Kimi K2.6
by MoonshotAI · moonshotai/kimi-k2.6
Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...
- Input / 1M tokens
- $0.65
- Output / 1M tokens
- $3.41
- Context
- 262K
Specs
| Input price | $0.65 / 1M tokens |
|---|---|
| Output price | $3.41 / 1M tokens |
| Cached input | $0.15 / 1M tokens |
| Context window | 262K tokens |
| Max output | 236K tokens |
| Reads | text, image |
| Writes | text |
| Tool calling | Yes |
| Reasoning | Yes |
| Listed | Apr 20, 2026 |
List prices in USD, updated Oct 30, 2026. Providers may charge differently.
Providers
17 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 |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Chutes | int4 | 262K | 65.5K | $0.39 | $1.80 | $0.039 | 100% | 2.97 s | 29 tok/s | Normal | |
| DigitalOcean | — | 262K | 236K | $0.57 | $2.40 | $0.114 | 100% | 2.05 s | 34 tok/s | Normal | |
| StreamLake | fp8 | 256K | 230K | $0.599 | $2.52 | $0.101 | 100% | 1.32 s | 38 tok/s | Normal | |
| CoreWeave | fp4 | 262K | 236K | $0.65 | $3.41 | $0.15 | 83.3% | 529 ms | 68 tok/s | Code -2 | |
| SiliconFlow | fp8 | 262K | 236K | $0.77 | $3.40 | $0.14 | 100% | 1.72 s | 24 tok/s | Normal | |
| Inceptron | int4 | 262K | 236K | $0.682 | $3.50 | $0.137 | 100% | 633 ms | 61 tok/s | Normal | |
| Crusoe | bf16 | 262K | 236K | $0.70 | $3.50 | $0.35 | 96.7% | 362 ms | 59 tok/s | Normal | |
| Novita | — | 262K | 236K | $0.80 | $3.40 | $0.16 | 100% | 4.78 s | 24 tok/s | Normal | |
| DeepInfra | fp4 | 262K | 16.4K | $0.75 | $3.50 | $0.15 | 100% | 934 ms | 74 tok/s | Normal | |
| Parasail | int4 | 262K | 236K | $0.75 | $3.50 | $0.16 | 100% | 706 ms | 55 tok/s | Normal | |
| Venice | int4 | 256K | 65.5K | $0.75 | $3.50 | $0.16 | 77.8% | 907 ms | 61 tok/s | Code -5 | |
| GMICloud | fp8 | 262K | 236K | $0.855 | $3.60 | $0.144 | 0% | — | — | Code -5 | |
| AtlasCloud | int4 | 262K | 236K | $0.95 | $4.00 | $0.16 | 100% | 2.28 s | 35 tok/s | Normal | |
| Baidu | fp4 | 262K | 236K | $0.95 | $4.00 | $0.16 | 100% | 763 ms | 82 tok/s | Normal | |
| Cloudflare | — | 262K | 236K | $0.95 | $4.00 | $0.16 | 100% | 777 ms | 25 tok/s | Normal | |
| Moonshot AI | — | 262K | 236K | $0.95 | $4.00 | $0.16 | 100% | 1.30 s | 33 tok/s | Code -2 | |
| Phala | — | 262K | 236K | $1.09 | $4.60 | $0.37 | — | 1.35 s | 33 tok/s | Code -2 |
"Cheapest" is the lowest input plus output price; "Fastest" the highest median throughput. Columns empty for every provider are not shown.
Related models
- MoonshotAI
Kimi K3.1 Pro
- Input
- $2.00
- Output
- $10.00
- Context
- 1.05M
- MoonshotAI
Kimi K3
- Input
- $0.192
- Output
- $15.00
- 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 K2.5
- Input
- $0.50
- Output
- $2.50
- Context
- 262K
- MoonshotAI
Kimi K2 Thinking
- Input
- $0.60
- Output
- $2.50
- Context
- 262K