MiniMax API pricing for every model, newest first
By TechCompare · Updated · How we check
MiniMax M3.1 Flash is the newest MiniMax model and the lowest cost one MiniMax sells for a 100,000 token prompt with a 5,000 token answer, at $0.01125 a call with half the input cached.
Every MiniMax model and its API price
Newest first. Prices are per 1M tokens. One request is 100K tokens in and 5K out, with 50% of the input cached.
| Model | Input | Output | Cached | Context | One request | Listed |
|---|---|---|---|---|---|---|
| MiniMax M3.1 FlashMinimax | $0.15 | $0.60 | $0.015 | 1.05M | $0.0112 | Oct 19, 2026 |
| MiniMax M3Minimax | $0.30 | $1.20 | $0.06 | 1.05M | $0.024 | May 31, 2026 |
| MiniMax M2.7Cheapest host: GMICloud | $0.30 | $1.20 | $0.06 | 197K | $0.024 | Mar 18, 2026 |
| MiniMax M2.5Cheapest host: Venice | $0.27 | $0.95 | $0.03 | 198K | $0.0198 | Feb 12, 2026 |
| MiniMax M2-herMinimaxLast known price | $0.30 | $1.20 | $0.03 | 66K | $0.0225 | Jan 23, 2026 |
| MiniMax M2.1MinimaxLast known price | $0.30 | $1.20 | $0.03 | 205K | $0.0225 | Dec 23, 2025 |
| MiniMax M2MinimaxLast known price | $0.30 | $1.20 | $0.30 | 205K | $0.036 | Oct 23, 2025 |
| MiniMax M1Cheapest host: NovitaLast known price | $0.55 | $2.20 | $0.55 | 1M | $0.066 | Jun 17, 2025 |
| MiniMax-01MinimaxLast known price | $0.20 | $1.10 | $0.20 | 1M | $0.0255 | Jan 15, 2025 |
Listed is the day OpenRouter added the model. Prices checked Nov 14, 2026.
MiniMax is an AI company in Shanghai. Besides its M series language models, it makes the Hailuo video models and speech models. This page lists all 4 MiniMax language models OpenRouter carries, newest first, at MiniMax's own price where MiniMax sells the model.
MiniMax M3 is multimodal. It reads text, images and video with a 1.05M window, at $0.30 input and $1.20 output per million tokens. MiniMax M3.1 Flash improves on M3 at agent, coding and cybersecurity work, at $0.15 and $0.60.
Calculator
Cost Comparison
Based on 100,000 input tokens (50% cached), 5,000 output tokens, and 100 requests.Prices come live from OpenRouter at each maker's own price where it's listed. Temporary deals are left out.
How to read the MiniMax prices
MiniMax has off-peak rates on MiniMax M3.1 Flash. In those hours it bills $0.075 input and $0.30 output per million, 50% off input. MiniMax's pricing page lists the hours, so move work that can wait into them. MiniMax M3 bills one rate around the clock right now.
A cached token on MiniMax M3.1 Flash costs $0.015 per million, 90% off the normal input rate. That's most of the input in a long agent session. No batch price is listed for MiniMax M3 right now.
MiniMax M3.1 Flash reads up to 1.05M tokens, the largest window in the family. Video and images use up that window fast, so check the token count of a real input before you plan around it.
Verdict
MiniMax M3.1 Flash is the newest MiniMax model and the lowest cost one for the example request, so it's the place to start. Use MiniMax M3 where you need it to read images or video.
If your traffic can wait, check the off-peak hours. Moving a nightly job into them is an easy saving.
More LLM pricing scenarios
Related guides
Frequently asked questions
How much does the MiniMax API cost?
Who makes MiniMax?
Does MiniMax have off-peak pricing?
Can MiniMax M3 read images and video?
Which MiniMax model has the largest context window?
Where do these prices come from?
Related tools
LLM VRAM Calculator
Calculate the VRAM needed to run or fine-tune any LLM at any quantization.
Use toolPower Cost Estimator
Estimate annual electricity costs for your PC, Server, or TV.
Use toolData Transfer Calculator
Estimate transfer times for files over USB, WiFi, Ethernet, and more.
Use toolJSON 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