Side by side

See the difference.

Scores, capabilities and costs for the models you’re considering.

Comparison of Qwen: Qwen3 Coder Next
1 modelqwenQwen: Qwen3 Coder NextRemove ×
What’s differentQwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per...
DateFeb 4, 2026Listed
Listed rate$0.12 in / $0.80 out/ 1M tokensParasail · via OpenRouter · all routes ↗parasail/bf16 · quantization=bf16
Provider endpoints2 endpoints →
Context window262.1K
Max output235.9K
Parameters—
Tool callingSupported
Structured outputSupported
Prompt cachingSupported
Open weightsSupported

Add another model

Search all models →