Skip to content

MiniMax M3 (DeepInfra)

by LLM Gateway · family minimax · listed Jun 2026RTVW

MiniMax multimodal model for long-context coding, perception, and agent planning

Current rates USD per 1M tokens

Input$0.28

Output$1.10

Cache read$0.056

Cache write—

Against the market

Input price vs. maker flagships ($/1M tokens)

Output price vs. maker flagships ($/1M tokens)

On the record

Model id: deepinfra/minimax-m3
Context window: 524K tokens
Max output: 524K tokens
Input modalities: text, image, video
Output modalities: text
Reasoning: yes
Tool calls: yes
Open weights: yes
Knowledge cutoff: —
Released: 2026-06-01
Last updated: 2026-06-01
Provider docs: llmgateway.io/docs

Back of the envelope

Input M tokensOutput M tokens

≈

Also listed at

SCNet Token Planfree in · free out
Volcengine Ark Coding Planfree in · free out
MiniMax Token Plan (minimax.io)free in · free out
MiniMax Token Plan (minimax.cn)free in · free out
Vultr$0.20 in · $0.90 out
EmpirioLabs AI$0.225 in · $0.90 out
CoreWeave$0.23 in · $0.96 out
NanoGPT$0.23 in · $0.96 out
Ambient$0.23 in · $0.96 out
Vancine$0.24 in · $0.96 out
Lilac$0.28 in · $1.10 out
Boundless$0.28 in · $1.10 out
DevPass (LLM Gateway)$0.28 in · $1.10 out
Deep Infra$0.28 in · $1.10 out
AIHubMix$0.288 in · $1.15 out

← All LLM Gateway listings