LEGACY 1M CONTEXTTEXT + VISIONOPENROUTERLOW INPUT PRICE
MiniMax-01 API Pricing
MiniMax-01 is the earlier MiniMax long-context model exposed on OpenRouter. The live model page lists $0.20/M input and $1.10/M output, with no separate cache price. Pulled directly from openrouter.ai daily.
Input - per 1M tokens
$0.20/M
Source openrouter.ai verified
Output - per 1M tokens
$1.10/M
Source openrouter.ai verified
Cached input - not published
$0.00/M
Cache no public row not listed
Effective - agentic blend
$0.27/M
92/8 split - no cache
§ 01 / TERMINAL
Run the numbers.
Live calculator pre-loaded with current MiniMax-01 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 DOC
Full archive summarization
$0.189/doc
VISION QA
Image-heavy case notes
$0.028/case
AGENT
Budget agent loop
$0.015/run
CHATBOT
Support turn
$0.002/turn
§ 03 / TAPE
Price history.
Input · $0.20/M
Output · $1.1/M
Cached · $0.00/M
JAN 15 OpenRouter release row lists MiniMax-01MAY 23 Verified unchanged on the live OpenRouter model page
§ 04 / TOKENIZER
Paste text. See tokens. See cost.
Estimate · minimax-tokenizer-estimate · ≈3.85 chars/token Auto-counts as you type
This is a chars-per-token approximation, not a real tokenizer. Actual tokens vary by language, code density, and tool-call overhead — counts are typically ±10–20% off for English prose, more for code or non-Latin scripts. For exact billing, use the vendor's official tokenizer.
Characters —
Words —
Tokens (estimated) —
Cost as input · uncached —
Cost as output · uncached —
Cost as cached input —
| Model | Input /M | Output /M | Effective blended | Context | Best for |
|---|---|---|---|---|---|
| MiniMax-01 Current | $0.20 | $1.10 | $0.27 agentic 92/8 | 1M | Cheaper 1M MiniMax workloads |
| MiniMax M1 | $0.40 | $2.20 | $0.54 pricier reasoning sibling | 1M | Legacy long-context reasoning |
| 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 |
| Gemini 2.5 Flash | $0.30 cache $0.03 | $2.50 | $0.27 Google multimodal peer | 1M | Global multimodal budget workloads |
| Baichuan4 Air | $0.14 | $0.14 | $0.14 China budget peer | 32K | Low-cost Chinese text workloads |
Frequently asked.
Practical MiniMax-01 pricing questions, with source prices separated from workload assumptions.
Q · 01 What is the MiniMax-01 API price? +
OpenRouter lists
MiniMax-01 at $0.20/M input and $1.10/M output. No cached-input price is published on the OpenRouter row.Q · 02 Why is this an archive page? +
The current MiniMax first-party PAYG docs emphasize M2-family models.
MiniMax-01 remains useful for invoice lookup and historical price comparison because OpenRouter still publishes the model page.Q · 03 Does it support vision? +
OpenRouter describes MiniMax-01 as combining MiniMax-Text-01 and MiniMax-VL-01 for image understanding. The per-token price on the model page is still the same
$0.20/$1.10 row.Q · 04 How is the effective cost computed? +
Because no cache discount is listed, the effective tile uses
$0.20/M for all input tokens. With a 92/8 input-output blend, MiniMax-01 lands at about $0.27/M.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 Is there a batch discount? +
OpenRouter does not publish a separate Batch API discount for this model row. Use the public
$0.20/M input and $1.10/M output rates unless your provider account has private terms.