MiniMax M3

Provider: MiniMax CN Official API price

Input price
$0.30
/ 1M tokens
Output price
$1.20
/ 1M tokens
Cache price
$0.06
/ 1M tokens (read)
Batch API
$0.22 / $0.88
input / output per 1M tokens
Context
524K tokens
Max output 512K tokens

Overview

MiniMax M3 is a multimodal flagship model built for long-horizon agentic workflows and large context tasks.

Strengths

  • 524288 token context window
  • 512000 token maximum output
  • Supports vision, function-calling, json-mode, and thinking
  • Cached input priced at $0.06/1M tokens

Best use cases

  • Long-horizon agentic software development
  • Analyzing extensive multimedia documents
  • Complex multi-step reasoning pipelines

Pricing position

Input matches Codestral 2508 and Qwen3.5 Plus at $0.3/1M, while output is $1.2/1M.

Caveats

No free tier is available; M3.1 Flash offers a larger context for one-fourth the price.

Notes drafted by an LLM from the figures on this page (2026-11-12) and rewritten when the price changes.

Key facts

Price basis
Official API price
Max output
512K tokens
Listed on OpenRouter
2026-05-31
Tracked since
2026-06-01
Last updated
2026-11-10

Features

Image inputFunction callingJSON outputReasoning

Price history

  • 2026-06-01 Added

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $0.09
1M (small app) 1 0.5 $0.90
10M (mid scale) 10 5 $9.00
100M (large) 100 50 $90.00

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from MiniMax

Similar-priced models

Source: OpenRouter API (minimax/minimax-m3)