Models

MiniMax-M3

wandb · 1049K ctx · 21 providers · updated 2026-09-19 00:16 UTC

Cheapest
$0.412 Official list · Wandb
Avg price
$0.569 /1M
providers
21
Tokens (24h)
219B
Volume (24h)
$114.9K est.
(3 × $0.230 + $0.960) ÷ 4 = $0.412/1M — the $/1M figure blends input and output at 3:1 — that is the only way models with two different rates can be ranked on one axis. Your actual rate depends on your own input:output mix — input only $0.230, 3:1 $0.412, 1:1 $0.595, output only $0.960 per 1M.

The board shows this model's cheapest measured offer ($0.412/1M); the smaller figure under it is the mean of the 30 offers listed below ($0.569/1M). Add those up and divide — it matches. 24h token volume (219B) is sourced from OpenRouter public rankings — today's only public source of absolute per-model token counts (Vercel AI Gateway publishes share-of-traffic percentages); as more sources come online, the per-router breakdown will sum to this total here.

ProviderRouter / Source$ in /1M$ out /1MTTFTTPSUptimeEvidence
wandb Pricebook (LiteLLM) $0.230$0.960 Official list
CoreWeave (fp4) OpenRouter $0.230$0.960 480ms 63 99.8% API-measured
GMICloud (fp8) OpenRouter $0.240$0.960 1083ms 27 100.0% API-measured
0g-teetls 0G Router $0.270$1.08 API-measured
deepinfra Pricebook (LiteLLM) $0.280$1.10 Official list
deepinfra HuggingFace Router $0.280$1.10 659ms 17 API-measured
DeepInfra (fp8) OpenRouter $0.280$1.10 1397ms 15 100% API-measured
aihubmix Pricebook (LiteLLM) $0.288$1.15 Official list
fireworks_ai Pricebook (LiteLLM) $0.300$1.20 Official list
minimax Pricebook (LiteLLM) $0.300$1.20 Official list
nebius Pricebook (LiteLLM) $0.300$1.20 Official list
together_ai Pricebook (LiteLLM) $0.300$1.20 Official list
tencent Pricebook (LiteLLM) $0.300$1.20 Official list
novita Pricebook (LiteLLM) $0.300$1.20 Official list
openrouter Pricebook (LiteLLM) $0.300$1.20 Official list
novita HuggingFace Router $0.300$1.20 580ms 192 API-measured
together HuggingFace Router $0.300$1.20 395ms 102 API-measured
fireworks-ai HuggingFace Router $0.300$1.20 785ms 97 API-measured
novita-ai Novita AI $0.300$1.20 API-measured
requesty Requesty $0.300$1.20 API-measured
StreamLake (fp8) OpenRouter $0.300$1.20 1350ms 72 99.6% API-measured
Venice (fp8) OpenRouter $0.300$1.20 1322ms 68 96.0% API-measured
Together OpenRouter $0.300$1.20 799ms 68 100% API-measured
Parasail (fp8) OpenRouter $0.300$1.20 818ms 115 99.3% API-measured
AtlasCloud (fp8) OpenRouter $0.300$1.20 1106ms 87 99.9% API-measured
Novita (fp8) OpenRouter $0.300$1.20 1491ms 68 100% API-measured
Minimax (fp8) OpenRouter $0.300$1.20 639ms 86 99.3% API-measured
Mara OpenRouter $0.600$2.40 1055ms 68 85.2% API-measured
SambaNova OpenRouter $0.600$2.40 927ms 96 99.1% API-measured
ModelRun (fp4) OpenRouter $0.750$3.00 306ms 125 100% API-measured

Volume trend

1.1T 30d d-29 · 243B tokensd-28 · 199B tokensd-27 · 181B tokensd-26 · 176B tokensd-25 · 213B tokensd-24 · 310B tokensd-23 · 373B tokensd-22 · 554B tokensd-21 · 805B tokensd-20 · 884B tokensd-19 · 948B tokensd-18 · 668B tokensd-17 · 1.0T tokensd-16 · 1.1T tokensd-15 · 1.1T tokensd-14 · 1.1T tokensd-13 · 976B tokensd-12 · 384B tokensd-11 · 804B tokensd-10 · 226B tokensd-9 · 220B tokensd-8 · 234B tokensd-7 · 205B tokensd-6 · 181B tokensd-5 · 175B tokensd-4 · 210B tokensd-3 · 223B tokensd-2 · 233B tokensd-1 · 238B tokensd-0 · 219B tokens

Last 30 days: 243B → 219B (-10%); range 175B–1.1T tokens/day. Source: OpenRouter public rankings; refreshed hourly.

Data & method

Cheapest ranked by blended = (3×in + out) ÷ 4; performance columns show only when a source provides them, never estimated. “Official list” = LiteLLM open pricebook (MIT); “API-measured” = provider/aggregator public APIs. Machine-readable data: /api/v1/models/minimax-m3.json. Free reuse requires attribution to tkx.org.

About

Minimax-M3 is an AI model that specializes in decision-making and optimization tasks. It is served by multiple inference providers on AI model marketplaces, making it accessible for various applications that require strategic planning and risk management.

AI-generated summary from public information — is this yours?

FAQ

How much does MiniMax-M3 cost?

Cheapest measured offer right now: $0.23/1M input, $0.96/1M output via wandb — across 21 tracked providers, refreshed hourly.

Who serves MiniMax-M3?

21 providers currently serve it. The table above lists each with input/output price, TTFT, TPS, uptime and an evidence tier.

How heavily is MiniMax-M3 used?

MiniMax-M3 routed 219B tokens in the last 24h. The daily bars above show routed volume over recent days. Source: OpenRouter public rankings — one of the few routers publishing per-model usage; TKX refreshes hourly.

Related analysis

Back to rankings