MiniMax: MiniMax M3

minimax/minimax-m3

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,...

Prompt $/1M

$0.300

Completion $/1M

$1.200

Context

1,048,576 tok

Best provider

107 tok/s · Venice

Specs

Model id: minimax/minimax-m3
Display name: MiniMax: MiniMax M3
Modality: text+image+video->text
Tokenizer: Other
Instruct type: —
Context length: 1,048,576
Max completion: 512,000
Prompt $/1M: $0.300
Completion $/1M: $1.200
Free tier: no

Capabilities

Function callingno
JSON modeno
System promptno
Visionyes
Moderatedno

Benchmark scores

Each axis is one benchmark, normalized to the best model in the field.

No benchmark data for this model.

Speed by provider

Provider	tok/s	TTFT	Total latency
Venicefastest	107	2,019 ms	2,602 ms
Artificial Analysis	98	1,211 ms	—
AtlasCloud	63	1,123 ms	1,369 ms
Minimax	61	1,372 ms	1,859 ms
Together	51	1,016 ms	1,358 ms
Novita	51	1,985 ms	2,526 ms
Parasail	40	1,203 ms	1,991 ms
Morph	36	2,166 ms	3,994 ms
SiliconFlow	31	2,989 ms	3,746 ms
GMICloud	22	3,508 ms	4,857 ms
DeepInfra	15	908 ms	1,269 ms