MiniMax-M3

minimax/minimax-m3

Maker: MiniMax, China
Released: 2026-06-01
Family: minimax
Weights: open
Tasks: text.chat, text.reasoning, code, vision.understand, vision.extract
Cheapest offering: DeepInfra, about $0.00061 for a typical text.chat call

Try it in the sandbox Use it from the API

Offerings

Provider	Model id at the provider	Status	Price per 1M tokens	Per-unit prices	Limits	Capabilities (level)
DeepInfra	`MiniMaxAI/MiniMax-M3`	ga	Input: $0.28 Output: $1.1 Cache read: $0.056 Since 2026-11-03 · models.dev, MIT	none	Context: 524,288 tokens Max output: 512,000 tokens	`input.text` claimed `input.image` claimed `input.video` claimed `input.pdf` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` claimed `tool_choice` claimed `prompt_caching` claimed
Fireworks AI	`accounts/fireworks/models/minimax-m3`	ga	Input: $0.3 Output: $1.2 Cache read: $0.06 Input, priority tier: $0.45 Output, priority tier: $1.8 Cache read, priority tier: $0.09 Since 2026-11-03 · models.dev, MIT	none	Context: 512,000 tokens Max output: 512,000 tokens	`input.text` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` claimed `input.image` claimed `tool_choice` claimed
Fireworks AI	`accounts/fireworks/routers/minimax-latest`	ga	Input: $0.3 Output: $1.2 Cache read: $0.06 Input, priority tier: $0.45 Output, priority tier: $1.8 Cache read, priority tier: $0.09 Since 2026-11-03 · models.dev, MIT	none	Context: 512,000 tokens Max output: 512,000 tokens	`input.text` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` claimed
OpenRouter	`minimax/minimax-m3`	ga	Input: $0.3 Output: $1.2 Cache read: $0.06 Since 2026-11-03 · models.dev, MIT	none	Context: 1,048,576 tokens Max output: 512,000 tokens	`input.text` claimed `input.image` claimed `input.video` claimed `input.pdf` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` claimed
Together AI	`MiniMaxAI/MiniMax-M3`	gadeprecated 2026-11-06	Input: $0.3 Output: $1.2 Cache read: $0.06 Since 2026-11-03 · models.dev, MIT	none	Context: 524,288 tokens Max output: 524,288 tokens	`input.text` claimed `input.image` claimed `input.video` claimed `input.pdf` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` claimed `parallel_tools` claimed `tool_choice` claimed `prompt_caching` claimed

Quality scores

Basis	Score (0–1)	Raw	Measured	Source
`epoch:gpqa_diamond`	0.943	0.9091	2026-08-10	Epoch AI, CC-BY-4.0, normalized by Nanner Tech
`lmarena:document_style_control`	0.813	1432.9648	2026-09-13	LMArena, CC-BY-4.0, normalized by Nanner Tech
`lmarena:vision_style_control`	0.810	1233.2884	2026-10-19	LMArena, CC-BY-4.0, normalized by Nanner Tech
`lmarena:webdev`	0.265	1483.3052	2026-10-28	LMArena, CC-BY-4.0, normalized by Nanner Tech
`lmarena:agent`	0.000	-0.1042	2026-11-02	LMArena, CC-BY-4.0, normalized by Nanner Tech

Aliases

Other names the API accepts for this model.

accounts/fireworks/models/minimax-m3
accounts/fireworks/routers/minimax-latest
minimaxai/minimax-m3

Use it from the API

Look this model up, or ask for the best model for its task on the providers that offer it. See the quickstart and the API reference.

Look up this model

curl 'https://rhumbdata.com/v1/models/minimax/minimax-m3' \
  -H "Authorization: Bearer $RHUMB_KEY"

Resolve text.chat on its providers

curl 'https://rhumbdata.com/v1/resolve?task=text.chat&providers=deepinfra,fireworks,openrouter,together' \
  -H "Authorization: Bearer $RHUMB_KEY"

Built from catalog version 2026-11-04.3 of 2026-11-04. Prices are list prices per 1M tokens unless marked otherwise; every score shows its source's notice (see Attributions).