Compare
Kimi K2.7 Code (batch) vs Kimi K3
Kimi K2.7 Code (batch) (MoonshotAI) and Kimi K3 (Moonshot) compared on benchmarks, pricing, context window, and use-case rankings.
- Kimi K2.7 Code (batch) is cheaper on input tokens — $0.95 vs $2.80 per 1M.
- Kimi K3 has a larger context window (1M vs 262K tokens).
| Attribute | Kimi K2.7 Code (batch) | Kimi K3 |
|---|---|---|
| Scores | ||
| Intelligence (ECI) | — | 157 |
| Coding | — | 99 |
| Math | — | 81 |
| Reasoning & Knowledge | — | 78 |
| Agentic & Tools | — | 84 |
| Specifications | ||
| Developer | MoonshotAI | Moonshot |
| Family | Kimi | Kimi |
| Released | Jun 12, 2026 | Jul 16, 2026 |
| Parameters | — | 2.8T |
| Availability | — | Open weights (non-commercial) |
| Context window | 262K | 1M |
| Price — $/M input | $0.95 | $2.80 |
| Price — $/M output | $4.00 | $14.00 |
| Inputs | text, image | text, image, video |
| Outputs | text | text |
| Benchmarks | ||
| AIME 2024/2025 | — | 97% |
| APEX | — | 39% |
| ARC-AGI | — | 95% |
| ARC-AGI-2 | — | 60% |
| GPQA Diamond | — | 93% |
| Humanity's Last Exam | — | 47% |
| SciCode | — | 59% |
| SimpleQA Verified | — | 43% |
| WebDev Arena | — | 1682 |
| WeirdML | — | 83% |
Use-case scores are 0–100 percentile composites across each area’s benchmarks, ranked against every model from the past year. Highlighted cells lead each row. Open a model for the full picture.
Frequently asked questions
Which is cheaper, Kimi K2.7 Code (batch) or Kimi K3?
Kimi K2.7 Code (batch) is cheaper on input tokens at $0.95 per million, versus $2.80 (representative OpenRouter pricing).
Which has a larger context window, Kimi K2.7 Code (batch) or Kimi K3?
Kimi K3 supports up to 1M tokens, compared with 262K for the other.
Want a different match-up? Open the compare tool to add or swap models.
More comparisons
Benchmarks & model data from Epoch AI (CC BY); pricing & specs from OpenRouter. ECI = Epoch Capabilities Index.