MiniMax

MiniMax M3

minimax/minimax-m3Hugging Face ↗

MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...

toolsstructuredreasoningimage in
Data source

Only tracked on Vercel AI Gateway.

MiniMax M3 usage over time

Vercel AI Gateway share of tokens, by day.

View
Tidelines — LLM usage and market share

MiniMax M3 holds 1.13% today, down from 2.19% at the start of the visible window.

Data: Vercel AI Gateway as of 2026-09-12 · Source: tidelines.ai/models/minimax-minimax-m3

Rank history

Tidelines — LLM usage and market share
Data: Vercel AI Gateway as of 2026-09-12 · Source: tidelines.ai/models/minimax-minimax-m3

Adoption curve vs the pantheon

MiniMax M3's share plotted against days since first tracked, overlaid on other current leaders on the same axis. The question every new-model page asks: is this one going to make it?

Tidelines — LLM usage and market share
Data: Vercel AI Gateway as of 2026-09-12 · Source: tidelines.ai/models/minimax-minimax-m3

Citable stat

As of 2026-09-12, MiniMax M3 holds 0.0% of Vercel AI Gateway token share, down 1.00pp over 30 days. Source: Tidelines (Vercel AI Gateway).

Cost per session

Median dollars spent on one MiniMax M3 session, by coding agent and session length.

Tidelines — LLM usage and market share

Token rate sets the price; session length and reasoning set the bill.

Agent1 turn2–9 turns10–49 turns50+ turns
Claude Code$0.0075$0.024$0.176$1.57
Hermes Agent$0.0050$0.014$0.101$0.634
Kilo Code$0.0040$0.019$0.084$0.629

Compare every model's session cost →

Data: OpenRouter session-cost dataset as of 2026-09-06 · Source: tidelines.ai/models/minimax-minimax-m3

Where to run it

MiniMax M3 pricing by provider

Tidelines — LLM usage and market share

Per-provider pricing, context, and uptime via OpenRouter. Sorted by output price.

MiniMax M3 is served by 12 tracked endpoints on OpenRouter. The cheapest output price is $0.96 per million tokens from CoreWeave, and the most expensive is $3.00 from ModelRun. The largest context window offered is 1049k tokens. Prices are list rates and refresh daily.

ProviderInput $/MOutput $/MContextUptime
CoreWeave$0.23$0.96262k99.62%
GMICloud$0.24$0.961049k99.60%
DeepInfra$0.28$1.10524k99.28%
StreamLake$0.30$1.201000k98.24%
Venice$0.30$1.20524k91.87%
Together$0.30$1.20524k99.98%
Parasail$0.30$1.201049k99.74%
AtlasCloud$0.30$1.20524k84.67%
Novita$0.30$1.201000k99.50%
Minimax$0.30$1.20524k72.51%
SambaNova$0.60$2.401049k95.10%
ModelRun$0.75$3.001049k100.00%