AI Model Catalogue

DeepSeekMath-Instruct 7B is a mathematically instructed tuning model derived from DeepSeekMath-Base 7B. DeepSeekMath is initialized with DeepSeek-Coder-v1.5 7B and continues pre-training on math-related tokens sourced from Common Crawl, together with natural language and code data for 500B tokens.

Qwen3-Coder-30B-A3B-Instruct — available via AWS Bedrock (us-east-1).

Open-source Yi-Coder-9B-Chat model from 01-ai — available for download and self-hosting on Hugging Face.

Open-source Yi-Coder-9B model from 01-ai — available for download and self-hosting on Hugging Face.

Open-source Yi-Coder-1.5B-Chat model from 01-ai — available for download and self-hosting on Hugging Face.

Open-source Yi-Coder-1.5B model from 01-ai — available for download and self-hosting on Hugging Face.

Open-source deepseek-coder-6.7b-instruct model from deepseek-ai — available for download and self-hosting on Hugging Face.

Open-source deepseek-coder-7b-instruct-v1.5 model from deepseek-ai — available for download and self-hosting on Hugging Face.

Open-source deepseek-coder-6.7b-base model from deepseek-ai — available for download and self-hosting on Hugging Face.

Open-source deepseek-coder-1.3b-instruct model from deepseek-ai — available for download and self-hosting on Hugging Face.

Open-source deepseek-coder-1.3b-base model from deepseek-ai — available for download and self-hosting on Hugging Face.

Open-source deepseek-coder-33b-instruct model from deepseek-ai — available for download and self-hosting on Hugging Face.

Open-source DeepSeek-Coder-V2-Instruct model from deepseek-ai — available for download and self-hosting on Hugging Face.

Open-source stable-code-instruct-3b model from stabilityai — available for download and self-hosting on Hugging Face.

Open-source stable-code-3b model from stabilityai — available for download and self-hosting on Hugging Face.

Open-source Qwen2.5-Coder-7B-Instruct-GGUF model from bartowski — available for download and self-hosting on Hugging Face.

Open-source Qwen2.5-Coder-0.5B-Instruct model from qwen — available for download and self-hosting on Hugging Face.

Open-source Qwen2.5-Coder-14B-Instruct-AWQ model from qwen — available for download and self-hosting on Hugging Face.

Open-source Qwen3-Coder-Next model from qwen — available for download and self-hosting on Hugging Face.

Open-source DeepSeek-Coder-V2-Lite-Instruct model from deepseek-ai — available for download and self-hosting on Hugging Face.

Open-source Qwen3-Coder-Next-8bit model from nexveridian — available for download and self-hosting on Hugging Face.

Open-source Qwen2.5-Coder-1.5B model from qwen — available for download and self-hosting on Hugging Face.

Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual...

A specialized coding assistant designed for developers who need advanced programming support with a 16K token context window, offering cost-effective access at $0.80 per million input tokens for tasks like code generation, debugging, and technical problem-solving.

Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the...

Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’s designed for hard multi-step problems; math proofs, code synthesis/debugging, logic, and agentic...

Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual...

DeepSeek V3 — 671B MoE model with exceptional coding and math performance at very low cost.

Alibaba Qwen2.5 72B Instruct on DeepInfra — top open-source model with multilingual and coding strengths.

This large-scale code generation and software development model excels at complex programming tasks, algorithm design, and technical problem-solving, making it ideal for professional developers, software engineers, and technical teams seeking advanced AI-assisted coding capabilities.

Our medium code-agentic model.

Our small open-source code-agentic model.