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,...

Modalities
Text
Image
Video
In / Out price
$0.30 / $1.20 per 1M
Context
1.05M · 512K out
Released
Jun 1, 2026

Providers

Live list prices and uptime across 13 providers serving this model.

ProviderInput /MOutput /MCache read /MContextMax outputUptime 24h
CoreWeavefp4$0.23$0.96$0.05262K236K99.77%
GMICloudfp8$0.24$0.96$0.0481.05M524K99.72%
DeepInfrafp8$0.28$1.10$0.056524K512K99.30%
StreamLakefp8$0.30$1.20$0.061M512K99.20%
Venicefp8$0.30$1.20$0.06524K66K94.76%
Together$0.30$1.20$0.06524K472K99.91%
Parasailfp8$0.30$1.20$0.061.05M524K98.10%
AtlasCloudfp8$0.30$1.20$0.06524K524K91.14%
Novitafp8$0.30$1.20$0.061M131K99.78%
Minimaxfp8$0.30$1.20$0.06524K512K98.98%
Mara$0.60$2.401.05M944K88.24%
SambaNova$0.60$2.401.05M944K99.14%
ModelRunfp4$0.75$3.00$0.151.05M944K99.87%

No implicit prompt caching; cache reads require explicit cache control.

Capabilities

Tool calling
Reasoning
Frequency penalty
Include reasoning
Logit bias
Logprobs
Max tokens
Min p
Presence penalty
Repetition penalty
Response format
Seed
Stop
Structured outputs
Temperature
Tool choice
Top K
Top logprobs
Top P

Pricing detail

Input
$0.30
Output
$1.20
Cache read
$0.06
Cache write

USD per 1M tokens.