kimi-k2.6 vs kimi-k2.7-code
Side-by-side comparison of kimi-k2.6 and kimi-k2.7-code: benchmarks, pricing, context window and capabilities. Both are accessible through Requesty's unified API. kimi-k2.6 outperforms kimi-k2.7-code on 6 of 7 shared benchmarks.
kimi-k2.6
Input / 1M
$0.95
Output / 1M
$4.00
Context
262K
Model ID
moonshot/kimi-k2.6
kimi-k2.7-code
Input / 1M
$0.95
Output / 1M
$4.00
Context
262K
Model ID
moonshot/kimi-k2.7-code
Benchmark comparison
Intelligence Indexreasoning
kimi-k2.644.2%
kimi-k2.7-code41.9%
Coding Indexcoding
kimi-k2.661.8%
kimi-k2.7-code60.8%
GPQA Diamondreasoning
kimi-k2.691.1%
kimi-k2.7-code89.6%
Terminal-Bench Hardagentic
kimi-k2.643.9%
kimi-k2.7-code44.7%
τ²-Benchagentic
kimi-k2.695.9%
kimi-k2.7-code90.1%
SciCodecoding
kimi-k2.653.5%
kimi-k2.7-code47.5%
Humanity's Last Examreasoning
kimi-k2.635.9%
kimi-k2.7-code32.8%
Scores sourced from official model cards, Artificial Analysis, and public leaderboards. Benchmarks measure specific skills and don't capture every aspect of model quality.
Pricing & specifications
| kimi-k2.6 | kimi-k2.7-code | |
|---|---|---|
| Input price / 1M | $0.95 | $0.95 |
| Output price / 1M | $4.00 | $4.00 |
| Context window | 262K tokens | 262K tokens |
| Max output | 262K tokens | 262K tokens |
| Vision input | Yes | Yes |
| Tool calling | Yes | Yes |
| Reasoning | Yes | Yes |
| Prompt caching | Yes | Yes |
| Computer use | N/A | N/A |
| Provider | Moonshot AI | Moonshot AI |
Questions people ask
Is kimi-k2.6 better than kimi-k2.7-code?
kimi-k2.6 outperforms kimi-k2.7-code on 6 of 7 shared benchmarks. See the benchmark comparison above for specifics: kimi-k2.6 and kimi-k2.7-code have different strengths across reasoning, coding, math and multimodal tasks.
Which is cheaper, kimi-k2.6 or kimi-k2.7-code?
kimi-k2.6 and kimi-k2.7-code have identical combined pricing.
Can I use kimi-k2.6 and kimi-k2.7-code through the same API?
Yes. Requesty provides a single OpenAI-compatible API that routes to both. Change just the "model" parameter to switch between "moonshot/kimi-k2.6" and "moonshot/kimi-k2.7-code", no other code changes needed.
What are the context windows?
kimi-k2.6 supports up to 262K tokens of context. kimi-k2.7-code supports up to 262K tokens. Longer context means you can feed larger documents or codebases in a single prompt, though quality often degrades past 128K for most models.
Switch between kimi-k2.6 and kimi-k2.7-code with one line of code
Requesty provides a single OpenAI-compatible API for 400+ models. Change the model parameter, not your code.