MiniMax M2
MiniMax-M2Pricing
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
6 hosts serve MiniMax M2. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
MiniMaxLab API MiniMax-M2 | $0.30 / $1.20 | MiniMax-M2 | |
Vertex AICloud minimax-m2-maas | $0.30 / $1.20 | minimax-m2-maas | |
Amazon BedrockCloud minimax.minimax-m2 | $0.30 / $1.20 Retires 30 Mar 2027 | minimax.minimax-m2 | Retires 30 Mar 2027 |
GMI CloudInference MiniMax-M2 | $0.30 / $1.20 | MiniMax-M2 | |
Fireworks AIInference minimax-m2 | $0.30 / $1.20 | minimax-m2 | |
Novita AIInference minimax-m2 | $0.30 / $1.20 | minimax-m2 |
Show 17 more listings: regions, snapshots and variantsHide regional listings
| Amazon Bedrock | |||||||
| Mantle minimax.minimax-m2 | $0.30 / $1.20 Retires 30 Mar 2027 | minimax.minimax-m2 | Retires 30 Mar 2027 | ||||
| ap-southeast-2 · Mantle minimax.minimax-m2 | $0.309 / $1.24 +3% vs headline Retires 30 Mar 2027 | minimax.minimax-m2 | Retires 30 Mar 2027 | ||||
| ap-south-1 minimax.minimax-m2 | $0.35 / $1.41 +17% vs headline Retires 30 Mar 2027 | minimax.minimax-m2 | Retires 30 Mar 2027 | ||||
| eu-south-1 minimax.minimax-m2 | $0.35 / $1.41 +17% vs headline Retires 30 Mar 2027 | minimax.minimax-m2 | Retires 30 Mar 2027 | ||||
| eu-west-1 minimax.minimax-m2 | $0.35 / $1.41 +17% vs headline Retires 30 Mar 2027 | minimax.minimax-m2 | Retires 30 Mar 2027 | ||||
| ap-south-1 · Mantle minimax.minimax-m2 | $0.35 / $1.41 +17% vs headline Retires 30 Mar 2027 | minimax.minimax-m2 | Retires 30 Mar 2027 | ||||
| eu-south-1 · Mantle minimax.minimax-m2 | $0.35 / $1.41 +17% vs headline Retires 30 Mar 2027 | minimax.minimax-m2 | Retires 30 Mar 2027 | ||||
| eu-west-1 · Mantle minimax.minimax-m2 | $0.35 / $1.41 +17% vs headline Retires 30 Mar 2027 | minimax.minimax-m2 | Retires 30 Mar 2027 | ||||
| ap-southeast-3 · Mantle minimax.minimax-m2 | $0.36 / $1.44 +20% vs headline Retires 30 Mar 2027 | minimax.minimax-m2 | Retires 30 Mar 2027 | ||||
| eu-central-1 · Mantle minimax.minimax-m2 | $0.36 / $1.44 +20% vs headline Retires 30 Mar 2027 | minimax.minimax-m2 | Retires 30 Mar 2027 | ||||
| eu-north-1 · Mantle minimax.minimax-m2 | $0.36 / $1.44 +20% vs headline Retires 30 Mar 2027 | minimax.minimax-m2 | Retires 30 Mar 2027 | ||||
| ap-northeast-1 minimax.minimax-m2 | $0.36 / $1.45 +20% vs headline Retires 30 Mar 2027 | minimax.minimax-m2 | Retires 30 Mar 2027 | ||||
| sa-east-1 minimax.minimax-m2 | $0.36 / $1.45 +20% vs headline Retires 30 Mar 2027 | minimax.minimax-m2 | Retires 30 Mar 2027 | ||||
| ap-northeast-1 · Mantle minimax.minimax-m2 | $0.36 / $1.45 +20% vs headline Retires 30 Mar 2027 | minimax.minimax-m2 | Retires 30 Mar 2027 | ||||
| sa-east-1 · Mantle minimax.minimax-m2 | $0.36 / $1.45 +20% vs headline Retires 30 Mar 2027 | minimax.minimax-m2 | Retires 30 Mar 2027 | ||||
| eu-west-2 minimax.minimax-m2 | $0.47 / $1.86 +56% vs headline Retires 30 Mar 2027 | minimax.minimax-m2 | Retires 30 Mar 2027 | ||||
| eu-west-2 · Mantle minimax.minimax-m2 | $0.47 / $1.86 +56% vs headline Retires 30 Mar 2027 | minimax.minimax-m2 | Retires 30 Mar 2027 | ||||
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-2.0Runtimes: 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 M2.5$0.30 / $1.20
- UndatedMiniMax M2.1$0.30 / $1.20
- UndatedMiniMax M2This page$0.30 / $1.20
Call it
Using MiniMax's API.
from litellm import completion
response = completion(
model="minimax/MiniMax-M2",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does MiniMax M2 cost?
On MiniMax, MiniMax M2 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?
MiniMax M2 runs on 6 APIs: MiniMax, Vertex AI, Amazon Bedrock, GMI Cloud, Fireworks AI and Novita AI.
What is MiniMax M2's context window?
200K tokens, with up to 8K tokens in one reply.
Is MiniMax M2 being retired?
Amazon Bedrock retires it on 30 Mar 2027. 5 hosts keep serving it.
Is there a newer version of MiniMax M2?
Yes. MiniMax M3 is the newest model in this line, released on 31 May 2026.
What are cheaper alternatives to MiniMax M2?
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.
What is MiniMax M2's API model id?
Use MiniMax-M2 with MiniMax. Other hosts use their own ids: minimax-m2-maas on Vertex AI, minimax.minimax-m2 on Amazon Bedrock, minimax-m2 on Fireworks AI, minimax-m2 on Novita AI.
Sources
Raw catalog entry for MiniMax-M2 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": 200000,
"max_output_tokens": 8192
}