Kimi K3
moonshotai/kimi-k3
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...
Modalities
Text
Image
Video
In / Out price
$3.00 / $15.00 per 1M
Context
1.05M · 944K out
Released
Jul 16, 2026
Providers
Live list prices and uptime across 20 providers serving this model.
| Provider | Input /M | Output /M | Cache read /M | Context | Max output | Uptime 24h |
|---|---|---|---|---|---|---|
| Relacefp4 | $1.70 | $8.50 | $0.17 | 1.05M | 944K | 99.08% |
| Morph | $2.05 | $11.48 | $0.238 | 1.05M | 944K | 99.39% |
| Phala | $2.07 | $10.35 | $0.207 | 1.05M | 944K | 92.28% |
| InferenceNetfp4 | $2.10 | $10.95 | $0.23 | 1.05M | 944K | 98.94% |
| Wafer | $2.10 | $10.95 | $0.21 | 1.05M | 944K | 99.89% |
| Sail Researchfp4 | $2.144 | $10.758 | $0.244 | 1.05M | 944K | 99.73% |
| Makora | $2.55 | $12.75 | $0.256 | 1.05M | 944K | 96.57% |
| DigitalOcean | $2.55 | $12.95 | $0.255 | 1.05M | 944K | 99.57% |
| DeepInfrabf16 | $2.85 | $14.25 | $0.285 | 1.05M | 16K | 95.52% |
| Chutesmxfp4 | $3.00 | $15.00 | $0.30 | 1.05M | 66K | 98.03% |
| Parasailfp4 | $3.00 | $15.00 | $0.30 | 1.05M | 944K | 97.82% |
| Modalmxfp4 | $3.00 | $15.00 | $0.30 | 1.05M | 944K | 99.37% |
| Together | $3.00 | $15.00 | $0.30 | 1.05M | 944K | 99.75% |
| Fireworks | $3.00 | $15.00 | $0.30 | 1.05M | 944K | 99.64% |
| BaseTenfp8 | $3.00 | $15.00 | $0.30 | 1.05M | 262K | 99.85% |
| Moonshot AImxfp4 | $3.00 | $15.00 | $0.30 | 1.05M | 944K | 99.93% |
| Fireworks | $3.30 | $16.50 | $0.33 | 1.05M | 944K | 99.39% |
| Alibaba | $3.45 | $17.25 | $0.345 | 1.05M | 944K | 98.79% |
| Fireworks | $4.50 | $22.50 | $0.45 | 1.05M | 944K | 99.83% |
| Morph | $6.00 | $22.50 | $0.60 | 1.05M | 944K | 98.64% |
No implicit prompt caching; cache reads require explicit cache control.
Capabilities
Tool calling
Reasoning
Frequency penalty
Include reasoning
Logit bias
Logprobs
Max tokens
Min p
Presence penalty
Reasoning effort
Repetition penalty
Response format
Seed
Stop
Structured outputs
Temperature
Tool choice
Top K
Top logprobs
Top P
Pricing detail
- Input
- $3.00
- Output
- $15.00
- Cache read
- $0.30
- Cache write
- —
USD per 1M tokens.