GPT 5%, Claude 10% — limited-time rates through Aug 17, 2026, 00:00 (UTC+8). All GPT and Claude text models are billed at 5% and 10% of their official list prices.View pricing
Minimax

MiniMax M2.7

Save 90%Official

minimax/minimax-m2.7

Call minimax/minimax-m2.7 through the RouteMux AI Gateway. One URL connects you to every model.

Context window
205K
Max output
131K
Input modalities
text
Output modalities
text
Capabilities
Reasoning · Tool Calling · Coding · Cache
RouteMux name
minimax/minimax-m2.7
Official ID
MiniMax-M2.7
Live model playground

Try MiniMax M2.7 here

Tune the request, see the current price ceiling, and inspect the real response without leaving this model page.

streamchat
1Configure input
0 / 20,000
Maximum estimated cost
2Live result

Your result will appear here

Enter an input on the left. The same RouteMux Playground execution and billing path powers this embedded test.

conversation

What is MiniMax M2.7

MiniMax M2.7 is a text-only model with a 204K-token context window and 131K of output headroom. It supports reasoning, coding, tool calling and prompt caching, and answers on OpenAI Chat Completions, OpenAI Responses and Anthropic Messages.

Through RouteMux it is $0.03 per 1M input tokens against MiniMax's $0.30, and $0.12 against $1.20 on output.

Two things to note before choosing it over M3: the context is 204K rather than 1M, and it does not take image input. If either matters, M3 is the same price per token with both.

MiniMax M2.7 API pricing

Source: minimax_text_x0.10 · Verified 2026-08-07

InputOfficial $0.3 / M tokens
$0.03/ M tokensSave 90%
OutputOfficial $1.2 / M tokens
$0.12/ M tokensSave 90%

Cache read $0.006/M · Cache write /M

Estimate cost

Estimated cost$0.00042

Limited time20% off your first top-up — save up to $200

Applies to your first top-up within 72 hours of signing up. Minimum $20, once per account.

Sign up and claimNo subscription. Pay for what you use.

Key capabilities

Text-only

No image input — if you need vision at this price point, M3 has it at the same token rate.

204K context, 131K output

Output headroom is unusually large relative to the context window.

Tool calling and caching

Reasoning, coding, tool calling and prompt caching are supported.

Three protocols

OpenAI Chat, OpenAI Responses and Anthropic Messages.

Interface and protocols

OpenAI Chat CompletionsStreamingOpenAI ResponsesStreamingAnthropic MessagesStreaming

Use either ID to call this model via the API.

RouteMux nameminimax/minimax-m2.7
Official IDMiniMax-M2.7

Replace the ROUTEMUX_KEY placeholder with your API key. Create one →

from openai import OpenAI

client = OpenAI(
    base_url="https://api.routemux.com/v1",
    api_key="<ROUTEMUX_KEY>",
)

completion = client.chat.completions.create(
    model="minimax/minimax-m2.7",
    messages=[{"role": "user", "content": "What is the meaning of life?"}],
)
print(completion.choices[0].message.content)
base_url: https://api.routemux.com/v1

Performance (last 30 days)

MiniMax M2.7 FAQ

How large is the context window of MiniMax M2.7?

MiniMax M2.7 supports a context window of up to 205K tokens, with up to 131K output tokens per request.

How much does the MiniMax M2.7 API cost?

Through RouteMux, MiniMax M2.7 costs $0.03 for input and $0.12 for output (USD per 1M tokens), below the official list price.

How do I call MiniMax M2.7 via API?

MiniMax M2.7 is OpenAI-compatible: point your base URL at RouteMux and set the model field to minimax/minimax-m2.7 — no code changes needed.

Which input and output modalities does MiniMax M2.7 support?

MiniMax M2.7 accepts text as input and produces text as output.

M2.7 or M3?

M3 has a 1M context and image input at the same token price. Choose M2.7 only if a workflow is already calibrated to it.

Does it accept images?

No — M2.7 is text-only. M3 accepts text and image input.

Sources

Reviewed by Jerry Fan on 2026-08-09

View as Markdown