MiniMax-M2.5 pricing, context window and limits
MiniMax-M2.5 costs $0.3 per million input tokens and $1.2 per million output tokens at Amazon Bedrock list price. It accepts up to 196,608 tokens of context and returns up to 98,304 tokens.
- Model id
bedrock/minimax.minimax-m2.5 - Snapshot
What does MiniMax-M2.5 cost?
| Input | $0.3 |
|---|---|
| Output | $1.2 |
| Cached input (read) | — |
| Cache write | — |
US dollars per million tokens. A dash means no price is published.
How much can MiniMax-M2.5 read and write?
| Context window | 196,608 |
|---|---|
| Max output | 98,304 |
What can MiniMax-M2.5 do?
| Vision (image input) | No |
|---|---|
| Tool calling | Yes |
| Structured output | Yes |
| Reasoning | Yes |
| Input | text |
| Output | text |
What does a request to MiniMax-M2.5 cost?
| A typical request: 1,000 tokens in, 500 out | $0.0009 |
|---|---|
| A long request: 10,000 tokens in, 1,000 out | $0.0042 |
| 1,000 typical requests | $0.9 |
| 1 million tokens in and 1 million out | $1.5 |
Among 191 Amazon Bedrock models with a published price, MiniMax-M2.5 is the 51st cheapest by input price. Its context window is the 150th largest of 191. List prices only; discounts, batch prices and prices above 200K tokens are not shown.
How do I call MiniMax-M2.5 through DVARA?
Configure the bedrock provider in the DVARA LLM Gateway and send the model id bedrock/minimax.minimax-m2.5. DVARA, the AI governance platform, applies your policies, audit and cost attribution to the call. See LLM cost attribution and budgets.
In DVARA, if you haven't set your own price for a model, its calls are costed at the price in the catalogue that ships with your DVARA version. A price you set in Flightdeck always wins. You can switch catalogue prices off. Then a model with no price you set is counted as costing nothing. Every cost record says which price it used.
Which other Amazon Bedrock models are there?
- MiniMax-M2.1$0.3 in · $1.2 out · 197K context
- MiniMax-M2$0.3 in · $1.2 out · 205K context
- Devstral 2 123B$0.4 in · $2 out · 262K context
- Magistral Small 1.2$0.5 in · $1.5 out · 128K context
- Llama 4 Scout 17B Instruct$0.17 in · $0.66 out · 10M context
- Ministral 14B 3.0$0.2 in · $0.2 out · 128K context
- Llama 4 Maverick 17B Instruct$0.24 in · $0.97 out · 1M context
- Ministral 3 3B$0.1 in · $0.1 out · 256K context
- Llama 3.3 70B Instruct$0.72 in · $0.72 out · 128K context
- Ministral 3 8B$0.15 in · $0.15 out · 128K context
- Llama 3.1 8B Instruct$0.22 in · $0.22 out · 128K context
- Mistral Large 3$0.5 in · $1.5 out · 262K context
Which models from other providers are similar to MiniMax-M2.5?
These are the closest in context window and input price, one per provider.
- Codestral (latest)Mistral AI · $0.3 in · $0.9 out · 256K context
- GLM-4.6VZhipu GLM · $0.3 in · $0.9 out · 128K context
- Qwen2.5 32B InstructAlibaba Qwen · $0.287 in · $0.861 out · 131K context
- GPT-5 MiniOpenAI · $0.25 in · $2 out · 400K context
- Nano Banana 2Google Gemini · $0.5 in · $60 out · 131K context