The current official MiniMax-M3 USD card is conditional: retained flat observations cover Standard requests up to 512k input tokens only. Cache, larger-prompt and Priority dimensions require complete publication; do not use the historical flat pair as a universal current quote.
Current price verification is unresolved or overdue. These are the last recorded rates; check the official source before budgeting. We do not relabel an old check with today's build date.
MiniMax M3 API Pricing
The current official MiniMax-M3 USD card is conditional: retained flat observations cover Standard requests up to 512k input tokens only. Cache, larger-prompt and Priority dimensions require complete publication; do not use the historical flat pair as a universal current quote. No directly comparable current token quote is available. These rates were last verified on .
The current official MiniMax-M3 USD card is conditional: retained flat observations cover Standard requests up to 512k input tokens only. Cache, larger-prompt and Priority dimensions require complete publication; do not use the historical flat pair as a universal current quote.
Published rates and billing units
| Billing dimension | USD list price |
|---|
Verified 2026-10-20 · Official source · Pricing methodology. Taxes, optional services and account-specific discounts are not included.
The current official MiniMax-M3 USD card is conditional: retained flat observations cover Standard requests up to 512k input tokens only. Cache, larger-prompt and Priority dimensions require complete publication; do not use the historical flat pair as a universal current quote.
Cost examples
These examples use published list prices only. They exclude taxes, enterprise discounts, minimum charges, retries, batch discounts, and provider-specific billing rules.
1M input + 1M output
—
A direct per-million comparison against every other text model.
100K input + 25K output
—
A compact chat, summarization, or analysis workload.
10M input + 2M output
—
A monthly production estimate for heavier RAG or agent traffic.
75% cached input + 250K output
Not listed
minimax does not publish a cached-input rate for this model in our dataset.
Calculator for MiniMax M3
Enter your own input, output, and cached-token assumptions. This calculator is preloaded with only MiniMax M3, so the result stays focused on this model.
The current official MiniMax-M3 USD card is conditional: retained flat observations cover Standard requests up to 512k input tokens only. Cache, larger-prompt and Priority dimensions require complete publication; do not use the historical flat pair as a universal current quote. Token-only calculation unavailable.
Price history
No list-price movement across 114 daily snapshots from 2026-07-21 to 2026-11-11.
When to use MiniMax M3
Good fit
- high-volume routing, classification, extraction, summaries, and fallback traffic
- long-document and repository-scale prompts where context window matters
Be careful with
- blind migration without testing your own prompts, latency, and failure modes