LLM Reference

MiniMax M2.5 Highspeed on Novita AI

MiniMax M2 · MiniMax

ServerlessOpen Source

Last refreshed 2026-06-15. Next refresh: weekly.

Why use MiniMax M2.5 Highspeed on Novita AI?

Novita AI offers MiniMax M2.5 Highspeed with pay-as-you-go pricing at $0.60/1M input tokens. Novita AI offers a GPU-based inference API for image, video, and language model generation with a broad catalog of open-source models.

Compare MiniMax M2.5 Highspeed across 3 providers to find the best fit for your use case
Input / 1M
$0.60
Output / 1M
$2.40
Cache
Not sourced
Batch
Not sourced

Setup recipe

Docs fallback
Install
Use the provider REST API or SDK
Auth
Create a provider API key
Call
model: minimax-m2.5-highspeed
Model ID
minimax-m2.5-highspeed

Request example

Curated snippets for this provider have not been sourced yet.

Gotchas

No curated gotchas have been sourced for this exact provider/model route yet.

Compare MiniMax M2.5 Highspeed Across Providers

ProviderInput (per 1M)Output (per 1M)
MiniMax
Vercel AI Gateway$0.60$2.40
Novita AI$0.60$2.40

Pricing

TypePrice (per 1M)
Input tokens$0.60
Output tokens$2.40

Capabilities

ReasoningFunction CallingTool UseStructured Outputs

About MiniMax M2.5 Highspeed

MiniMax M2.5 Highspeed is MiniMax's inference-optimized variant of M2.5, released simultaneously in February 2026. It delivers identical intelligence and outputs to standard M2.5 through a specialized inference engine at lower latency. The model supports a 204,800-token context window, 131,072-token max output, function calling, structured output, and reasoning. API model ID: MiniMax-M2.5-highspeed. It is designed for latency-sensitive interactive applications and automated agent pipelines.

FAQ

What does MiniMax M2.5 Highspeed cost on Novita AI?

On Novita AI, MiniMax M2.5 Highspeed costs $0.6 per 1M input tokens and $2.4 per 1M output tokens.

What is the context window for MiniMax M2.5 Highspeed on Novita AI?

MiniMax M2.5 Highspeed supports a 205k token context window on Novita AI.

How does Novita AI compare to other MiniMax M2.5 Highspeed providers?

MiniMax M2.5 Highspeed is available from 3 providers. The cheapest input pricing is $0.6/1M tokens from Vercel AI Gateway.

What API model ID do I use for MiniMax M2.5 Highspeed on Novita AI?

Use the model ID minimax-m2.5-highspeed when calling Novita AI's API.

Who created MiniMax M2.5 Highspeed?

MiniMax M2.5 Highspeed was created by MiniMax as part of the MiniMax M2 model family.

Is MiniMax M2.5 Highspeed open source?

MiniMax M2.5 Highspeed is open source under MIT according to the seed data.

Get Started

Model Specs

Released2026-02-12
Parameters230B (10B active)
Context205k
ArchitectureDecoder Only