← All models
Flash — fastest and cheapest, lighter reasoningOpen Weights
MiniMax M3 (batch) Pricing
MiniMax · minimax-minimax-m3-batch
Input / 1M tokens
$0.300
Output / 1M tokens
$1.20
Context window
524,288 tokens
≈ 699 pages of text
Max output
471,859 tokens
What it costs in practice
Typical request (1,200 in + 400 out tokens)$0.0008
1,000 requests / month$0.84/mo10,000 requests / month$8.40/mo100,000 requests / month$84.00/moEstimate your own workloadOpens the calculator with MiniMax M3 (batch) preloaded — adjust volume and token counts there.
Price history
List price per 1M tokens since we started tracking in Jul 2026. Each step marks a price change — hover a point for the exact date and rate.
What it excels at
Handles large-batch inference over extended contexts at low cost, supported by open weights and a 524k token window.
The business tradeoff
Open-weights hosting creates variable latency and infrastructure overhead; limited ecosystem and unproven reasoning depth relative to established providers.
Cheaper from MiniMax
Head-to-head
Vendor list rates, as of Aug 18, 2026 · source: openrouter · per-request examples assume 1,200 input + 400 output tokens.