MiniMax-M2.5 pricing & specs
MiniMax · released 2026-02-12 · ● verified 2026-10-11
input / 1M$0.30
output / 1M$1.20
context204.8K
max output131.1K
// price history ($/1M tokens)
// cheaper or similar alternatives
| model | in | out | ctx | vs MiniMax-M2.5 |
|---|---|---|---|---|
| Gemma 4 E2B IT | $0.04 | $0.08 | 131.1K | −90.5% |
| Qwen3.7 Flash | $0.03 | $0.13 | 1M | −89.5% |
| Qwen Turbo | $0.05 | $0.20 | 1M | −83.3% |
| DeepSeek V4 Flash 0731 | $0.06 | $0.18 | 1.05M | −82.9% |
| GPT OSS 120B | $0.05 | $0.25 | 131.1K | −81% |
// price by host
| host | in $/1M | out $/1M |
|---|---|---|
| Amazon Bedrock | $0.30 | $1.20 |
| Novita AI | $0.30 | $1.20 |
// faq
How much does MiniMax-M2.5 cost?
MiniMax-M2.5 costs $0.30 per million input tokens and $1.20 per million output tokens. At 50M input and 10M output tokens per month that is about $27.00.
What is the context window of MiniMax-M2.5?
204.8K tokens, with up to 131.1K output tokens per request.
Does MiniMax-M2.5 support prompt caching?
Yes. Cached input tokens cost $0.03 per million and cache writes cost $0.375 per million.
What are cheaper alternatives to MiniMax-M2.5?
Gemma 4 E2B IT ($0.04 in / $0.08 out), Qwen3.7 Flash ($0.03 in / $0.13 out), Qwen Turbo ($0.05 in / $0.20 out) offer the same input types and capabilities for less.
Is MiniMax-M2.5 open weights?
Yes. It is available from 2 tracked hosts; the cheapest is Amazon Bedrock at $0.30 input and $1.20 output per million tokens.
// spec sheet
- input / 1M
- $0.30
- output / 1M
- $1.20
- cache read / 1M
- $0.03
- cache write / 1M
- $0.375
- blended (3:1)
- $0.525
- context
- 204.8K
- max output
- 131.1K
- input types
- text
- reasoning
- yes
- tool calling
- yes
- structured output
- no
- open weights
- yes
- knowledge cutoff
- n/a
- price source
- MiniMax
// cost calculator
| model | in $/1M | out $/1M | = monthly |
|---|---|---|---|
| Gemma 4 E2B IT | $0.04 | $0.08 | $2.80 |
| Qwen3.7 Flash | $0.03 | $0.13 | $2.80 |
| Qwen Turbo | $0.05 | $0.20 | $4.50 |
| MiniMax-M2.5 | $0.30 | $1.20 | $27.00 |
Base-tier list prices. Long-context tiers, caching and batch discounts are not included.