MiniMax: MiniMax M2.5 API pricing
$0.295 per 1M input tokens and $1.20 per 1M output tokens on OpenRouter. Context window: 198,000 tokens.
$0.295input / 1M tokens
$1.20output / 1M tokens
$0.06cached input / 1M
193Kcontext
text->textmodality
What it costs in practice
| Workload | Cost |
|---|---|
| Chatbot: 10,000 messages (1,500 in / 400 out tokens each) | $9.22 |
| RAG: 1,000 queries (8,000 in / 600 out each) | $3.08 |
| Summarize 100 long documents (50,000 in / 1,000 out each) | $1.59 |
Cross-check against the provider's list price
LiteLLM's price map lists minimax/MiniMax-M2.5 (minimax) at $0.30 in / $1.20 out per 1M tokens. Matches OpenRouter
Price history
No price change recorded since we started tracking on Nov 17, 2026. We check every 6 hours and log every change.
Run it yourself instead
The open weights are on Hugging Face. See the VRAM MiniMax M2.5 needs and which GPUs fit it →
Cheaper alternatives with similar context
Text models with at least 125K context and a lower blended price (75% input, 25% output). Price only, not a quality ranking.
| Model | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| Meta: Llama 4 Maverick | $0.35 | $1.00 | 512K |
| Thinking Machines: Inkling Small (batch) | $0.36 | $0.96 | 512K |
| DeepSeek: DeepSeek V3 0324 | $0.29 | $1.14 | 160K |
| Z.ai: GLM 5.2 (batch) | $0.322 | $0.989 | 1M |
| Thinking Machines: Inkling 2 Small | $0.30 | $1.00 | 1M |
| Reflection: Beam 1.0 501B A23B | $0.30 | $1.00 | 1M |
| Qwen: Qwen3 Coder 480B A35B | $0.30 | $1.00 | 256K |
| OpenAI: GPT-5.4 Nano | $0.20 | $1.25 | 391K |
Source: OpenRouter listing via the public models API · LiteLLM price map (MIT). Prices checked Nov 17, 2026. Model ID minimax/minimax-m2.5, listed Feb 12, 2026. Report an error.