MiniMax M2.7 Highspeed
minimax-m2.7-highspeedPricing
List prices at Novita AI, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.60 | $2.40 | |
| Cached input 90% off input | $0.06 | 90% off input |
What it costs a month
At Novita AI list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$311
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$245
- Coding agent1,000 requests a day, 40K in / 2K out, cached$410
- Overnight batch20,000 requests a day, 4K in / 0.4K out$2,016
Where to run it
2 hosts serve MiniMax M2.7 Highspeed. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
EmpirioLabs AICloud minimax-m2-7-highspeed | $0.30 / $1.20 −50% vs headline | minimax-m2-7-highspeed | |
Novita AIInference minimax-m2.7-highspeed | $0.60 / $2.40 | minimax-m2.7-highspeed |
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
- EmpirioLabs AI50% lessminimax-m2-7-highspeed$0.30 / $1.20
Smaller MiniMax models
No cheaper MiniMax model keeps its key capabilities.
Other frontier labs
- 19% less
- 56% less
- 81% less
- 81% less
Open-weight picks
- 18% less
- 25% less
- 35% less
- 39% less
Model line
Newer and older versions, at each lab's own price.
- UndatedMiniMax M2.7 HighspeedLatest$0.60 / $2.40
- UndatedMiniMax M2.5 Highspeed$0.60 / $2.40
Call it
Using Novita AI's API.
from litellm import completion
response = completion(
model="novita/minimax-m2.7-highspeed",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does MiniMax M2.7 Highspeed cost?
On Novita AI, MiniMax M2.7 Highspeed costs $0.60 per million input tokens and $2.40 per million output tokens. Cached input costs $0.06 per million tokens. The cheapest host is EmpirioLabs AI, at $0.30 per million input tokens and $1.20 per million output tokens.
Which APIs offer MiniMax M2.7 Highspeed?
MiniMax M2.7 Highspeed runs on 2 APIs: EmpirioLabs AI and Novita AI.
What is MiniMax M2.7 Highspeed's context window?
205K tokens, with up to 131K tokens in one reply.
Is MiniMax M2.7 Highspeed being retired?
No retirement date is scheduled for it on any API we track.
Is there a newer version of MiniMax M2.7 Highspeed?
No. MiniMax M2.7 Highspeed is the newest model in its line.
What are cheaper alternatives to MiniMax M2.7 Highspeed?
Models that cost less and keep most of what it can do: Gemini 3.5 Flash Lite on Google AI Studio (19% less), GPT-5.4 Nano on OpenAI (56% less) and GLM 5.3 on CLF AI Gateway (18% less). MiniMax M2.7 Highspeed itself costs 50% less on EmpirioLabs AI. Savings are on a mix of 3 input tokens to 1 output token.
What is MiniMax M2.7 Highspeed's API model id?
Use minimax-m2.7-highspeed with Novita AI. Other hosts use their own ids: minimax-m2-7-highspeed on EmpirioLabs AI.
Sources
Raw catalog entry for minimax-m2.7-highspeed on Novita AI
{
"cache_read_input_token_cost": 6e-8,
"input_cost_per_token": 6e-7,
"litellm_provider": "novita",
"max_input_tokens": 204800,
"max_output_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 0.0000024,
"source": "https://api.novita.ai/v3/openai/models",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": false
}