Kimi K2.7 CodevsGPT-4o

Kimi K2.7 Code
GPT-4o
Specifications
Parameters
1T
Context window
256k128k
API pricing
Input price
$0.95$2.50
Output price
$4.00$10.00
Cached input price
$0.19$1.25
Cheapest input
$0.68DeepInfra$2.50Azure
Cheapest output
$3.00StreamLake$10.00Azure
Benchmarks
BullshitBench v2
12%
DeepSWE 1.1
31%
Next.js Evals
74%
GPQA Diamond
49.9%
Overview
CompanyMoonshot AIOpenAI
Release dateJun 12 2026May 13 2024
AccessOpen WeightProprietary

Other comparisons

Kimi K2.7 CodevsClaude Fable 5.1GPT-4ovsClaude Fable 5.1Kimi K2.7 CodevsGemini 3.8 FlashGPT-4ovsGemini 3.8 FlashKimi K2.7 CodevsMuse Spark 1.3GPT-4ovsMuse Spark 1.3Kimi K2.7 CodevsGrok 4.6GPT-4ovsGrok 4.6Kimi K2.7 CodevsDeepSeek-V4.1-FlashGPT-4ovsDeepSeek-V4.1-FlashKimi K2.7 CodevsMistral Medium 3.5GPT-4ovsMistral Medium 3.5

Frequently asked questions

Kimi K2.7 Code and GPT-4o don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Kimi K2.7 Code is cheaper on both input and output: $0.95 vs $2.50 per million input tokens, and $4.00 vs $10.00 per million output tokens. GPT-4o shipped 760 days before Kimi K2.7 Code, so benchmark comparisons should account for the intervening progress.

Context windows are 256k (Kimi K2.7 Code) vs 128k (GPT-4o). Kimi K2.7 Code is open weight, while GPT-4o is proprietary.

Direct benchmark comparisons are unavailable — Kimi K2.7 Code and GPT-4o don't publish scores on any of the same benchmarks.