Access 1 agentica-org model through the OpenRouter unified API including Deepcoder 14B Preview. Compare pricing, context windows, benchmarks, and capabilities between different agentica-org models.
agentica-org tokens processed on OpenRouter
DeepCoder-14B-Preview is a 14B parameter code generation model fine-tuned from DeepSeek-R1-Distill-Qwen-14B using reinforcement learning with GRPO+ and iterative context lengthening. It is optimized for long-context program synthesis and achieves strong performance across coding benchmarks, including 60.6% on LiveCodeBench v5, competitive with models like o3-Mini