MiniMax M3
MiniMaxUpdated June 2026. MiniMax M3 by MiniMax: $0.3/M cache-miss input, $1.20/M output tokens. Cached input: $0.06/M. Long-context pricing above 512K input tokens: $0.6/M input, $2.40/M output. 1.0M context, 524K max output. Vision & Video. Free calculator + compare 40+ models.
Input Price
$0.3
cache miss / 1M tokens
Cached Input
$0.06
per 1M tokens
Output Price
$1.20
per 1M tokens
Context Window
1.0M
tokens
Specifications
| Provider | MiniMax |
| Model ID | MiniMax-M3 |
| Input Price | $0.3 / 1M cache-miss tokens |
| Cached Input Price | $0.06 / 1M tokens |
| Output Price | $1.2 / 1M tokens |
| Long Context Threshold | 512K input tokens |
| Long Context Pricing | $0.6 / 1M cache-miss input, $0.12 / 1M cached input, $2.4 / 1M output |
| Context Window | 1.0M tokens |
| Max Output | 524K tokens |
| Capabilities | textvisionvideofunction_calling |
| Release Date | 2026-06-01 |
| Pricing Source | Official MiniMax pricing |
| Price Verified | 2026-06-14 · International API pricing is listed in USD. China API pricing is listed separately in RMB. |
| Notes | Latest MiniMax frontier coding and agent model. Supports Adaptive Thinking, tool use, and native image/video input. Inputs above 512K tokens use long-context pricing and currently require limited-access availability. |
Monthly Cost Estimates
Estimated monthly costs based on different daily usage levels (assuming 50% input / 50% output split). Input estimates use cache-miss pricing, so cache-heavy workloads can be lower.
| Daily Tokens | Monthly Cost | Annual Cost |
|---|---|---|
| 10K | $0.22 | $2.70 |
| 50K | $1.13 | $13.50 |
| 100K | $2.25 | $27.00 |
| 500K | $11.25 | $135.00 |
| 1.0M | $22.50 | $270.00 |
About MiniMax M3
MiniMax M3 is a large language model by MiniMax. It features a 1.0M token context window with up to 524K tokens of output per request. The model supports 4 capabilities: text, vision, video, function_calling.
At $0.3 per million cache-miss input tokens and $1.2 per million output tokens, MiniMax M3 is positioned as a cost-effective option in the MiniMax lineup. Repeated prefix input can be charged at $0.06 per million cached tokens. Use our Token Counter to estimate how many tokens your prompts use, and our Pricing Calculator to compare costs across all models.
MiniMax M3 Key Details
- Pricing: $0.3/M cache-miss input tokens, $0.06/M cached input tokens, $1.2/M output tokens
- Context window: 1.0M tokens — one of the largest available
- Max output: 524K tokens per response
- Capabilities: text, vision, video, function_calling
- Highlights: Latest MiniMax frontier coding and agent model. Supports Adaptive Thinking, tool use, and native image/video input. Inputs above 512K tokens use long-context pricing and currently require limited-access availability.
- Released: 2026-06-01
Similar Price Range
Related Tools
FAQ
How much does MiniMax M3 cost?
MiniMax M3 costs $0.3 per million cache-miss input tokens and $1.2 per million output tokens. Cached input costs $0.06 per million tokens. For a typical workload of 100K input tokens/day and 50K output tokens/day, expect approximately $2.70/month before cache-hit savings.
What is MiniMax M3's context window?
MiniMax M3 supports a context window of 1.0M tokens. This means your combined input prompt and output response can be up to 1.0M tokens. The maximum output per response is 524K tokens.
Is MiniMax M3 good for my use case?
MiniMax M3 supports text, vision, video, function_calling. As a budget-friendly model, it works well for high-volume tasks like classification, summarization, and simple generation. Use our Pricing Calculator to compare with alternatives.