Kimi K2.7 Code
DeprecatedKimi K2.7 Code is Moonshot AI (Kimi)'s language model with a 262K context window and up to 236K output tokens, available from 16 providers, starting at $0.68 / 1M input and $3.21 / 1M output. A code-specialized variant of the Kimi K2 series, designed for programming tasks and software development workflows.
| Specifications | |
|---|---|
moonshot-kimi-k2-7-code | |
| Language | |
| Deprecated | |
| Moonshot AI (Kimi) | |
| 262K tokens | |
| 236K tokens | |
| ImagePDFTextVideo | |
| Text | |
| default | |
| 1.03T | |
| 1,354 | |
| 675,289 | |
| 1,567,092 | |
| · 3 months ago | |
| Benchmarks | |
|---|---|
| Intelligence Index | #102 |
| Coding Index | #41 |
| GPQA | #51 |
| HLE | #57 |
| IFBench | #107 |
| Time to First Token | #513 |
| SciCode | #66 |
| LCR | #44 |
| TerminalBench Hard | #26 |
| TAU2 | #66 |
| Output TPS | #180 |
Capabilities
Input4/5
Text✓
Image✓
Audio·
Video✓
PDF✓
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities7/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling✓
Structured Outputs✓
Native JSON Schema✓
Web Search✓
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching✓
Assistant Prefill·
Pricing by Provider
US Dollar ($)
Per 1M tokens
| Provider | Standard | Fast | Batch | |||||
|---|---|---|---|---|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Cache Read $ / 1M | Input $ / 1M | Output $ / 1M | Cache Read $ / 1M | Input $ / 1M | Output $ / 1M | |
| $0.894 | $3.71 | $0.19 | — | — | — | $0.447 | $1.86 | |
| $0.95 | $4.00 | $0.21 | — | — | — | — | — | |
| $0.95 | $4.00 | $0.19 | — | — | — | — | — | |
| $0.68 | $3.40 | $0.136 | — | — | — | — | — | |
| $0.95 | $4.00 | $0.19 | $1.43 | $6.00 | $0.285 | — | — | |
| $0.95 | $4.00 | N/A | — | — | — | — | — | |
| $0.95 | $4.00 | $0.19 | — | — | — | — | — | |
| $0.95 | $4.00 | N/A | — | — | — | — | — | |
| $0.95 | $4.00 | $0.19 | — | — | — | — | — | |
| $0.706 | $3.21 | $0.18 | — | — | — | — | — | |
| $0.95 | $4.00 | $0.19 | — | — | — | — | — | |
| $0.95 | $4.00 | $0.19 | — | — | — | — | — | |
| $0.95 | $4.00 | $0.19 | — | — | — | — | — | |
| $0.95 | $4.00 | $0.19 | — | — | — | — | — | |
| $0.95 | $4.00 | $0.16 | — | — | — | — | — | |
| $0.71 | $3.50 | $0.15 | — | — | — | — | — | |
Cost Calculator
US Dollar ($)
Preset:
Cheapest Instances to Run It
Cloud GPU instances that can host Kimi K2.7 Code, ranked by cheapest on-demand price. The model needs about 2465 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.
All clouds
FP16 (full precision)
US Dollar ($)
No GPU instances fit Kimi K2.7 Code at FP16 precision — try a lower precision such as INT4.
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Kimi K3 | 1.0M | $2.83 | $14.13 | Available | |
| Kimi K3 Batch | — | 1.0M | $3.00 | $15.00 | Available |
| Kimi K3 Coding | — | 1.0M | $0.440 | $1.61 | Available |
| Kimi K3 Fast | — | 1.0M | $4.50 | $22.50 | Available |
| Kimi K3 US | — | 1.0M | $3.30 | $16.50 | Available |
| Kimi K2.7 Code HighSpeed | 262K | $1.90 | $8.00 | Available | |
| Kimi K2.7 Code | 262K | $0.680 | $3.21 | Current | |
| Kimi K2 Thinking Turbo | 262K | $1.15 | $8.00 | Deprecated | |
| Kimi K2 Turbo | 256K | — | — | Available | |
| Kimi K2.5 Non-Reasoning | — | — | — | — | Available |
| Kimi K2 Instruct V0 | — | — | — | — | Available |