Questions? hello@viberation.devGet supportBlogDocsChangelog
Get started

MiniMax

Open-weight multimodal models built for long agent runs.

MiniMax publishes open weights for its M-series models, which are aimed at long-horizon agentic work and coding. The current M3 takes text, images and video with a million-token context, and the older M2 models are still around and cheaper. A solid middle option: more capable than the tiny Flash models, far cheaper than a frontier API, and you can host it yourself if you need to.

At a glance — MiniMax M2.5

Cost
$0.27 in · $1.08 out per 1M tokensBudget
Memory
205K tokens — about 300 pages
Reads
Text
Can do
  • Use tools (agents)
  • Structured output
  • Thinking mode
Reliability
100.00% uptime, last 24h
Released
Feb 12, 2026
Advanced details
API model ID
minimax/minimax-m2.5
Max output
128K tokens
Cached input
$0.027 per 1M
Tokenizer
Other

Providers

The same model, hosted by different companies. OpenRouter picks one per request and falls back to the next if it fails.

ProviderInput /1MOutput /1MCached /1MMax outputUptime 24h
VeniceDegraded$0.27$0.95$0.0333K90.84%
StreamLake$0.27$1.08$0.027128K99.76%
AtlasCloud · fp8$0.295$1.20$0.06177K99.81%
DigitalOcean$0.30$1.20$0.0659K0.00%
Friendli$0.30$1.20$0.06177K100.00%
Novita · fp8$0.30$1.20$0.03131K99.86%
Minimax · fp8$0.30$1.20$0.03131K99.87%
Minimax · highspeed$0.60$2.40$0.06131K99.81%

Supported parameters

  • frequency_penalty
  • include_reasoning
  • logit_bias
  • logprobs
  • max_tokens
  • min_p
  • presence_penalty
  • reasoning
  • repetition_penalty
  • response_format
  • seed
  • stop
  • structured_outputs
  • temperature
  • tool_choice
  • tools
  • top_k
  • top_logprobs
  • top_p

Live from OpenRouter, refreshed hourly.

Key info

Pricing
Open source
Category
Models
Best for
Expert
Made by
MiniMax
Weights
Open
Good for
Agentic work over a long context

More in Models

  • France's frontier lab, with the small models everyone self-hosts.

    Models
  • Meta's current line, built for long multi-agent runs.

    Models
  • The open-weight family everyone else gets benchmarked against.

    Models
  • Google's open models — Gemini's research, small enough to self-host.

    Models