MiniMax M3
MiniMax-M3Compare MiniMax-M3 API pricing, supported endpoints, capabilities and access options on Modelsell.
- Starting price
- View full pricing
- Context
- 1M
- Maximum input window
- Max output
- 512K
- Maximum tokens per response
- Modalities
- →
Pricing by Supplier
Capabilities / Supported modalities
Provider & data privacy
ABAB tokenizerPerformance
Benchmarks
Scores on standardized evaluations. Higher percentages are better — and rank percentile shows
Metrics sourced fromArtificial Analysis 2026-09-30·MiniMax M3
This model is not included in the current benchmark snapshot.
Missing models or measurements are not zero scores.
Benchmark charts preserve the source model selection and reasoning settings. Missing models or measurements are not zero scores, and benchmark cost or speed is not this site’s service commitment.
About MiniMax M3
让文字与视觉信息共同参与工作
MiniMax-M3 支持文字、图片和视频输入，输出文本，适合将需求、代码与实际画面放在一起分析。它面向持续的多步骤协作，既可以帮助开发者完成编程任务，也可以围绕项目资料、设计参考和反馈不断完善成果。
从看懂素材到理解任务
分析一个交互功能时，可以同时提供需求说明、页面截图和操作录像，让模型比较预期流程与实际表现；制作内容方案时，可以结合文字目标和视觉参考，整理表达重点与执行步骤。明确每份素材的用途，有助于它把信息连接起来，而不是分别给出几段互不相关的说明。
M3适合需要多轮修改的工作方式：先理解目标与约束，交付可讨论版本，再依据反馈继续调整。长材料可以保留在上下文中，但仍应标出优先级、已有决策和不允许改变的内容。配合应用提供的工具，可以进一步参与文件处理、代码执行和实际验证。
按任务选择思考方式
M3支持开启、自适应与关闭思考三种方式。复杂排障或方案比较适合保留思考；规则明确的信息整理可以采用较轻的处理方式。评估时应关注任务是否真正完成、反馈是否被吸收，以及最终产物能否使用。长流程要保留阶段成果和失败信息，避免每轮从头开始。
Use cases and prompting
交互功能改进示例
“结合需求文档、当前页面截图和操作录像，改进文件上传流程。先找出实际操作与需求不一致的地方，再提出最小修改。保留现有文件类型与权限规则，重点处理上传进度、失败重试和重复提交。完成后按原录像中的步骤验证。”
提供工具时，应把真实执行结果交回模型，供下一轮修正。
多轮修改怎样避免丢失前面的要求？
保留原目标、已有决策和需要沿用的素材，并在反馈中指出具体改动。阶段结束时整理已完成内容与待办。
所有任务都需要一直思考吗？
M3支持enabled、adaptive和disabled思考方式。可按任务难度选择，并用实际样本比较结果质量与响应表现。
API access
API documentation
Code samples
/v1/chat/completions| Parameter | Type | Default / range | Description |
|---|---|---|---|
temperature | number | = 10 ~ 2 | Sampling temperature; lower is more deterministic |
top_p | number | = 10 ~ 1 | Nucleus sampling probability mass |
max_tokens | integer | >= 1 | Maximum number of tokens in the response |
frequency_penalty | number | = 0-2 ~ 2 | Penalises repetition of frequent tokens |
presence_penalty | number | = 0-2 ~ 2 | Encourages introducing new topics |
stop | array | — | Up to 4 strings that stop generation |
seed | integer | — | Deterministic sampling seed (best-effort) |
n | integer | = 1>= 1 | Number of completions to generate |
stream | boolean | = false | Stream tokens via Server-Sent Events |
response_format | object | — | Force JSON object or schema-conforming output |
tools | array | — | Tool / function declarations the model may call |
tool_choice | string | autononerequired | Tool-choice policy or specific tool name |
logprobs | boolean | = false | Return per-token log probabilities |
top_logprobs | integer | 0 ~ 20 | Number of top log probabilities returned per token |
logit_bias | object | — | Per-token logit bias map |
user | string | — | End-user identifier for abuse monitoring |
Replace <YOUR_API_KEY> with the API key from your token settings.
Authentication
All requests must include Authorization: Bearer <TOKEN> header. Anthropic-formatted endpoints accept the x-api-key header instead.
Generate tokens from the Tokens page; you can scope them to specific models, groups, IPs, and rate-limits.
Supported parameters
| Parameter | Type | Default / range | Description |
|---|---|---|---|
temperature | number | = 10 ~ 2 | Sampling temperature; lower is more deterministic |
top_p | number | = 10 ~ 1 | Nucleus sampling probability mass |
max_tokens | integer | >= 1 | Maximum number of tokens in the response |
frequency_penalty | number | = 0-2 ~ 2 | Penalises repetition of frequent tokens |
presence_penalty | number | = 0-2 ~ 2 | Encourages introducing new topics |
stop | array | — | Up to 4 strings that stop generation |
seed | integer | — | Deterministic sampling seed (best-effort) |
n | integer | = 1>= 1 | Number of completions to generate |
stream | boolean | = false | Stream tokens via Server-Sent Events |
response_format | object | — | Force JSON object or schema-conforming output |
tools | array | — | Tool / function declarations the model may call |
tool_choice | string | autononerequired | Tool-choice policy or specific tool name |
logprobs | boolean | = false | Return per-token log probabilities |
top_logprobs | integer | 0 ~ 20 | Number of top log probabilities returned per token |
logit_bias | object | — | Per-token logit bias map |
user | string | — | End-user identifier for abuse monitoring |
Rate limits
| Supplier | RPM | TPM | RPD |
|---|---|---|---|
| Alibaba | Unlimited | Unlimited | Unlimited |
| official | Unlimited | Unlimited | Unlimited |
No restriction
Frequently asked questions about MiniMax-M3
What is MiniMax-M3?
Compare MiniMax-M3 API pricing, supported endpoints, capabilities and access options on Modelsell.
How do I call MiniMax-M3?
Create an API key with access to MiniMax-M3, then use the exact model ID and a supported endpoint from the API access section. Request fields depend on the selected endpoint.
How is MiniMax-M3 priced?
Pricing depends on the selected provider group and the model billing unit. The current input, output, request, or media prices are shown on this page before sign-up.
What is the context window of MiniMax-M3?
The model catalog lists a context window of 1048576 tokens. Check the selected endpoint for request limits.
What is the maximum output of MiniMax-M3?
The model catalog lists a maximum output of 512000 tokens. Your request settings may set a lower limit.
How should I evaluate MiniMax-M3 for my project?
Start with the use cases and prompting guidance on this page, then evaluate the model with representative inputs from your project.