MiniMax
Long-context frontier models with 1M token windows
MiniMax is a Chinese AI company offering the MiniMax M-series of large language models. MiniMax M2.7 and M1 support context windows up to 1M tokens and are designed for enterprise chat, long-document analysis, and agentic workflows.
MiniMax M1 supports a 1M token context window at $0.30/1M input tokens — one of the most cost-effective long-context models available.
- 1M token context window
- Competitive pricing
- Strong multilingual performance
- Smaller international developer community
- Less third-party tooling than OpenAI
All Models
MiniMax — Frequently Asked Questions
Community Reviews
All LLM Providers
Full comparison tableMiniMax LLM pricing overview
MiniMax is a proprietary AI lab that develops and hosts its own large language models. MiniMax is a Chinese AI company offering the MiniMax M-series of large language models. MiniMax M2.7 and M1 support context windows up to 1M tokens and are designed for enterprise chat, long-document analysis, and agentic workflows. Common use cases include Chat, Long-document analysis, Agentic workflows, Enterprise AI. Headquartered in Shanghai, China, founded 2021. All models are accessible via a REST API compatible with standard OpenAI-style request formats, enabling drop-in integration with most LLM frameworks and orchestration tools.
MiniMax vs other LLM providers
MiniMax competes with OpenAI, Anthropic, Google, Groq, Together AI, Mistral, Cohere, and other inference API providers across dimensions of price, throughput, latency, context window, and model intelligence. MiniMax M1 supports a 1M token context window at $0.30/1M input tokens — one of the most cost-effective long-context models available. Use the LLM provider comparison tool to see MiniMax token pricing, latency, and throughput side-by-side with any other provider. The full LLM pricing table shows all providers ranked by input token cost, output token cost, and throughput in a single sortable view.
Why choose MiniMax?
MiniMax's key strengths are: 1M token context window; Competitive pricing; Strong multilingual performance. Limitations to consider: Smaller international developer community; Less third-party tooling than OpenAI. For teams running high-volume inference workloads, prompt caching and batch API endpoints can reduce effective input token costs by 50–90% — check the context window cost guide for a full breakdown of caching economics.
Understanding MiniMax token pricing
MiniMax charges separately for input (prompt) and output (completion) tokens, priced per 1M tokens in USD. Output tokens are typically 3–5× more expensive than input tokens due to the compute cost of autoregressive generation. Prices shown are sourced from MiniMax's public pricing page and updated daily. Need help estimating your spend? Read the LLM API cost calculator guide — it covers tokens, context windows, prompt caching, and batch discounts with worked examples for RAG, chat history, and document processing workloads.
MiniMax context window and model capabilities
Context window size directly affects both capability and cost — every token in the context window is charged as an input token. For RAG and document processing workloads, longer context windows enable richer retrieval but increase per-call costs proportionally. Prompt caching — where supported — stores the KV state of repeated prefixes and charges 75–90% less for cache hits, making it the most impactful cost optimization for applications with consistent system prompts or retrieved documents. See the LLM context window cost guide for a full analysis of how context length affects your API bill.
Self-hosted vs managed inference: when MiniMax makes sense
Managed inference APIs like MiniMax eliminate infrastructure overhead — no GPU provisioning, driver management, or model serving stack to maintain. The trade-off is cost at scale: a single H100 at ~$2.50/hr can serve ~500K tokens/min of Llama 3.3 70B, which at MiniMax API rates would cost significantly more per token. The break-even point depends on your request volume, latency requirements, and engineering capacity. For teams processing fewer than ~10M tokens/day, managed APIs are almost always cheaper when total cost of ownership is considered. Above that threshold, self-hosted inference on rented GPU compute typically wins on unit economics. Read the cheapest GPU cloud guide for a full break-even analysis. Historical MiniMax token price data is available in the LLM price history charts.