LONG-CONTEXT REASONING1M CONTEXTTEXT ONLYOPEN-WEIGHTOPENROUTER
MiniMax M1 API Pricing
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. Pulled directly from openrouter.ai daily.
Input - per 1M tokens
$0.40/M
Source openrouter.ai verified
Output - per 1M tokens
$2.20/M
Source openrouter.ai verified
Cached input - not published
$0.00/M
Cache no public row not listed
Effective - agentic blend
$0.54/M
92/8 split - no cache
§ 01 / TERMINAL
Run the numbers.
Live calculator pre-loaded with current MiniMax M1 rates. Tweak workload split, then share the URL to share the calculation.
$ /mo
Workload split
Prompt cache hit rate
Tokens you can process
—
Words equivalent (English)
—
Effective rate
—
§ 02 / SCENARIOS
Real-world presets.
LONG CONTEXT
Reading a 900k-token archive
$0.382/doc
CODING AGENT
Large repo debug pass
$0.043/task
REASONING
Multi-step analysis
$0.037/run
RAG
Deep retrieval brief
$0.023/brief
§ 03 / TOKENIZER
Paste text. See tokens. See cost.
Calibrated · measured on the vendor's tokenizer · 2026-06-10 Auto-counts as you type
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.
Characters 374
Words 63
Tokens (estimated) 70 tokens
Cost as input · uncached $0.000028 USD
Cost as output · uncached $0.000154 USD
Cost as cached input $0.000000 USD
| Model | Input /M | Output /M | Effective blended | Context | Best for |
|---|---|---|---|---|---|
| MiniMax M1 Current | $0.40 | $2.20 | $0.54 agentic 92/8 | 1M | Legacy 1M reasoning workloads |
| MiniMax-01 | $0.20 | $1.10 | $0.27 cheaper MiniMax legacy sibling | 1M | Cheaper 1M-context MiniMax tasks |
| MiniMax M2.7 | $0.30 cache $0.06 | $1.20 | $0.19 newer MiniMax flagship | 205K | Current MiniMax agent loops |
| MiniMax M2.5 | $0.30 cache $0.03 | $1.20 | $0.17 newer value sibling | 205K | Lower-cost MiniMax agent loops |
| GPT-5.4 mini | $0.75 cache $0.07 | $4.50 | $0.54 OpenAI coding peer | 400K | OpenAI subagent workloads |
| DeepSeek V4 Pro | $0.43 cache $0.00 | $0.87 | $0.14 budget reasoning peer | 1M | Low-cost reasoning workloads |
Frequently asked.
Practical MiniMax M1 pricing questions, with source prices separated from workload assumptions.
Q · 01 What is the MiniMax M1 API price? +
OpenRouter lists
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 · 02 Is MiniMax M1 on MiniMax's current pay-as-you-go docs? +
No. The current MiniMax first-party PAYG page focuses on M2-family rows. This archive page uses the live OpenRouter model page because the queue marks M1 as surfaced via OpenRouter.
Q · 03 What context window does it support? +
The live OpenRouter page lists a
1M context window for minimax/minimax-m1. That is the main reason to keep an archive pricing page for it.Q · 04 Does prompt caching change the effective cost? +
No public cache price is listed for this OpenRouter row. The effective tile therefore uses the normal
$0.40/M input price for all input tokens in the 92/8 blend.Q · 05 When was this checked? +
The OpenRouter model page was opened and checked on
May 23, 2026. The snapshot row was refreshed to the exact model URL used for this page.Q · 06 How accurate is the tokenizer estimate? +
The browser widget uses a
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.