MiniMax M2.5
MiniMax-M2.5 is a SOTA large language model designed for real-world productivity.
MiniMax-M2.5Released 12 Feb 2026 (Feb 2026)Pricing
List prices at MiniMax, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.30 | $1.20 | |
| Cached input 90% off input | $0.03 | 90% off input | |
| Cache write, 5 minutes | $0.375 |
What it costs a month
At MiniMax list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$156
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$122
- Coding agent1,000 requests a day, 40K in / 2K out, cached$205
- Overnight batch20,000 requests a day, 4K in / 0.4K out$1,008
Where to run it
9 hosts serve MiniMax M2.5. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
MiniMaxLab API MiniMax-M2.5 | $0.30 / $1.20 | MiniMax-M2.5 | |
TensormeshCloud MiniMax-M2.5 | $0.30 / $1.20 | MiniMax-M2.5 | |
StreamLakeCloud minimax-m2.5 | $0.30 / $1.20 | minimax-m2.5 | |
Amazon BedrockCloud minimax.minimax-m2.5 | $0.30 / $1.20 | minimax.minimax-m2.5 | |
BasetenInference MiniMax-M2.5 | $0.30 / $1.20 | MiniMax-M2.5 | |
GMI CloudInference MiniMax-M2.5 | $0.30 / $1.20 | MiniMax-M2.5 | |
Nebius AI StudioInference MiniMax-M2.5 | $0.30 / $1.20 | MiniMax-M2.5 | |
Novita AIInference minimax-m2.5 | $0.30 / $1.20 | minimax-m2.5 | |
Kyma APICloud minimax-m2.5 | $0.419 / $1.68 +40% vs headline | minimax-m2.5 |
Show 14 more listings: regions, snapshots and variantsHide regional listings
| Amazon Bedrock | |||||||
| us-east-1 minimax.minimax-m2.5 | $0.30 / $1.20 | minimax.minimax-m2.5 | |||||
| us-east-2 minimax.minimax-m2.5 | $0.30 / $1.20 | minimax.minimax-m2.5 | |||||
| us-west-2 minimax.minimax-m2.5 | $0.30 / $1.20 | minimax.minimax-m2.5 | |||||
| Mantle minimax.minimax-m2.5 | $0.30 / $1.20 | minimax.minimax-m2.5 | |||||
| ap-southeast-2 minimax.minimax-m2.5 | $0.31 / $1.24 +3% vs headline | minimax.minimax-m2.5 | |||||
| ap-northeast-1 minimax.minimax-m2.5 | $0.36 / $1.44 +20% vs headline | minimax.minimax-m2.5 | |||||
| ap-south-1 minimax.minimax-m2.5 | $0.36 / $1.44 +20% vs headline | minimax.minimax-m2.5 | |||||
| ap-southeast-3 minimax.minimax-m2.5 | $0.36 / $1.44 +20% vs headline | minimax.minimax-m2.5 | |||||
| eu-north-1 minimax.minimax-m2.5 | $0.36 / $1.44 +20% vs headline | minimax.minimax-m2.5 | |||||
| eu-central-1 minimax.minimax-m2.5 | $0.36 / $1.44 +20% vs headline | minimax.minimax-m2.5 | |||||
| eu-west-1 minimax.minimax-m2.5 | $0.36 / $1.44 +20% vs headline | minimax.minimax-m2.5 | |||||
| eu-south-1 minimax.minimax-m2.5 | $0.36 / $1.44 +20% vs headline | minimax.minimax-m2.5 | |||||
| sa-east-1 minimax.minimax-m2.5 | $0.36 / $1.44 +20% vs headline | minimax.minimax-m2.5 | |||||
| eu-west-2 minimax.minimax-m2.5 | $0.47 / $1.86 +56% vs headline | minimax.minimax-m2.5 | |||||
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- Text
- Produces
- Text
- Features
- Prompt caching
- Open weights
- License: Apache-2.0Runs in about 548.9 GB of GPU memoryRuntimes: SGLang, vLLM
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
No host sells it for less than MiniMax.
Smaller MiniMax models
No cheaper MiniMax model keeps its key capabilities.
Other frontier labs
- 12% less
- 62% less
- 62% less
- 50% less
Open-weight picks
- 8% less
- 10% less
- 17% less
- 25% less
Model line
Newer and older versions, at each lab's own price.
- May 2026MiniMax M3Latest$0.30 / $1.20
- Mar 2026MiniMax M2.7$0.21 / $0.84
- Feb 2026MiniMax M2.5This page$0.30 / $1.20
- UndatedMiniMax M2.1$0.30 / $1.20
- UndatedMiniMax M2$0.30 / $1.20
Call it
Using MiniMax's API.
from litellm import completion
response = completion(
model="minimax/MiniMax-M2.5",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does MiniMax M2.5 cost?
On MiniMax, MiniMax M2.5 costs $0.30 per million input tokens and $1.20 per million output tokens. Cached input costs $0.03 per million tokens.
Which APIs offer MiniMax M2.5?
MiniMax M2.5 runs on 9 APIs: MiniMax, Tensormesh, StreamLake, Amazon Bedrock, Baseten, GMI Cloud, Nebius AI Studio, Novita AI and Kyma API.
What is MiniMax M2.5's context window?
1M tokens, with up to 8K tokens in one reply.
Is MiniMax M2.5 being retired?
No retirement date is scheduled for it on any API we track.
Is there a newer version of MiniMax M2.5?
Yes. MiniMax M3 is the newest model in this line, released on 31 May 2026.
What are cheaper alternatives to MiniMax M2.5?
Models that cost less and keep most of what it can do: GPT-5.4 Nano on OpenAI (12% less), Claude Haiku 5.5 on Anthropic (62% less) and Qwen3.7 Plus on Replicate (8% less). Savings are on a mix of 3 input tokens to 1 output token.
When was MiniMax M2.5 released?
MiniMax released it on 12 Feb 2026.
What is MiniMax M2.5's API model id?
Use MiniMax-M2.5 with MiniMax. Other hosts use their own ids: minimax-m2.5 on StreamLake, minimax.minimax-m2.5 on Amazon Bedrock, minimax-m2.5 on Novita AI, minimax-m2.5 on Kyma API.
Sources
- GMI Cloud pricing
- Nebius AI Studio pricing
- Tensormesh pricing
- Novita AI pricing
- StreamLake pricing
- Amazon Bedrock pricing
- LiteLLM model map
Raw catalog entry for MiniMax-M2.5 on MiniMax
{
"input_cost_per_token": 3e-7,
"output_cost_per_token": 0.0000012,
"cache_read_input_token_cost": 3e-8,
"cache_creation_input_token_cost": 3.75e-7,
"litellm_provider": "minimax",
"mode": "chat",
"supports_function_calling": true,
"supports_tool_choice": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_system_messages": true,
"max_input_tokens": 1000000,
"max_output_tokens": 8192
}