K
Kimi K3
Scores reviewed 2026-07-18Prices checked 2026-11-09Moonshot AI
- OpenRouter
- moonshotai/kimi-k3
- Context
- 1.05M
- Price per 1M
- $3 in / $15 out
- Tooling
- 5/5
- Deploy
- Cloud API
Monthly cost, worked example
| Input | 667,000 tokens × $3 per 1M | $2 |
|---|---|---|
| Output | 333,500 tokens × $15 per 1M | $5 |
| Total | ~$7/mo |
667 requests a month at 1,000 input and 500 output tokens each, about 1M tokens. The recommender uses the same assumption when you don't give your own usage.
Best for
- Agentic workflows and tool calling
- Writing and editing code
- Complex reasoning and analysis
- Long documents (~1.05M context)
Skip if
- You need rock-bottom per-token cost
Capability scores
Tool calling5/5
Tooling (1-5): how reliably the model calls tools and follows multi-step instructions. Editorial score from LMFinder, not a benchmark.
Multi-step reasoning5/5
Specifications
- Context window
- 1.05M tokens
- VRAM
- N/A (cloud-hosted)
- License
- modified-mit
- Pricing
- $3 in / $15 out per 1M
- Deployment
- Cloud API
- Docs
- Model docs ↗
Our take
Kimi K3 from Moonshot AI offers a 1.05M-token context window and is well-suited to strong tool calling, multi-step reasoning, coding, long-context work. Pricing is $3 in / $15 out per 1M, billed per token through the provider API.
Watch for the trade-offs: output pricing is on the higher side.
Compare to
Not sure this is the one?
Describe your project and let LMFinder rank the field for your exact constraints.
Describe your project →