LLMminimax

MiniMax: MiniMax M3

MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...

Anyone in the Space can @-mention MiniMax: MiniMax M3 with the team's shared context — pooled credits, one chat, one memory.

All models

Starter is free forever — 1 Space, 100 credits/month, 1 MCP. No card.

Verdict

MiniMax M3 offers a massive 524K token context window at aggressive pricing — $0.30 input makes it one of the cheapest options for long-context work. The multimodal support (text, image, video) is rare at this price point, though lack of public benchmarks means you're flying blind on quality versus Claude or GPT-4. Best for teams willing to test a cost-optimized alternative for document-heavy workflows where budget matters more than proven performance.

Best for

  • Budget-conscious long-context document analysis
  • Video content summarization and extraction
  • High-volume multimodal batch processing
  • Prototyping with large context requirements

Strengths

The 524K context window handles entire codebases or book-length documents in one pass. At $0.30 per million input tokens, it undercuts most competitors by 50-70% on ingestion costs. Native video understanding eliminates preprocessing steps for multimedia workflows. The pricing structure favors read-heavy use cases where you're analyzing far more than you're generating.

Trade-offs

No public benchmark data makes quality assessment speculative — you can't compare reasoning ability or instruction-following against established models. The $1.20 output pricing is 4x the input rate, so generation-heavy tasks lose the cost advantage quickly. Multimodal capabilities are unproven in production contexts. Documentation and community resources lag far behind OpenAI or Anthropic, increasing integration friction.

Specifications

Provider
minimax
Category
llm
Context length
524,288 tokens
Max output
512,000 tokens
Modalities
text, image, video
License
proprietary
Released
2026-05-31

Pricing

Input
$0.30/Mtok
Output
$1.20/Mtok
Model ID
minimax/minimax-m3

Per-token prices show what the model costs upstream. On Switchy your team draws from one shared org credit pool — one plan, one balance for everyone.

Team cost calculator

Estimated monthly spend
$10.03
17.6M tokens / month
5 seats · 80 msgs/day

Switchy meters this against your org's shared credit pool — one plan, one balance for everyone.

Providers

ProviderContextInputOutputP50 latencyThroughput30d uptime
minimax524k$0.30/Mtok$1.20/Mtok

Performance

Performance snapshots are collected daily. Check back after the next ingestion run.

Benchmarks

Public benchmark scores are not available yet for this model. Check back after the next ingestion run.

Works well with

Top MCPs

Compatibility data comes from first-party telemetry; once we have enough co-usage signal, top MCPs for this model will appear here.

How Switchy teams use it

Not enough Spaces have used this model yet to share anonymised team stats. We wait for at least 50 distinct Spaces per week before publishing any aggregate.

Starter prompts

Analyze Full Codebase

Review this complete codebase for architectural patterns, code quality issues, and potential security vulnerabilities. Provide a structured summary with specific file references and severity ratings.
Open in a Space →

Summarize Long Video

Watch this video and provide a detailed summary including: main topics covered, key timestamps for important moments, and actionable insights. Format as a bulleted outline.
Open in a Space →

Extract Contract Terms

Extract all financial terms, obligations, deadlines, and termination clauses from this contract. Present findings in a comparison table with page references.
Open in a Space →

Compare Multiple Documents

Compare these three policy documents and identify: areas of alignment, contradictions, and gaps in coverage. Organize findings by policy domain.
Open in a Space →

Analyze Image Series

Examine this sequence of images and describe: visual changes over time, recurring elements, and any anomalies or patterns. Provide frame-by-frame analysis where relevant.
Open in a Space →
Data last verified 2 hours ago.Sources aggregated hourly to weekly. See docs/architecture/model-directory.md.