TechCompare LogoTechCompare

MiniMax-M3 API Pricing & Cost Calculator

By TechCompare · Updated · How we check

MiniMax-M3 is a strong value pick for high-volume utility work: it's 3.1x cheaper on output than Gemini Flash, with up to 1M tokens of context.

Calculator

Cost Comparison

Based on 30,000 input tokens (50% cached), 3,000 output tokens, and 1,000 requests.Prices come live from OpenRouter at each maker's own price where it's listed. Temporary deals are left out.

Loading model prices
Same 30,000 in / 3,000 out (50% cached) scenario, pre-loaded. Adjust tokens, caching, or swap models.
Edit in the full tool

MiniMax-M3 is MiniMax's API model, priced below Gemini 3.6 Flash on both rows, aimed at high-volume classification and routing workloads. Its context window reaches 1M tokens (512K guaranteed).

MiniMax: MiniMax M3

Cheapest host: GMICloud (fp8)

Input
$0.30
Output
$1.20
Cached
$0.06

per 1M tokens

Batch availableFlex available

Price checked 2026-11-12

How this is calculated

MiniMax-M3 is priced at $0.30 per million input tokens and $1.20 per million output tokens, with a prompt caching discount of 80% ($0.06 per million cached reads).

Verdict

Use MiniMax-M3 for high-volume utility pipelines with stable prompts, such as classification, routing and formatting.

It sits at $0.30/M input and $1.20/M output, with the 80% cache discount dropping cached input to $0.06/M. Output is 3.1x cheaper than on Gemini 3.6 Flash, and its context reaches 1M tokens. The cache hit rate decides most of the per-call cost, since cached input drops to $0.06/M.

More API Standalones scenarios

GPT-5.6 Luna vs MiniMax-M3
Two utility tier models for high volume work. Compare token rates and caching.
View details
Ling-3.1-flash vs MiniMax-M3.1-Flash
Compare a cheap text only model with a multimodal one, and see how deals and off-peak hours change the bill.
View details
MiniMax-M3.1-Flash Pricing
What MiniMax-M3.1-Flash costs per request and per month, with prompt caching.
View details

Related guides

MiniMax-M3.1-Flash API pricing
See the input, output, and cache rates for M3.1 Flash.
View guide
minimax m3 428b VRAM estimate
VRAM footprint for the minimax m3 428b model this pricing entry is for.
View guide
Prompt optimization
Cutting tokens is the cheapest way to cut cost.
View guide

Frequently asked questions

How does MiniMax-M3 stack up against GPT-5.6 Luna?
Luna ($0.20/$1.20 list price) is cheaper than MiniMax-M3 ($0.30/$1.20) on a typical 30K-input, 3K-output call ($0.0096 vs $0.0126). M3 has up to 1M tokens of context. Pick Luna for the absolute floor on price, M3 for its long context.
How much does MiniMax-M3 cost per million output tokens?
MiniMax-M3 charges $1.20 per million output tokens at standard pricing, matching GPT-5.6 Luna's output rate. Input is $0.30 per million (above Luna's $0.20/M). The 80% prompt caching discount brings cached input to $0.06 per million.

Related tools

LLM VRAM Calculator

Calculate the VRAM needed to run or fine-tune any LLM at any quantization.

Use tool

Power Cost Estimator

Estimate annual electricity costs for your PC, Server, or TV.

Use tool

Data Transfer Calculator

Estimate transfer times for files over USB, WiFi, Ethernet, and more.

Use tool

JSON Formatter

Validate, format, and minify JSON. Browse it as a tree, run JSONPath queries, compare two documents, or validate against a JSON Schema.

Use tool