Moonshot AI
Kimi K3 — 1T MoE open-weight model, strong agentic and coding benchmark scores
Moonshot AI is a Chinese AI startup behind the Kimi model family. Kimi K3 is their latest 1-trillion-parameter MoE model, succeeding K2 with improved coding and agentic benchmark scores. Kimi K2.6 remains available as a stable production option. The Kimi API offers long-context processing up to 128K tokens with competitive pricing, and models are available via OpenRouter for global access.
Kimi K3 is a 1-trillion-parameter open-weight MoE model with strong coding and agentic benchmark scores — available for self-hosting or via the Moonshot API and OpenRouter.
- Kimi K3: 1T MoE open-weight model with strong coding and agentic benchmark scores
- Kimi K2.6 available as stable production option
- Competitive on agentic and tool-use benchmarks
- Long-context support up to 128K tokens
- Open-weight release enables self-hosting
- Available via OpenRouter for global access
- API primarily targets Chinese market — international latency may vary
- Smaller ecosystem than OpenAI or Anthropic
- Fewer third-party integrations available
Moonshot AI Models
| Model | Modality | Tier | Price | Cached /1M | TTFT | Throughput | Context | Intel. | Caps | |
|---|---|---|---|---|---|---|---|---|---|---|
moonshot-v1-8k Moonshot | Chat | efficient | $0.12/ $0.12 in / out per 1M EST Jul 2026 | — | 300ms | 200 t/s | 8K | 55 | ||
kimi-k1.5 Kimi K1.5 | Chat | advanced | $0.15/ $2.50 in / out per 1M EST Jul 2026 | — | 2.5s | 70 t/s | 131K | 78 | ||
moonshot-v1-32k Moonshot | Chat | efficient | $0.40/ $1.60 in / out per 1M EST Jul 2026 | — | 500ms | 150 t/s | 33K | 60 | ||
kimi-k2-0711-preview Kimi K2 | Chat | advanced | $0.60/ $2.50 in / out per 1M EST Jul 2026 | — | 800ms | 90 t/s | 131K | 80 | ||
kimi-k2.5 Kimi K2 | Chat | advanced | $0.60/ $3.00 in / out per 1M EST Jul 2026 | — | 700ms | 110 t/s | 262K | 85 | ||
kimi-k2-thinking Kimi K2 | Chat | advanced | $0.60/ $2.50 in / out per 1M EST Jul 2026 | — | 3.0s | 60 t/s | 262K | 86 | ||
moonshot-v1-128k Moonshot | Chat | advanced | $0.80/ $3.20 in / out per 1M EST Jul 2026 | — | 700ms | 110 t/s | 131K | 65 | ||
kimi-k2.7-code Kimi K2 | Chat | advanced | $0.90/ $3.75 in / out per 1M EST Jul 2026 | — | 600ms | 120 t/s | 262K | 87 | ||
kimi-k3 Kimi K3 | Chat | frontier | $2.00/ $8.00 in / out per 1M EST Jul 2026 | — | 900ms | 80 t/s | 1.0M | 91 |
Moonshot AI — Frequently Asked Questions (FAQs)
Similar Providers
Moonshot AI Reviews
All LLM Providers
Full comparison tableMoonshot AI LLM pricing overview
Moonshot AI is a proprietary AI lab that develops and hosts its own large language models. Moonshot AI is a Chinese AI startup behind the Kimi model family. Kimi K3 is their latest 1-trillion-parameter MoE model, succeeding K2 with improved coding and agentic benchmark scores. Kimi K2.6 remains available as a stable production option. The Kimi API offers long-context processing up to 128K tokens with competitive pricing, and models are available via OpenRouter for global access. Common use cases include Coding, Agents, Long-context, Reasoning. Headquartered in Beijing, China, founded 2023. 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.
Moonshot AI vs other LLM providers
Moonshot AI 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. Kimi K3 is a 1-trillion-parameter open-weight MoE model with strong coding and agentic benchmark scores — available for self-hosting or via the Moonshot API and OpenRouter. Use the LLM provider comparison tool to see Moonshot AI 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 Moonshot AI?
Moonshot AI stands out because: Kimi K3 is a 1-trillion-parameter open-weight MoE model with strong coding and agentic benchmark scores — available for self-hosting or via the Moonshot API and OpenRouter.. The API currently offers 9 models, spanning 1 frontier, 6 advanced, 2 efficient tiers. 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 Moonshot AI token pricing
Moonshot AI 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. The cheapest {meta.name} input rate is currently $0.12/1M tokens. Prices shown are sourced from Moonshot AI's public pricing page and updated every 15 minutes. 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.
Moonshot AI 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. Moonshot AI's largest context window is 1.0M tokens. 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 Moonshot AI makes sense
Managed inference APIs like Moonshot AI 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 Moonshot AI 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 Moonshot AI token price data is available in the LLM price history charts.
Compare Moonshot AI With Another LLM Provider
Compare Moonshot AI vs other providers
Side-by-side token pricing, latency, throughput, and context window. View all LLM provider comparisons →
Looking for alternatives?
Compare Moonshot AI with other LLM API providers side by side.