Moonshot
Kimi K3
Released 2026-07-16
Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...
You send / 1M
$0.200
tokens in
It replies / 1M
$11.50
tokens out
Memory
1.05M
tokens it can read at once
Typical request
$0.0060
1,000 words in, 400 out
Data privacy
No training or retention: Yes. At least one provider serves it with zero data retention.
| Provider | You send / 1M | It replies / 1M | Uptime | Privacy policy |
|---|---|---|---|---|
| Decart · mxfp4 | $1.65 | $8.25 | 100% | Read |
| Fireworks | $2.10 | $10.50 | 96% | Read |
| Relace · fp4 | $0.170 | $10.56 | 100% | Read |
| InferenceNet · fp4 | $0.239 | $10.80 | 100% | Read |
| InferenceNet · fp4 | $0.239 | $10.80 | 100% | Read |
| Sail Research · fp4 | $0.230 | $11.00 | 100% | Read |
| Sail Research · fp4 | $0.230 | $11.00 | 100% | Read |
| Wafer · mxfp4 | $0.200 | $11.50 | 100% | Read |
| InferenceNet · fp4 | $0.500 | $11.88 | 100% | Read |
| InferenceNet · fp4 | $0.500 | $11.88 | 100% | Read |
| Wafer · mxfp4 | $0.360 | $11.90 | 100% | Read |
| Phala | $2.55 | $12.75 | 100% | Read |
| DigitalOcean | $2.55 | $12.95 | 100% | Read |
| AkashML · fp4 | $1.20 | $14.00 | 98% | Read |
| DeepInfra · mxfp4 | $2.85 | $14.25 | 100% | Read |
| ParetoAlpha | $3.00 | $15.00 | 97% | Read |
| Amazon Bedrock | $3.00 | $15.00 | 97% | Read |
| Makora · fp4 | $0.650 | $15.00 | 100% | n/a |
| Parasail · fp4 | $3.00 | $15.00 | 99% | Read |
| Modal · mxfp4 | $3.00 | $15.00 | 100% | Read |
| Together | $3.00 | $15.00 | 97% | Read |
| Fireworks | $3.00 | $15.00 | 100% | Read |
| BaseTen · fp8 | $3.00 | $15.00 | 100% | Read |
| Moonshot AI | $3.00 | $15.00 | 100% | Read |
| Morph · fp8 | $1.81 | $15.16 | 100% | Read |
| Wafer · mxfp4 | $0.500 | $22.00 | 100% | Read |
| Fireworks | $4.50 | $22.50 | 81% | Read |
| Fireworks | $4.50 | $22.50 | 99% | Read |
Based on OpenRouter and Vercel AI Gateway data. Confirm terms with the provider before sending sensitive data.
What it can do
- Reads: text, image, video
- Writes: text
- Reasoning: Yes
- Tool calling: Yes
- Longest reply: 944K tokens
- Repeated text is billed at $0.190 per 1M (prompt caching)
- Intelligence score: 43.6 / 100 (Artificial Analysis)
Similar models
- Qwen3.8 Max PrimeQwen · $4.00 in / $12.00 out per 1M
- GPT-5.6 Terra ProOpenAI · $2.00 in / $12.00 out per 1M
- GPT-5.6 TerraOpenAI · $2.00 in / $12.00 out per 1M
- Nano Banana Pro (Gemini 3 Pro Image)Google · $2.00 in / $12.00 out per 1M
- Gemini 3.1 Pro Preview Custom ToolsGoogle · $2.00 in / $12.00 out per 1M
- Gemini 3.1 Pro PreviewGoogle · $2.00 in / $12.00 out per 1M
Appears in
Top No-Training AI ModelsTop No-Training Zero Data Retention AI ModelsTop No-Training Zero Data Retention Vision AI ModelsTop No-Training Zero Data Retention Reasoning AI ModelsTop No-Training Zero Data Retention Tool-Calling AI ModelsTop No-Training Zero Data Retention Long-Context AI ModelsTop No-Training Vision AI ModelsTop No-Training Vision Reasoning AI Models