Compare AI models

Specifications
Parameters
1T7B
Context window
256k64k
API pricing
Cheapest input
$0.60Novita—
Cheapest output
$2.50Novita—
$245Novita · bf16—
These models have no shared benchmark scores.
Overview
CompanyMoonshot AIQwen
Release dateNov 6 2025Apr 16 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Kimi K2 Thinking and CodeQwen1.5 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. CodeQwen1.5 shipped 569 days before Kimi K2 Thinking, so benchmark comparisons should account for the intervening progress.

Kimi K2 Thinking has 1T parameters, while CodeQwen1.5 has 7B. Context windows are 256k (Kimi K2 Thinking) vs 64k (CodeQwen1.5).

Direct benchmark comparisons are unavailable — Kimi K2 Thinking and CodeQwen1.5 don't publish scores on any of the same benchmarks.