ModelPickr

Models / MiniMax / MiniMax-M3

MiniMax · minimax

MiniMax-M3

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

$0.30 in · $1.20 out

per 1M tokens · first-party price. Reference price from MiniMax, the lab's own listing.

Provider input prices run from $0.20 to $0.72 per 1M tokens. Output prices run from $0.90 to $2.88.

Context
1,048,576
Max output
512,000
Cache read
$0.06
Cache write
—
Reasoning
Yes
Tool calls
Yes
Structured output
Unknown
Vision
Yes
Open weights
Yes
License
—
Released
Jun 1, 2026
Updated in source
Jun 1, 2026
Knowledge
—
Providers
47

Higher rates apply above 200,000, 512,000 input tokens. The calculator switches to that rate when the input is longer.

Hugging Face weights

What this model costs per month

Prices are USD per 1M tokens. A month is 30 days. Cache hits use the cache-read rate when the model has one; otherwise the cache field is ignored.

monthly = requests/day × 30 × (input tokens × (1 − cache hit) × input price + input tokens × cache hit × cache-read price + output tokens × output price) ÷ 1,000,000

Providers

Base rates from Models.dev. Where a provider lists the model more than once, the row is the listing whose id is closest to the canonical model id.
ProviderInputOutputCache readCache writeStatus
Vultr$0.20$0.90———
EmpirioLabs AI$0.23$0.90$0.045——
CoreWeave$0.23$0.96$0.05——
Vancine$0.24$0.96$0.048——
Deep Infra$0.28$1.10$0.056——
Lilac$0.28$1.10$0.05——
AIHubMix$0.29$1.15———
IteraCompute$0.29$1.20$0.08——
Abacus$0.30$1.20———
ClinePass$0.30$1.20$0.06——
Cortecs$0.30$1.20$0.06——
DevPass$0.30$1.20$0.06——
Eden AI$0.30$1.20$0.06——
Fireworks AI$0.30$1.20$0.06——
Hugging Face$0.30$1.20———
Inco$0.30$1.20———
Jalapeno Cloud$0.30$1.20———
Kilo Gateway$0.30$1.20$0.06——
LLM Gateway$0.30$1.20$0.06——
Merge Gateway$0.30$1.20$0.06——
MiniMaxreference$0.30$1.20$0.06——
NanoGPT$0.30$1.20$0.06——
Nebius Token Factory$0.30$1.20———
Novita AI$0.30$1.20$0.06——
OpenCode$0.30$1.20$0.06——
OpenRouter$0.30$1.20$0.06——
OrcaRouter$0.30$1.20$0.06——
Pioneer$0.30$1.20$0.06$0.30—
Requesty$0.30$1.20$0.06——
SiliconFlow$0.30$1.20$0.06——
Tempr Gateway$0.30$1.20$0.06——
Vercel AI Gateway$0.30$1.20$0.06——
Charm Hyper$0.33$1.31$0.064——
CrossModel$0.33$1.32$0.066$0.33—
Wafer$0.33$1.32$0.07$0—
TensorX$0.40$2.00$0.10——
GMI Cloud$0.60$2.40$0.12——
Ofox$0.60$2.40$0.12——
Opper$0.60$2.40$0.12——
SambaNova$0.60$2.40$0.06——
Synthetic$0.60$1.20$0.60——
ZenMux$0.60$2.40———
302.AI$0.72$2.88———
Kenari$0$0———
Nvidia$0$0——deprecated
SCNet Token Plan$0$0$0——
Volcengine Ark Coding Plan$0$0$0——

Comparisons