MiniMax M2.1 API Pricing
As of October 10, 2026, MiniMax M2.1 costs $0.30 per 1M input tokens and $1.20 per 1M output tokens on MiniMax, with cache reads at $0.03 and cache writes at $0.375 per 1M tokens. It has a 1,000,000-token context window and returns up to 8,192 tokens per response.
- Input
- $0.30 / 1M tokens
- Output
- $1.20 / 1M tokens
- Cache read
- $0.03 / 1M tokens
- Context window
- 1,000,000 tokens
- Max output
- 8,192 tokens
- Providers
- 5
- Added to LiteLLM
- December 2025
MiniMax M2.1 pricing by provider
18 listings across 5 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.
| Provider | Model name in LiteLLM | Input | Output | Cache read | Cache write | Context |
|---|---|---|---|---|---|---|
| MiniMax | minimax/MiniMax-M2.1 | $0.30 | $1.20 | $0.03 | $0.375 | 1M |
| Amazon Bedrock | minimax.minimax-m2.1 | $0.30 | $1.20 | – | – | 196K |
| Fireworks AI | fireworks_ai/accounts/fireworks/models/minimax-m2p1 | $0.30 | $1.20 | $0.03 | – | 200K |
| Fireworks AI | fireworks_ai/minimax-m2p1 | $0.30 | $1.20 | $0.03 | – | 200K |
| GMI Cloud | gmi/MiniMaxAI/MiniMax-M2.1 | $0.30 | $1.20 | – | – | 192K |
| Novita AI | novita/minimax/minimax-m2.1 | $0.30 | $1.20 | $0.03 | – | 200K |
| Amazon Bedrockap-northeast-1 | bedrock/ap-northeast-1/minimax.minimax-m2.1 | $0.36 | $1.44 | – | – | 196K |
| Amazon Bedrockap-south-1 | bedrock/ap-south-1/minimax.minimax-m2.1 | $0.36 | $1.44 | – | – | 196K |
| Amazon Bedrockap-southeast-3 | bedrock/ap-southeast-3/minimax.minimax-m2.1 | $0.36 | $1.44 | – | – | 196K |
| Amazon Bedrockeu-central-1 | bedrock/eu-central-1/minimax.minimax-m2.1 | $0.36 | $1.44 | – | – | 196K |
| Amazon Bedrockeu-north-1 | bedrock/eu-north-1/minimax.minimax-m2.1 | $0.36 | $1.44 | – | – | 196K |
| Amazon Bedrockeu-south-1 | bedrock/eu-south-1/minimax.minimax-m2.1 | $0.36 | $1.44 | – | – | 196K |
| Amazon Bedrockeu-west-1 | bedrock/eu-west-1/minimax.minimax-m2.1 | $0.36 | $1.44 | – | – | 196K |
| Amazon Bedrockeu-west-2 | bedrock/eu-west-2/minimax.minimax-m2.1 | $0.47 | $1.86 | – | – | 196K |
| Amazon Bedrocksa-east-1 | bedrock/sa-east-1/minimax.minimax-m2.1 | $0.36 | $1.44 | – | – | 196K |
| Amazon Bedrockus-east-1 | bedrock/us-east-1/minimax.minimax-m2.1 | $0.30 | $1.20 | – | – | 196K |
| Amazon Bedrockus-east-2 | bedrock/us-east-2/minimax.minimax-m2.1 | $0.30 | $1.20 | – | – | 196K |
| Amazon Bedrockus-west-2 | bedrock/us-west-2/minimax.minimax-m2.1 | $0.30 | $1.20 | – | – | 196K |
What MiniMax M2.1 costs in practice
1,000 requests with 2,000 input and 500 output tokens each
| MiniMax | $1.20 |
| Amazon Bedrock | $1.20 |
| Fireworks AI | $1.20 |
| GMI Cloud | $1.20 |
100 long-document requests with 100,000 input and 2,000 output tokens each
| MiniMax | $3.24 |
| Amazon Bedrock | $3.24 |
| Fireworks AI | $3.24 |
| GMI Cloud | $3.24 |
MiniMax M2.1 features
- Function calling
- Parallel tool calls
- Structured output
- Reasoning
- Prompt caching
Use MiniMax M2.1 with LiteLLM
Call MiniMax M2.1 through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.
from litellm import completion
response = completion(
model="minimax/MiniMax-M2.1",
messages=[{"role": "user", "content": "Hello!"}],
)model_list:
- model_name: minimax-m2.1
litellm_params:
model: minimax/MiniMax-M2.1
# credentials: see the provider's LiteLLM docs pagecurl http://0.0.0.0:4000/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk-1234" \
-d '{
"model": "minimax-m2.1",
"messages": [{"role": "user", "content": "Hello!"}]
}'MiniMax M2.1 FAQ
How much does MiniMax M2.1 cost?
MiniMax M2.1 costs $0.30 per 1M input tokens and $1.20 per 1M output tokens on MiniMax, with cache reads at $0.03 and cache writes at $0.375 per 1M tokens.
What is the context window of MiniMax M2.1?
MiniMax M2.1 has a 1,000,000-token context window and returns up to 8,192 tokens per response.
Which providers offer MiniMax M2.1?
MiniMax M2.1 is available from 5 providers through LiteLLM: MiniMax, Amazon Bedrock, Fireworks AI, GMI Cloud and Novita AI.
How do I call MiniMax M2.1 with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="minimax/MiniMax-M2.1", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.
What features does MiniMax M2.1 support?
MiniMax M2.1 supports function calling, parallel tool calls, structured output, reasoning and prompt caching.
When did LiteLLM add MiniMax M2.1?
MiniMax M2.1 was added to LiteLLM's model price file in December 2025.
Sources
Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Provider pricing pages:
- docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html
- fireworks.ai/models/fireworks/minimax-m2p1
LiteLLM docs: MiniMax, Amazon Bedrock, Fireworks AI, GMI Cloud.
Provider pages: MiniMax, Amazon Bedrock, Fireworks AI, GMI Cloud, Novita AI.