MiniMax M1 API Pricing
Not on MiniMax's model list: MiniMax's documentation lists MiniMax M1 neither as available nor as retired, and MiniMax never published this price — the figures below come from an OpenRouter resale listing and are kept for reference only. MiniMax M1 is the legacy long-context reasoning model surfaced through OpenRouter. The live OpenRouter model page lists $0.40/M input and $2.20/M output, with no separate cache-read price. Checked by hand against openrouter.ai.
MiniMax M1 API cost calculator.
Live calculator pre-loaded with current MiniMax M1 rates. Tweak workload split, then share the URL to share the calculation.
MiniMax M1 cost on real workloads.
Reading a 900k-token archive
Large repo debug pass
Multi-step analysis
Deep retrieval brief
Counts use a chars-per-token calibration measured on the vendor's own published tokenizer (MiniMaxAI/MiniMax-M2.1, 2026-06-10). English prose is typically within a few percent; code and non-Latin scripts tokenize heavier. For billing-exact counts use the vendor's count-tokens API.
| Model | Input /M | Output /M | Effective blended | Context | Best for |
|---|---|---|---|---|---|
| MiniMax M1 Current | $0.40 | $2.20 | $0.544 agentic 92/8 | 1M | Legacy 1M reasoning workloads |
| MiniMax-01 | $0.20 | $1.10 | $0.272 deprecated · −2.0× | 1M | Cheaper 1M-context MiniMax tasks |
| MiniMax M2.7 | $0.30 cache $0.06 | $1.20 | $0.191 deprecated · −2.8× | 205K | MiniMax agent loops until November 18, 2026 |
| MiniMax M2.5 | $0.30 cache $0.03 | $1.20 | $0.168 deprecated · −3.2× | 205K | Lower-cost MiniMax agent loops |
| GPT-6.1 Terra | $1.00 cache $0.05 | $5.00 | $0.645 +19% | 1.05M | OpenAI's fast, efficient GPT-6 tier |
| DeepSeek V4 Pro | $1.32 cache $0.044 | $3.96 | $0.569 +5% | 1M | Low-cost reasoning workloads |
MiniMax M1 API pricing FAQ.
Practical MiniMax M1 pricing questions, with source prices separated from workload assumptions.
Q · 01 Is MiniMax M1 still sold by MiniMax? +
Q · 02 What is the MiniMax M1 API price? +
MiniMax M1 at $0.40/M input and $2.20/M output. The page does not publish a separate cached-input tier, so this calculator treats cached input as unavailable.Q · 03 Is MiniMax M1 on MiniMax's current pay-as-you-go docs? +
Q · 04 What context window does it support? +
1M context window for minimax/minimax-m1. That is the main reason to keep an archive pricing page for it.Q · 05 Does prompt caching change the effective cost? +
$0.40/M input price for all input tokens in the 92/8 blend.Q · 06 When was this checked? +
May 23, 2026. The snapshot row was refreshed to the exact model URL used for this page.Q · 07 How accurate is the tokenizer estimate? +
minimax-tokenizer-estimate planning ratio for English text. Final billing depends on the provider-side tokenizer and can differ for code, Chinese, and mixed-language prompts.