30
- Output, per million tokens$1.20
- Cached input, per million$0.03
- Context window205K tokens
- Max output33K tokens
- Output speedNot measured
What a request costs
Three fixed token mixes at the list price, without cache or batch discounts. For a whole month, use the calculator.
| Workload | Tokens | One request | 1,000 requests | Fits the context window |
|---|---|---|---|---|
| Chat turn | 1K input + 500 output tokens | $0.0009 | $0.900 | Yes |
| Repository review | 50K input + 3K output tokens | $0.019 | $18.60 | Yes |
| Agent loop | 200K input + 10K output tokens | $0.072 | $72.00 | No, it would need splitting |
| Solved coding task | One SWE-bench Verified attempt, divided by the share that succeed | $0.62 | $620.00 |
Price history
We have read MiniMax's own price every day since October 21, 2026. It has not changed yet; any change will be listed here with its date.
- October 21, 2026 First recorded: $0.30 input, $1.20 output
Cheaper models as good as MiniMax M2.5
Models within two points of MiniMax M2.5 or above it on the LLMBenchmark Index, with a lower output price. Cheapest first.
- gpt-oss-20b$0.15 Overall 38.5 against 37.3 · 88% cheaper output
- Qwen3.5-Flash$0.26 Overall 50.1 against 37.3 · 78% cheaper output
- MiMo-V2.6-Flash$0.28 Overall 60.8 against 37.3 · 77% cheaper output
- Qwen3 30B A3B Instruct 2507$0.30 Overall 41.5 against 37.3 · 75% cheaper output
- MiMo-V2.5$0.336 Overall 50.7 against 37.3 · 72% cheaper output
MiniMax M2.5 pricing questions
- How much does MiniMax M2.5 cost per million tokens?
- $0.30 per million input tokens and $1.20 per million output tokens, as listed on OpenRouter on October 22, 2026.
- Does MiniMax M2.5 support prompt caching?
- Yes. OpenRouter lists cached input at $0.03 per million tokens, against $0.30 for uncached input.
- Is there a cheaper model as good as MiniMax M2.5?
- gpt-oss-20b scores 38.5 on the LLMBenchmark Index, within two points of MiniMax M2.5 or above it, and costs $0.15 per million output tokens.
- Has the price of MiniMax M2.5 changed?
- Not since we started recording it daily on October 21, 2026.