MiniMax M3 API Pricing
As of October 10, 2026, MiniMax M3 costs $0.30 per 1M input tokens and $1.20 per 1M output tokens on MiniMax, with cache reads at $0.06 per 1M tokens. Across 9 providers on LiteLLM, the input price ranges from $0.23 to $0.30. It has a 1,000,000-token context window and returns up to 128,000 tokens per response.
- Input
- $0.30 / 1M tokens
- Output
- $1.20 / 1M tokens
- Cache read
- $0.06 / 1M tokens
- Context window
- 1,000,000 tokens
- Max output
- 128,000 tokens
- Providers
- 9
- Added to LiteLLM
- June 2026
MiniMax M3 pricing by provider
10 listings across 9 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-M3 | $0.30 | $1.20 | $0.06 | – | 1M |
| AIHubMix | aihubmix/minimax-m3 | $0.288 | $1.152 | – | – | 1M |
| DeepInfra | deepinfra/MiniMaxAI/MiniMax-M3 | $0.28 | $1.10 | $0.056 | – | 512K |
| Fireworks AI | fireworks_ai/accounts/fireworks/models/minimax-m3 | $0.30 | $1.20 | $0.06 | – | 512K |
| Fireworks AI | fireworks_ai/minimax-m3 | $0.30 | $1.20 | $0.06 | – | 512K |
| Nebius AI Studio | nebius/MiniMaxAI/MiniMax-M3 | $0.30 | $1.20 | – | – | 1M |
| Novita AI | novita/minimax/minimax-m3 | $0.30 | $1.20 | $0.06 | – | 1M |
| Tencent TokenHub | tencent/minimax-m3 | $0.30 | $1.20 | $0.06 | $0 | 1M |
| Together AI | together_ai/MiniMaxAI/MiniMax-M3 | $0.30 | $1.20 | $0.06 | – | 512K |
| Weights & Biases | wandb/MiniMaxAI/MiniMax-M3 | $0.23 | $0.96 | $0.05 | – | 262K |
Other MiniMax M3 prices on MiniMax
| Input above 512K tokens | $0.60 per 1M tokens |
| Output above 512K tokens | $2.40 per 1M tokens |
| Cache read above 512K tokens | $0.12 per 1M tokens |
What MiniMax M3 costs in practice
1,000 requests with 2,000 input and 500 output tokens each
| MiniMax | $1.20 |
| Weights & Biases | $0.94 |
| DeepInfra | $1.11 |
| AIHubMix | $1.152 |
100 long-document requests with 100,000 input and 2,000 output tokens each
| MiniMax | $3.24 |
| Weights & Biases | $2.492 |
| DeepInfra | $3.02 |
| AIHubMix | $3.11 |
MiniMax M3 features
- Function calling
- Parallel tool calls
- Structured output
- Image input
- Reasoning
- Prompt caching
Use MiniMax M3 with LiteLLM
Call MiniMax M3 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-M3",
messages=[{"role": "user", "content": "Hello!"}],
)model_list:
- model_name: minimax-m3
litellm_params:
model: minimax/MiniMax-M3
# 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-m3",
"messages": [{"role": "user", "content": "Hello!"}]
}'MiniMax M3 FAQ
How much does MiniMax M3 cost?
MiniMax M3 costs $0.30 per 1M input tokens and $1.20 per 1M output tokens on MiniMax, with cache reads at $0.06 per 1M tokens. Above 512K input tokens, input costs $0.60 and output costs $2.40 per 1M tokens. Across 9 providers on LiteLLM, the input price ranges from $0.23 to $0.30.
What is the context window of MiniMax M3?
MiniMax M3 has a 1,000,000-token context window and returns up to 128,000 tokens per response.
Which providers offer MiniMax M3?
MiniMax M3 is available from 9 providers through LiteLLM: MiniMax, AIHubMix, DeepInfra, Fireworks AI, Nebius AI Studio, Novita AI, Tencent TokenHub, Together AI and Weights & Biases. The lowest price is on Weights & Biases.
How do I call MiniMax M3 with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="minimax/MiniMax-M3", 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 M3 support?
MiniMax M3 supports function calling, parallel tool calls, structured output, image input, reasoning and prompt caching.
When did LiteLLM add MiniMax M3?
MiniMax M3 was added to LiteLLM's model price file in June 2026.
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:
- aihubmix.com/api/v1/models
- deepinfra.com/pricing
- api.fireworks.ai/v1/serverless/models
- tokenfactory.nebius.com/models/catalog/text2text/MiniMaxAI%2FMiniMax-M3
LiteLLM docs: MiniMax, AIHubMix, DeepInfra, Fireworks AI, Nebius AI Studio, Tencent TokenHub.
Provider pages: MiniMax, AIHubMix, DeepInfra, Fireworks AI, Nebius AI Studio, Novita AI, Tencent TokenHub, Together AI, Weights & Biases.
