All models

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 8 providers serving this model.

ProviderInput /MOutput /MCache read /MContextMax outputUptime 24h
GMICloudfp8$0.24$0.96$0.0481.05M98.21%
Novitafp8$0.30$1.20$0.061M131K98.72%
Venicefp8$0.30$1.20$0.06524K66K95.96%
Minimaxfp8$0.30$1.20$0.06524K512K99.04%
AtlasCloudfp8$0.30$1.20$0.06524K524K98.39%
Together$0.30$1.20$0.06524K96.99%
Morph$0.30$1.20256K256K93.79%
DeepInfrafp8$0.30$1.20$0.06524K512K97.37%

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
reasoning
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.