Loading...
Loading...
Coder‑Large is a 32 B‑parameter offspring of Qwen 2.5‑Instruct that has been further trained on permissively‑licensed GitHub, CodeSearchNet and synthetic bug‑fix corpora. It supports a 32k context window, enabling multi‑file refactoring or long diff review in a single call, and understands 30‑plus programming languages with special attention to TypeScript, Go and Terraform. Internal benchmarks show 5–8 pt gains over CodeLlama‑34 B‑Python on HumanEval and competitive BugFix scores thanks to a reinforcement pass that rewards compilable output. The model emits structured explanations alongside code blocks by default, making it suitable for educational tooling as well as production copilot scenarios. Cost‑wise, Together AI prices it well below proprietary incumbents, so teams can scale interactive coding without runaway spend.
Preço/1M
$0.57
402nd mais barato
85% acima da mediana
Top 59%
Janela de Contexto
33K
291st maior
Top 91%
Entrada
$0.50
por 1M tokens
Saída
$0.80
por 1M tokens
Combinado
$0.57
por 1M tokens
Mais barato que 41% dos modelos. Preço mediano é $0.31/1M tokens.
Diário
$0.57
Mensal
$17.25
Janela de Contexto
33K
tokens
Maior que 9% dos modelos
Comparação de Janela de Contexto