impulse

MiniMax M2.7 Turbo

Open weights
API id MiniMax-M2.7-Turbo
Input / 1M
$0.38
at DeepInfra
Output / 1M
$1.70
at DeepInfra
Context window
197K
tokens
Max output
197K
tokens per reply
Hosts
1
1 listings
Released
-
date not published

Pricing

List prices at DeepInfra, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.38$1.70
Cached input
82% off input
$0.07

What it costs a month

At DeepInfra list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$214
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$169
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$298
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$1,320
Use your own numbers

Where to run it

1 host serve MiniMax M2.7 Turbo. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
DeepInfraInference
MiniMax-M2.7-Turbo
$0.38 / $1.70

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-2.0
Runtimes: 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 DeepInfra.

Smaller MiniMax models

No cheaper MiniMax model keeps its key capabilities.

Other frontier labs

  • GPT-5.4 Nano
    OpenAI · on OpenAI
    $0.20 / $1.25
    Has every key capability
    35% less
  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    72% less
  • GPT-6 Luna
    OpenAI · on OpenAI
    $0.10 / $0.50
    Has every key capability
    72% less
  • GPT-4o Mini
    OpenAI · on OpenAI
    $0.15 / $0.60
    Lacks reasoning
    63% less

Open-weight picks

  • Kimi K2.7 Code
    Moonshot AI · on CLF AI Gateway
    $0.38 / $1.60
    Has every key capability
    4% less
  • Inkling Small
    Independent · on DeepInfra
    $0.45 / $1.20
    Has every key capability
    10% less
  • DeepSeek Flash
    DeepSeek · on DeepSeek
    $0.30 / $1.20
    Has every key capability
    26% less
  • Qwen3.7 Plus
    Alibaba Qwen · on Replicate
    $0.276 / $1.10
    Has every key capability
    32% less

Call it

Using DeepInfra's API.

Python
from litellm import completion

response = completion(
    model="deepinfra/MiniMax-M2.7-Turbo",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does MiniMax M2.7 Turbo cost?

On DeepInfra, MiniMax M2.7 Turbo costs $0.38 per million input tokens and $1.70 per million output tokens. Cached input costs $0.07 per million tokens.

Which APIs offer MiniMax M2.7 Turbo?

MiniMax M2.7 Turbo runs on 1 API: DeepInfra.

What is MiniMax M2.7 Turbo's context window?

197K tokens, with up to 197K tokens in one reply.

Is MiniMax M2.7 Turbo being retired?

No retirement date is scheduled for it on any API we track.

What are cheaper alternatives to MiniMax M2.7 Turbo?

Models that cost less and keep most of what it can do: GPT-5.4 Nano on OpenAI (35% less), Claude Haiku 5.5 on Anthropic (72% less) and Kimi K2.7 Code on CLF AI Gateway (4% less). Savings are on a mix of 3 input tokens to 1 output token.

What is MiniMax M2.7 Turbo's API model id?

Use MiniMax-M2.7-Turbo with DeepInfra.

Sources

Raw catalog entry for MiniMax-M2.7-Turbo on DeepInfra
{
  "max_output_tokens": 196608,
  "max_input_tokens": 196608,
  "input_cost_per_token": 3.8e-7,
  "output_cost_per_token": 0.0000017,
  "cache_read_input_token_cost": 7e-8,
  "supports_prompt_caching": true,
  "litellm_provider": "deepinfra",
  "mode": "chat",
  "supports_function_calling": true,
  "supports_tool_choice": true,
  "supports_response_schema": true,
  "supports_reasoning": true,
  "supports_vision": false,
  "source": "https://deepinfra.com/pricing"
}