MiniMax M3
$0.30 per 1M input tokens and $1.20 per 1M output tokens · 1.05M context · vision, tools, reasoning, JSON, open weights.
Prices checked Oct 21, 2026 · tracked by LLM Cost Index since Oct 21, 2026
What MiniMax M3 costs per month
Estimated monthly bill for typical workloads, using the cached-input price for repeated context. Try your own numbers in the cost calculator.
| Workload | Per month |
|---|---|
| Customer chatbot 1,000 conversations a day, 8 turns each | $157 |
| Document Q&A (RAG) 500 questions a day over retrieved documents | $33.84 |
| Coding / tool-using agent 200 tasks a day, long tool-heavy contexts | $72.00 |
| Content generation 30 long articles a day | $3.51 |
| Classification / extraction 100,000 short items a day | $324 |
Price history
We started tracking MiniMax M3 on Oct 21, 2026; the chart appears as soon as there is a second data point. See all recent price changes.
Where to run MiniMax M3: 14 providers
DeepInfra is the cheapest at $0.224 input / $0.88 output per 1M tokens. Uptime is the average over the last 30 days as reported by OpenRouter; see provider reliability.
| Provider | Input / 1M | Output / 1M | Context | Uptime | Notes |
|---|---|---|---|---|---|
| DeepInfra | $0.224 | $0.88 | 524K | 71.4% | flex tier, fp8 |
| CoreWeave | $0.23 | $0.96 | 262K | 99.9% | fp4 |
| GMICloud | $0.24 | $0.96 | 1.05M | 99.9% | fp8 |
| DeepInfra | $0.28 | $1.10 | 524K | 99.6% | fp8 |
| AtlasCloud | $0.30 | $1.20 | 524K | 99.1% | fp8 |
| Minimax | $0.30 | $1.20 | 524K | 99.7% | fp8 |
| ModelRun | $0.30 | $1.30 | 1.05M | 99.7% | fp8 |
| Novita | $0.30 | $1.20 | 1M | 99.9% | fp8 |
| Parasail | $0.30 | $1.20 | 1.05M | 99.7% | fp8 |
| StreamLake | $0.30 | $1.20 | 1M | 99.5% | fp8 |
| Together | $0.30 | $1.20 | 524K | 99.8% | — |
| Venice | $0.30 | $1.20 | 524K | 94.3% | fp8 |
| Mara | $0.60 | $2.40 | 1.05M | 72.7% | — |
| SambaNova | $0.60 | $2.40 | 1.05M | 99.3% | — |
Cheaper alternatives to MiniMax M3
Models with the same tool calling, image input, structured output for at least 20% less (3:1 input/output mix), most capable first.
| Model | Input / 1M | Output / 1M | Context | Capabilities |
|---|---|---|---|---|
| Claude Haiku 5.5 Anthropic | $0.10 | $0.50 | 1M | visiontoolsreasoningJSON |
| GLM 5.3 Flash Z.ai | $0.041 | $0.12 | 1.05M | visiontoolsreasoningJSONopen weights |
| GPT-6 Luna OpenAI | $0.10 | $0.50 | 1.05M | visiontoolsreasoningJSON |
| MiMo-V2.6-Flash Xiaomi | $0.14 | $0.28 | 1.05M | visionaudiotoolsreasoningJSONopen weights |
| DeepSeek V4 Flash Vision Exp DeepSeek | $0.216 | $0.647 | 1.05M | visiontoolsreasoningJSONopen weights |
How to pay less for MiniMax M3
For a customer chatbot (1,000 conversations a day, 8 turns each) that costs $209 a month at list price without caching:
| Option | Per month | You save |
|---|---|---|
| Move to Claude Haiku 5.5 (similar capabilities) | $58.56 | $150 (72%) |
| Route to DeepInfra (flex tier) | $155 | $54.24 (26%) |
| Use prompt caching (60% of input cached) | $157 | $51.84 (25%) |
Other workloads: cut-your-bill tool for MiniMax M3.
Specifications
| Model ID | minimax/minimax-m3 |
| Input | text, image, video |
| Output | text |
| Tool calling | Yes |
| Structured output | Yes |
| Reasoning mode | Yes |
| Open weights | Yes — MiniMaxAI/Minimax-M3 |
| Released | May 31, 2026 |
FAQ
- How much does MiniMax M3 cost?
- $0.30 per million input tokens and $1.20 per million output tokens; cached input costs $0.06 per million. Prices as of Oct 21, 2026.
- What is the context window of MiniMax M3?
- 1.05M tokens, with up to 512K output tokens per response.
- Does MiniMax M3 support images, tools and structured output?
- Images as input: yes. Tool calling: yes. Structured (JSON) output: yes. Reasoning mode: yes.
- What are cheaper alternatives to MiniMax M3?
- Models with the same key capabilities for at least 20% less include Claude Haiku 5.5 ($0.10 / $0.50), GLM 5.3 Flash ($0.041 / $0.12), GPT-6 Luna ($0.10 / $0.50).
More from MiniMax: all MiniMax models · how we collect prices