Inference providers · open weights · MiniMax

MiniMax M3

Open-weights model published by MiniMax, which also serves it through its own endpoint on OpenRouter: that rate is the maker's list price, and the other 1 hosts below are compared with it. Each figure was read on that host's own pricing page and links to it, with the date it was checked.

What each host charges

2 hosts, every one of them at $0.30 per 1M input tokens and $1.20 per 1M output tokens: no spread at all, within the 1.15× that AI Signal treats as the same price. Pick a host on latency, region or tooling; the bill will be the same.

Host Input Output Cached input Context served Checked Source
Fireworks AI $0.30 $1.20 $0.06 — November 16, 2026 docs.fireworks.ai
OpenRouter (via Minimax, the maker) $0.30 $1.20 $0.06 524K tokens November 18, 2026 openrouter.ai

Hosts that no longer price it

Offerings AI Signal tracked and stopped listing, with the date and the reason. They are kept because nobody else records when a host drops a model.

Mentioned in

One post on AI Signal cites MiniMax M3. The sentence is the post's own, taken from where it links here.

Recorded price changes

Every change AI Signal has recorded for a host's price of MiniMax M3, with the date it took or takes effect and why. Changes of our own rule are listed too, and say so.

On OpenRouter

On September 15, 2026 OpenRouter listed 13 endpoints for MiniMax M3, 12 of them healthy, from $0.23 (CoreWeave) to $0.75 per 1M input tokens. The figure OpenRouter's catalog shows for the model, $0.30 / $1.20, is the 4th cheapest of those 13. Of these, only Minimax's own endpoint is the maker's list price; the rest are resellers. Together AI, which AI Signal stopped listing on November 6, 2026 because its own pricing page carries no price for the model, serves it once through OpenRouter; that is a reseller listing, not a published price, so the row stays out. DeepInfra, which AI Signal stopped listing on September 6, 2026 because its own pricing page carries no price for the model, serves it once through OpenRouter; that is a reseller listing, not a published price, so the row stays out.

Specifications

Weights published by MiniMax
Context length (maker) 1.0M tokens
Context served by hosts 524K tokens
API model ids Fireworks AI: minimax-m3; OpenRouter: minimax/minimax-m3
Hosts with a verified price 2

Host prices verified between November 16, 2026 and November 18, 2026, each on the host's own pricing page linked in the table above, never from a reseller catalog or a third-party table. Maker and context length from MiniMax's model card, checked September 15, 2026 (max_position_embeddings 1048576 in the model's config.json (text_config); the hosts below serve a shorter window). How the data is checked.