Kimi K3
$0.239 per 1M input tokens and $11.94 per 1M output tokens · 1.05M context · vision, tools, reasoning, JSON, open weights.
Prices checked Oct 21, 2026 · tracked by LLM Cost Index since Oct 21, 2026
What Kimi K3 costs per month
Estimated monthly bill for typical workloads, using the cached-input price for repeated context. Try your own numbers in the cost calculator.
| Workload | Per month |
|---|---|
| Customer chatbot 1,000 conversations a day, 8 turns each | $1,082 |
| Document Q&A (RAG) 500 questions a day over retrieved documents | $111 |
| Coding / tool-using agent 200 tasks a day, long tool-heavy contexts | $365 |
| Content generation 30 long articles a day | $27.50 |
| Classification / extraction 100,000 short items a day | $752 |
Price history
We started tracking Kimi K3 on Oct 21, 2026; the chart appears as soon as there is a second data point. See all recent price changes.
Where to run Kimi K3: 28 providers
Wafer is the cheapest at $0.238 input / $24.00 output per 1M tokens. Uptime is the average over the last 30 days as reported by OpenRouter; see provider reliability.
| Provider | Input / 1M | Output / 1M | Context | Uptime | Notes |
|---|---|---|---|---|---|
| Wafer | $0.238 | $24.00 | 1.05M | 99.3% | mxfp4 |
| InferenceNet | $0.239 | $11.94 | 1.05M | 99.2% | fp4 |
| InferenceNet | $0.239 | $11.94 | 1.05M | 98.8% | fp4 |
| Relace | $0.30 | $12.00 | 1.05M | 100% | fp4 |
| Wafer | $0.36 | $11.90 | 1.05M | 99.3% | mxfp4 |
| Makora | $0.65 | $15.00 | 1.05M | 98.8% | fp4 |
| Morph | $0.814 | $14.90 | 1.05M | 98.7% | fp8 |
| AkashML | $1.20 | $14.00 | 1.05M | 98.4% | fp4 |
| Sail Research | $1.20 | $5.50 | 1.05M | 100% | fp4 |
| Sail Research | $1.20 | $5.50 | 1.05M | 100% | fp4 |
| Decart | $1.65 | $8.25 | 1.05M | 99.7% | mxfp4 |
| Chutes | $1.85 | $9.50 | 1.05M | 90.7% | mxfp4 |
| InferenceNet | $2.04 | $13.20 | 1.05M | 99.4% | priority tier, fp4 |
| InferenceNet | $2.24 | $14.52 | 1.05M | 99.1% | priority tier, fp4 |
| DigitalOcean | $2.55 | $12.95 | 1.05M | 98.9% | — |
| Phala | $2.55 | $12.75 | 1.05M | 99.9% | — |
| DeepInfra | $2.85 | $14.25 | 1.05M | 99.3% | mxfp4 |
| Amazon Bedrock | $3.00 | $15.00 | 1.05M | 73.5% | — |
| BaseTen | $3.00 | $15.00 | 1.05M | 94.1% | fp8 |
| Fireworks | $3.00 | $15.00 | 1.05M | 99.8% | — |
| Modal | $3.00 | $15.00 | 1.05M | 95% | mxfp4 |
| Moonshot AI | $3.00 | $15.00 | 1.05M | 100% | mxfp4 |
| Parasail | $3.00 | $15.00 | 1.05M | 93% | fp4 |
| Together | $3.00 | $15.00 | 1.05M | 99.7% | — |
| Alibaba | $3.45 | $17.25 | 1.05M | 100% | — |
| Fireworks | $4.50 | $22.50 | 1.05M | 98.4% | priority tier |
| Fireworks | $4.50 | $22.50 | 1.05M | 88.7% | — |
| Parasail | $4.50 | $22.50 | 1M | 99.3% | priority tier, fp4 |
Cheaper alternatives to Kimi K3
Models with the same tool calling, image input, structured output for at least 20% less (3:1 input/output mix), most capable first.
| Model | Input / 1M | Output / 1M | Context | Capabilities |
|---|---|---|---|---|
| Muse Spark 1.3 Meta | $1.25 | $4.25 | 1.05M | visiontoolsreasoningJSON |
| MiMo-V2.6-Pro Xiaomi | $0.435 | $0.87 | 1.05M | visionaudiotoolsreasoningJSONopen weights |
| Step 5 Preview Stepfun | $1.00 | $2.70 | 1.05M | visiontoolsreasoningJSONopen weights |
| Claude Haiku 5.5 Anthropic | $0.10 | $0.50 | 1M | visiontoolsreasoningJSON |
| GLM 5.3 Flash Z.ai | $0.041 | $0.12 | 1.05M | visiontoolsreasoningJSONopen weights |
How to pay less for Kimi K3
For a customer chatbot (1,000 conversations a day, 8 turns each) that costs $1,089 a month at list price without caching:
| Option | Per month | You save |
|---|---|---|
| Move to Muse Spark 1.3 (similar capabilities) | $569 | $519 (48%) |
| Route to Sail Research | $894 | $195 (18%) |
Other workloads: cut-your-bill tool for Kimi K3.
Compare Kimi K3
Specifications
| Model ID | moonshotai/kimi-k3 |
| Input | text, image, video |
| Output | text |
| Tool calling | Yes |
| Structured output | Yes |
| Reasoning mode | Yes |
| Open weights | Yes — moonshotai/Kimi-K3 |
| Released | Jul 16, 2026 |
FAQ
- How much does Kimi K3 cost?
- $0.239 per million input tokens and $11.94 per million output tokens; cached input costs $0.21 per million. Prices as of Oct 21, 2026.
- What is the context window of Kimi K3?
- 1.05M tokens, with up to 944K output tokens per response.
- Does Kimi K3 support images, tools and structured output?
- Images as input: yes. Tool calling: yes. Structured (JSON) output: yes. Reasoning mode: yes.
- What are cheaper alternatives to Kimi K3?
- Models with the same key capabilities for at least 20% less include Muse Spark 1.3 ($1.25 / $4.25), MiMo-V2.6-Pro ($0.435 / $0.87), Step 5 Preview ($1.00 / $2.70).
More from Moonshot AI: all Moonshot AI models · how we collect prices