- Input $/1M
- $0.30
- Output $/1M
- $1.20
- Context
- 1M
- Max output
- 524K
- Reasoning
- Yes
- Included in
- 10 plans
API model id
MiniMax-M3Input
$0.30
Output
$1.20
Cache read
$0.06
- Above 512K input tokens
- Input $0.60 · Output $2.40 · Cache read $0.12 / 1M tokens
Published rate checked 2026-09-29. Sources below.
MiniMax lists M3 at $0.60 input, $2.40 output and $0.12 cache read per million tokens up to 512K input tokens, shown with a permanent 50% discount. The catalog records the discounted rates MiniMax charges. Priority service tier costs 1.5x standard. No cache-write rate is published for M3.
Current published base rates. Context tiers, cache-write duration and other conditions may change the rate for a request. These are not a reconstructed historical invoice.
- Context window
- 1,000,000
- Maximum output
- 524,288
- Input
- text · image · video
- Reasoning
- Supported
- Tool calling
- Supported
Thinking is off unless requested with thinking type adaptive.
- Thinking
- Thinking is off when the thinking parameter is omitted. Set thinking type to adaptive to turn it on.
- Released
- June 1, 2026
- Context
- The API supports up to 1M tokens of context with a guaranteed minimum of 512K tokens.
- Output limit
- max_completion_tokens accepts up to 524,288 tokens; MiniMax recommends 131,072.
- Long-context pricing
- Requests above 512K input tokens cost $0.60 input, $2.40 output and $0.12 cache read per MTok.
- Billing
- MiniMax shows a permanent 50% discount from $0.60 input and $2.40 output. Priority service tier costs 1.5x standard.
- Input support
- Text, image and video input.
Pricing, assumptions & evidence
Published base rate
Input $0.30 · Output $1.20 · Cache read $0.06 · Cache write Not listed
Above 512K input tokens: input $0.60, output $2.40, cache read $0.12.
- Official context window
- Maximum max_completion_tokens
- Thinking control and supported message content (text, image, video) by model
- Tool use and interleaved thinking
- Thinking control by model
- Context guarantee
- Output limit
- Discounted rates, long-context tier and priority tier
- Release date
Missing token-category prices are not zero. Workload pricing applies exact recorded categories and admitted routes. No benchmark score or quality ranking is inferred from prices.
Aliases, routes and identity
Catalog ID minimax-m3
Model release (kind: release)
Developer: MiniMax
minimax/minimax-m3harness_alias