Compare AI models

Specifications
Parameters
—30B/480B
Context window
1M256k
API pricing
Cheapest input
—$0.30DeepInfra
Cheapest output
—$1.00DeepInfra
—$110DeepInfra · turbo · fp4
These models have no shared benchmark scores.
Overview
CompanyQwenQwen
Release dateNov 15 2024Jul 22 2025
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen2.5-Turbo (1M) and Qwen3-Coder don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Qwen2.5-Turbo (1M) shipped 249 days before Qwen3-Coder, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (Qwen2.5-Turbo (1M)) vs 256k (Qwen3-Coder). Qwen2.5-Turbo (1M) is closed, while Qwen3-Coder is open weight.

Direct benchmark comparisons are unavailable — Qwen2.5-Turbo (1M) and Qwen3-Coder don't publish scores on any of the same benchmarks.