Kimi K3
by MoonshotAI · 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...
- Input / 1M tokens
- $0.192
- Output / 1M tokens
- $15.00
- Context
- 1.05M
Specs
| Input price | $0.192 / 1M tokens |
|---|---|
| Output price | $15.00 / 1M tokens |
| Cached input | $0.182 / 1M tokens |
| Context window | 1.05M tokens |
| Max output | 944K tokens |
| Reads | text, image, video |
| Writes | text |
| Tool calling | Yes |
| Reasoning | Yes |
| Listed | Jul 16, 2026 |
List prices in USD, updated Oct 30, 2026. Providers may charge differently.
Providers
30 providers serve this model, as of Oct 30, 2026, 18:12 UTC.
| Provider | Quantization | Context | Max output | Input / 1M | Output / 1M | Cache read / 1M | Uptime (30 min) | Latency (median) | Throughput (median) | Supports | Status |
|---|---|---|---|---|---|---|---|---|---|---|---|
| InferenceNet | fp4 | 1.05M | 944K | $0.234 | $6.97 | $0.195 | 100% | 788 ms | 72 tok/s | Normal | |
| InferenceNet | fp4 | 1.05M | 944K | $0.234 | $6.97 | $0.195 | 100% | 882 ms | 46 tok/s | Normal | |
| Relace | fp4 | 1.05M | 944K | $0.153 | $9.75 | $0.15 | 100% | 6.04 s | 21 tok/s | Normal | |
| Wafer | mxfp4 | 1.05M | 944K | $0.276 | $9.94 | $0.13 | 100% | 670 ms | 64 tok/s | Normal | |
| Sail Research | fp4 | 1.05M | 944K | $0.23 | $11.00 | $0.115 | 100% | 1.08 s | 55 tok/s | Normal | |
| Sail Research | fp4 | 1.05M | 944K | $0.23 | $11.00 | $0.115 | 100% | 1.55 s | 58 tok/s | Normal | |
| Chutes | mxfp4 | 1.05M | 65.5K | $1.85 | $9.50 | $0.185 | — | 3.47 s | 17 tok/s | Normal | |
| Decart | mxfp4 | 1.05M | 944K | $1.95 | $9.75 | $0.195 | 100% | 5.89 s | 37 tok/s | Normal | |
| InferenceNet | fp4 | 1.05M | 944K | $0.50 | $11.88 | $0.35 | 100% | 978 ms | 58 tok/s | Normal | |
| InferenceNet | fp4 | 1.05M | 944K | $0.50 | $11.88 | $0.35 | 100% | 900 ms | 59 tok/s | Normal | |
| Fireworks | — | 1.05M | 944K | $2.10 | $10.50 | $0.21 | 100% | 1.15 s | 55 tok/s | Normal | |
| Makora | fp4 | 1.05M | 944K | $0.50 | $13.00 | $0.20 | 100% | 1.18 s | 53 tok/s | Normal | |
| Wafer | mxfp4 | 1.05M | 944K | $0.192 | $15.00 | $0.182 | 100% | 803 ms | 60 tok/s | Normal | |
| AkashML | fp4 | 1.05M | 944K | $1.20 | $14.00 | $1.20 | — | 658 ms | 141 tok/s | Normal | |
| Phala | — | 1.05M | 944K | $2.55 | $12.75 | $0.255 | — | 6.13 s | 42 tok/s | Normal | |
| DigitalOcean | — | 1.05M | 944K | $2.55 | $12.95 | $0.255 | 100% | 1.81 s | 19 tok/s | Normal | |
| Morph | fp8 | 1.05M | 944K | $1.28 | $14.63 | $0.36 | 100% | 2.21 s | 37 tok/s | Normal | |
| DeepInfra | mxfp4 | 1.05M | 944K | $2.85 | $14.25 | $0.285 | 96.7% | 884 ms | 61 tok/s | Normal | |
| Amazon Bedrock | — | 1.05M | 128K | $3.00 | $15.00 | $0.30 | 100% | 3.13 s | 37 tok/s | Normal | |
| BaseTen | fp8 | 1.05M | 262K | $3.00 | $15.00 | $0.30 | 100% | 1.21 s | 48 tok/s | Normal | |
| Fireworks | — | 1.05M | 944K | $3.00 | $15.00 | $0.30 | 100% | 3.61 s | 62 tok/s | Normal | |
| Modal | mxfp4 | 1.05M | 944K | $3.00 | $15.00 | $0.30 | 100% | 2.05 s | 40 tok/s | Normal | |
| Moonshot AI | — | 1.05M | 944K | $3.00 | $15.00 | $0.30 | 100% | 7.15 s | 26 tok/s | Normal | |
| Parasail | fp4 | 1.05M | 944K | $3.00 | $15.00 | $0.30 | 100% | 1.13 s | 88 tok/s | Normal | |
| ParetoAlpha | — | 1.05M | 944K | $3.00 | $15.00 | $0.30 | — | 11.78 s | 15 tok/s | Normal | |
| Together | — | 1.05M | 944K | $3.00 | $15.00 | $0.30 | 100% | 1.02 s | 50 tok/s | Normal | |
| Alibaba | — | 1.05M | 131K | $3.45 | $17.25 | $0.345 | 100% | 2.15 s | 32 tok/s | Normal | |
| Wafer | mxfp4 | 1.05M | 944K | $0.161 | $22.00 | $0.16 | 100% | 701 ms | 63 tok/s | Normal | |
| Fireworks | — | 1.05M | 944K | $4.50 | $22.50 | $0.45 | — | 712 ms | 44 tok/s | Normal | |
| Fireworks | — | 1.05M | 944K | $4.50 | $22.50 | $0.45 | 100% | 1.13 s | 68 tok/s | Normal |
"Cheapest" is the lowest input plus output price; "Fastest" the highest median throughput. Columns empty for every provider are not shown.
Usage
#23
by tokens, Oct 29, 2026
273B
tokens that day · 7 days −4%
Data as of 2026-10-30T18:12:03.879Z.All rankings
Related models
- MoonshotAI
Kimi K3.1 Pro
- Input
- $2.00
- Output
- $10.00
- Context
- 1.05M
- MoonshotAI
Kimi K3 (batch)
- Input
- $2.28
- Output
- $11.40
- Context
- 1.05M
- MoonshotAI
Kimi K2.7 Code
- Input
- $0.60
- Output
- $3.50
- Context
- 262K
- MoonshotAI
Kimi K2.6
- Input
- $0.65
- Output
- $3.41
- Context
- 262K
- MoonshotAI
Kimi K2.5
- Input
- $0.50
- Output
- $2.50
- Context
- 262K
- MoonshotAI
Kimi K2 Thinking
- Input
- $0.60
- Output
- $2.50
- Context
- 262K