Forge is available: build a website with AI from your RodiumAi account.

Try Forge
MiniMax

MiniMax M2.7 Highspeed

Healthychattools
Context
205K
Max output
-
Speed
Fast
Quality
Basic
Released
2026-03-18
Input: / Output:
TextText

About this model

Faster throughput for agentic coding and tool-driven automation. MiniMax M2.7-Highspeed is the performance-tuned variant of M2.7, built for lower latency and higher throughput while keeping output behavior consistent with the standard model.

Pricing

RateRODIUSD (ref.)Unit
Text tokens
In454.6~ 0.600per 1M tokens (RODI/M, USD/M)
Out1818.1~ 2.40per 1M tokens (RODI/M, USD/M)

RODI prices include RodiumAi markup and upstream fees. USD figures are wholesale reference rates.

Providers & pricing

ProviderInputOutputCachedFree tierStatus
Runware

Runware

Default

All rates (2)
  • In454.6 RODI/M
  • Out1818.1 RODI/M
454.61,818--No data

Capabilities

Streaming
Tool calling
Vision
JSON mode
Reasoning

API usage

Use the canonical slug with client.chat() or chat.completions.create().

Examples

…

Example response

…

Streaming

…

RodiumAi SDK

Official Python, JavaScript, and Laravel SDKs: flat API aligned with this model slug.

…

Use cases

  • Customer support assistants that answer in the customer's language.
  • Drafting and rewriting: emails, product sheets, WhatsApp replies, summaries.
  • Structured extraction: turn invoices, forms or chat logs into JSON.
  • Code help: explain, review, generate and refactor snippets.
  • Back-office automation: classify tickets, tag documents, route requests.

Notes

  • Endpoint: POST https://api.rodiumai.io/v1/chat/completions, the OpenAI Chat Completions format. Any OpenAI SDK works by changing base_url and the key.
  • The model id is always minimax/minimax-m2.7-highspeed (provider slug, then model slug).
  • max_tokens and max_completion_tokens are both accepted.
  • Some OpenAI-only fields (n, frequency_penalty, presence_penalty, logit_bias, seed, user) are ignored by models served from a non-OpenAI upstream. Calls still succeed.
  • The response usage block reports the tokens billed. The RODI cost of each call is shown in Dashboard > Usage.
  • Streaming, tool calling and JSON mode depend on the capabilities listed in the Capabilities section of this page.
View all