MiniMax API pricing, checked at the source
Prices for MiniMax-M3 and MiniMax-M3.1-Flash, read off MiniMax's own pricing page with a link on every row. Estimate a monthly bill below.
MiniMax API prices per 1M tokens
Standard prices in USD. Each row links to MiniMax's pricing page and shows the day we checked it.
| Model | Input | Cached input | Output | Notes | Source |
|---|---|---|---|---|---|
| MiniMax-M3.1-Flash | $0.15 | $0.015 | $0.60 | Sourcechecked 2026-10-25 | |
| MiniMax-M3prompts up to 512k tokens | $0.30 | $0.06 | $1.20 | After the "permanent 50% off". List price: $0.60 input, $0.12 cache read, $2.40 output. | Sourcechecked 2026-10-25 |
| MiniMax-M3prompts over 512k tokens | $0.60 | $0.12 | $2.40 | After the "permanent 50% off". List price: $1.20 input, $0.24 cache read, $4.80 output. | Sourcechecked 2026-10-25 |
Terms on this page: Token · Prompt caching · Context window · Batch API
Estimate your MiniMax bill
Enter your monthly tokens and how they split between new input, cached input and output. The result updates as you type.
Write 40k, 250M or 5B. Input, cached input and output tokens together.
100M tokens a month costs from $9.42 (MiniMax-M3.1-Flash) to $20.58 (MiniMax-M3).
| Model | Per month | Per 1M tokens at this split |
|---|---|---|
| MiniMax-M3.1-Flash | $9.42 | $0.0942 |
| MiniMax-M3prompts up to 512k tokens | $20.58 | $0.2058 |
Standard prices in USD on 2026-10-25, before tax. Long-prompt tiers are left out; see the price table.
How the bill is worked out
Standing discount
Long prompts
Priority tier
Prompt caching
MiniMax API pricing questions
How much does the MiniMax API cost?
MiniMax bills its language models per million tokens, with separate prices for input, cached input and output. On 2026-10-25, standard prices ran from $0.15 (MiniMax-M3.1-Flash) to $0.30 (MiniMax-M3) per 1M input tokens, and $0.60 (MiniMax-M3.1-Flash) to $1.20 (MiniMax-M3) per 1M output tokens.
Does MiniMax offer a batch discount?
Its pricing page lists no batch price for the rows here. MiniMax-M3 shows a "permanent 50% off" its list price. The table shows the price you pay, with the list price next to it.
How does prompt caching change a MiniMax bill?
Cache reads are billed at the prompt caching read price, a tenth to a fifth of the input price.
Where do these prices come from?
From MiniMax's own pricing page, https://platform.minimax.io/docs/pricing/overview, checked on 2026-10-25. Every row links to it. When a price cannot be confirmed, the row says to check the vendor's page instead of showing a number.
What is MiniMax's "permanent 50% off"?
MiniMax's pricing page shows MiniMax-M3 at half its list price and calls the discount permanent. The table shows the price you pay, and the list price is in the notes.
What does the MiniMax Priority tier cost?
1.5 times the Standard rate, for priority admission, faster responses and more reliable requests. Set service_tier to priority to use it.
Compare and plan
Building with the MiniMax API? OceanLab builds AI into business workflows, with people kept in charge. AI automation →
