MiniMaxopen weightsMiniMax M3 pricing
$0.30 per 1M input tokens and $1.20 per 1M output tokens. In real work that is 0.12¢ per chat answer and 0.47¢ to summarize a 20-page PDF.
Official price at MiniMax: $0.30 / $1.20 per 1M, cached $0.06 (source, checked Oct 11, 2026).
What MiniMax M3 costs per task
Every row below was measured: we ran the task on this model and counted the tokens. Reasoning tokens are billed as output.
| Task | Cost | Tokens used | Price rank | Basis |
|---|---|---|---|---|
| Answer a chat question | 0.12¢$1.18 / 1,000 | 205 in · 447 out · 482 reasoning | 113 of 336 | measured |
| Reply to a customer email | 0.07¢$0.66 / 1,000 | 417 in · 260 out · 187 reasoning | 129 of 336 | measured |
| Write a 1,500-word blog post | 0.27¢$2.72 / 1,000 | 219 in · 1,774 out · 442 reasoning | 76 of 336 | measured |
| Write 10 product descriptions | 0.21¢$2.05 / 1,000 | 441 in · 1,071 out · 531 reasoning | 70 of 336 | measured |
| Translate 1,000 words | 0.73¢$7.33 / 1,000 | 1,473 in · 1,207 out · 4,535 reasoning | 166 of 336 | measured |
| Proofread one page (500 words) | 0.15¢$1.54 / 1,000 | 874 in · 651 out · 416 reasoning | 126 of 336 | measured |
| Summarize a 20-page PDF | 0.47¢$4.72 / 1,000 | 12,901 in · 462 out · 246 reasoning | 122 of 336 | measured |
| Extract data from an invoice | 0.12¢$1.18 / 1,000 | 536 in · 563 out · 289 reasoning | 113 of 336 | measured |
| Analyze a 200-row spreadsheet | ≥2.1¢$20.68 / 1,000 | 4,940 in · 153 out · 15,847 reasoning | 163 of 336 | measured |
| Answer from 5 retrieved documents (RAG) | 0.26¢$2.64 / 1,000 | 3,773 in · 822 out · 437 reasoning | 118 of 336 | measured |
| Classify 100 support tickets | 0.27¢$2.74 / 1,000 | 1,424 in · 441 out · 1,485 reasoning | 99 of 336 | measured |
| Review 500 lines of code | 0.45¢$4.53 / 1,000 | 4,762 in · 2,588 out | 75 of 336 | measured |
| Write a SQL query | 0.09¢$0.92 / 1,000 | 272 in · 702 out | 94 of 336 | measured |
| Run a 50-step coding agent | 18¢$182 / 1,000 | 2,221,837 in · 14,895 out · 9,350 reasoning | 86 of 336 | modeled |
Price at every provider
List prices per 1M tokens (input / output) at each host serving MiniMax M3 through OpenRouter today. Hosts can differ in quantization, context and speed.
| Provider | Input / output | Cached input | Context | Uptime |
|---|---|---|---|---|
 DeepInfrafp8 | $0.22 / $0.88 | $0.045 | 524K | 0% |
| C CoreWeavefp4 | $0.23 / $0.96 | $0.05 | 262K | 100% |
| G GMICloudfp8 | $0.24 / $0.96 | $0.048 | 1M | 100% |
DeepInfrafp8 | $0.28 / $1.10 | $0.056 | 524K | |
| S StreamLakefp8 | $0.30 / $1.20 | $0.06 | 1M | 100% |
| V Venicefp8 | $0.30 / $1.20 | $0.06 | 524K | 100% |
 Togetherunknown | $0.30 / $1.20 | $0.06 | 524K | 100% |
 Parasailfp8 | $0.30 / $1.20 | $0.06 | 1M | 100% |
| A AtlasCloudfp8 | $0.30 / $1.20 | $0.06 | 524K | 100% |
 Novitafp8 | $0.30 / $1.20 | $0.06 | 1M | 100% |
| M Minimaxfp8 | $0.30 / $1.20 | $0.06 | 524K | 100% |
| M ModelRunfp8 | $0.30 / $1.30 | $0.05 | 1M | 100% |
| M Maraunknown | $0.60 / $2.40 | - | 1M | 100% |
 SambaNovaunknown | $0.60 / $2.40 | $0.06 | 1M | 100% |
Price history
First seen in our price history on Jun 6, 2026 at $0.30 input / $1.20 output. The list price has not changed since.
FAQ
How much does MiniMax M3 cost?
MiniMax M3 costs $0.30 per 1 million input tokens and $1.20 per 1 million output tokens, with cached input at $0.06 (list price on Oct 18, 2026). In practice one chat answer costs about 0.12¢ and summarizing a 20-page PDF about 0.47¢.
Where is MiniMax M3 cheapest?
Among 14 providers we track, the lowest list price today is at DeepInfra: $0.22 input and $0.88 output per 1M tokens.
Is the MiniMax M3 cost per task measured or estimated?
Measured: we ran all 13 benchmark prompts on MiniMax M3 through OpenRouter and recorded the tokens it used.