RunsOnMy ModelsGPUs & MacsBy VRAMBest GPUCan I run…?OllamaStart hereAPI pricesVRAM calculatorNew

MiniMax: MiniMax M3 (batch) API pricing

$0.224 per 1M input tokens and $0.88 per 1M output tokens on OpenRouter. Context window: 524,288 tokens.

$0.224input / 1M tokens
$0.88output / 1M tokens
$0.0448cached input / 1M
512Kcontext
text+image+video->textmodality

This is the batch listing: requests are processed asynchronously rather than answered right away, at 25% less per input token and 27% less per output token than the standard MiniMax M3 price ($0.30 / $1.20).

What it costs in practice

WorkloadCost
Chatbot: 10,000 messages (1,500 in / 400 out tokens each)$6.88
RAG: 1,000 queries (8,000 in / 600 out each)$2.32
Summarize 100 long documents (50,000 in / 1,000 out each)$1.21

Cross-check against the provider's list price

No first-party entry for this model in LiteLLM's price map, so this price comes from OpenRouter only.

Price history

No price change recorded since we started tracking on Nov 17, 2026. We check every 6 hours and log every change.

Run it yourself instead

The open weights are on Hugging Face. See the VRAM MiniMax M3 needs and which GPUs fit it →

Cheaper alternatives with similar context

Text models with at least 125K context and a lower blended price (75% input, 25% output). Price only, not a quality ranking.

ModelInput / 1MOutput / 1MContext
Qwen: Qwen3 VL 8B Instruct$0.25$0.75256K
Venice: Uncensored$0.20$0.90125K
MiniMax: MiniMax M2.7$0.21$0.84192K
Qwen: Qwen3.5-35B-A3B$0.14$1.00256K
KT: Mi:dm K 3.0 Pro$0.20$0.80256K
Qwen: Qwen3 Next 80B A3B Instruct$0.10$1.10256K
OpenAI: GPT-4.1 Mini (batch)$0.20$0.801023K
TheDrummer: Cydonia 24B V4.1$0.30$0.50128K

Source: OpenRouter listing via the public models API. Prices checked Nov 18, 2026. Model ID minimax/minimax-m3:batch, listed May 31, 2026. Report an error.