MiniMax M2.7 API Pricing

As of October 10, 2026, MiniMax M2.7 costs $0.25 per 1M input tokens and $1.00 per 1M output tokens from DeepInfra, the lowest of 7 providers, with cache reads at $0.05 per 1M tokens. It has a 196,608-token context window and returns up to 204,800 tokens per response.

By MiniMaxModel ID deepinfra/MiniMaxAI/MiniMax-M2.7Prices updated October 10, 2026Checked October 10, 2026

Input: $0.25 / 1M tokens
Output: $1.00 / 1M tokens
Cache read: $0.05 / 1M tokens
Context window: 196,608 tokens
Max output: 204,800 tokens
Providers: 7
Added to LiteLLM: May 2026

MiniMax M2.7 pricing by provider

7 listings across 7 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	Context
DeepInfra	`deepinfra/MiniMaxAI/MiniMax-M2.7`	$0.25	$1.00	$0.05	192K
AIHubMix	`aihubmix/minimax-m2.7`	$0.2958	$1.183	$0.05916	200K
Fireworks AI	`fireworks_ai/accounts/fireworks/models/minimax-m2p7`	–	–	–	192K
Novita AI	`novita/minimax/minimax-m2.7`	$0.30	$1.20	$0.06	200K
Pinstripes	`pinstripes/ps/minimax-m2.7`	$0.255	$0.55	–	1M
SambaNova	`sambanova/MiniMax-M2.7`	$0.60	$2.40	–	192K
Together AI	`together_ai/MiniMaxAI/MiniMax-M2.7`	$0.30	$1.20	$0.06	192K

What MiniMax M2.7 costs in practice

1,000 requests with 2,000 input and 500 output tokens each

DeepInfra	$1.00
Pinstripes	$0.785
AIHubMix	$1.183
Novita AI	$1.20

100 long-document requests with 100,000 input and 2,000 output tokens each

DeepInfra	$2.70
Pinstripes	$2.66
AIHubMix	$3.195
Novita AI	$3.24

MiniMax M2.7 features

Function calling
Structured output
Image input
Reasoning
Prompt caching

Use MiniMax M2.7 with LiteLLM

Call MiniMax M2.7 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.

Python SDK

from litellm import completion

response = completion(
    model="deepinfra/MiniMaxAI/MiniMax-M2.7",
    messages=[{"role": "user", "content": "Hello!"}],
)

Proxy config.yaml

model_list:
  - model_name: minimax-m2.7
    litellm_params:
      model: deepinfra/MiniMaxAI/MiniMax-M2.7
      api_key: os.environ/DEEPINFRA_API_KEY

Call the proxy

curl http://0.0.0.0:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-1234" \
  -d '{
    "model": "minimax-m2.7",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

MiniMax M2.7 FAQ

How much does MiniMax M2.7 cost?

MiniMax M2.7 costs $0.25 per 1M input tokens and $1.00 per 1M output tokens from DeepInfra, the lowest of 7 providers, with cache reads at $0.05 per 1M tokens.

What is the context window of MiniMax M2.7?

MiniMax M2.7 has a 196,608-token context window and returns up to 204,800 tokens per response.

Which providers offer MiniMax M2.7?

MiniMax M2.7 is available from 7 providers through LiteLLM: DeepInfra, AIHubMix, Fireworks AI, Novita AI, Pinstripes, SambaNova and Together AI. The lowest price is on DeepInfra.

How do I call MiniMax M2.7 with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="deepinfra/MiniMaxAI/MiniMax-M2.7", 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 M2.7 support?

MiniMax M2.7 supports function calling, structured output, reasoning and prompt caching. It does not support image input.

When did LiteLLM add MiniMax M2.7?

MiniMax M2.7 was added to LiteLLM's model price file in May 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:

LiteLLM docs: DeepInfra, AIHubMix, Fireworks AI, Pinstripes, SambaNova, Together AI.

Provider pages: DeepInfra, AIHubMix, Fireworks AI, Novita AI, Pinstripes, SambaNova, Together AI.