MiniMax · Pricing

MiniMax M3 pricing

Complete MiniMax M3 API cost reference: $0.30/M input, $1.20/M output, 1.0M token context window, $0.06/M cached reads. Verified against official sources.

Prices verified August 20, 2026
MiniMax M3
Input / M
$0.30
Output / M
$1.20
Cache read
$0.06
Context
1.0M
Batch
Vision
Yes
Reasoning

What MiniMax M3 costs in practice

WorkloadCost / callCost @ 1K req/day
Light · 1K in / 300 out$0.0007$20.09/mo
Standard · 10K in / 2K out$0.0054$164.36/mo
Heavy · 100K in / 20K out$0.0540$1643.63/mo

Estimates assume medium reasoning effort, no batch discounts and no prompt caching. Turn on prompt caching and the input side typically drops 50–90% — run your own mix in the free calculator preloaded with MiniMax M3.

About this page

Prices were last verified on August 20, 2026 against MiniMax's official pricing page. Providers reprice frequently — see our methodology for exactly how estimates are computed, and always confirm final rates with the provider before budgeting.

MiniMax M3 FAQ

How much does MiniMax M3 cost?

MiniMax M3 charges $0.30 per million input tokens and $1.20 per million output tokens, with cached input reads at $0.06/M.

What is the context window of MiniMax M3?

MiniMax M3 supports a context window of 1,048,576 tokens (1.0M) — roughly 786,432 English words or about 1,573 pages of text in a single request.

Does MiniMax M3 support images, audio or reasoning?

MiniMax M3 offers vision & image understanding. Current flagship. Up to 512K input tokens; cached reads at $0.06/M.

How do I estimate my MiniMax M3 bill?

A typical workload of 10K input and 2K output tokens costs about $0.0054 per call with MiniMax M3. At 1,000 requests per day that is roughly $164.36 per month. Use the free AITokenCalculator to run your exact numbers.