"\n\n\nCoding & Developer Tools โ€” LLM SubHub\n\n\n\n\n\n\n\n
\n
\n\nS\nLLM SubHub\n\n\nDashboard\n
\n
\n\n\n
\n
\n
\n
\n
๐Ÿง‘โ€๐Ÿ’ป ๐Ÿง‘โ€๐Ÿ’ป
\n

\nCoding & Developer Tools\n

\n

Hermes, Aider, Cursor, Codex โ€” these providers power the best developer tooling available.

\n
\nFind Code Models โ†’\nโ† Back to Home\n
\n
\n
\n\n\n
\n
\n

11 providers in this category

\nSpecialized providers optimized for coding agents, IDEs, and developer workflows.\n
\n
\n\n \n
\n ๐Ÿค—\n
\n

Hugging Face

\n

The hub for open-source AI โ€” access thousands of models via free serverless inference.

\n
\n
\n
\n Llama 3.1 70BQwen 2.5 72BMistral 7B\n
\n
\n pay as you go\n
\n Signup โ†’\n Docs\n
\n
\n \n \n \n
\n โšก\n
\n

Cloudflare Workers AI

\n

Run AI at the edge โ€” 10k free inferences/day with models like Llama, Mistral, Phi.

\n
\n
\n
\n Llama 3.1 8BMeta-Llama-3-8Bphi-3-mini\n
\n
\n pay as you go\n
\n Signup โ†’\n Docs\n
\n
\n \n \n \n
\n ๐Ÿ’ฌ\n
\n

HuggingChat

\n

Free web-based AI chat powered by top open models. No API key required for basic use.

\n
\n
\n
\n Llama 3.1 70BQwen 2.5 72BMistral 7B\n
\n
\n free\n
\n Signup โ†’\n \n
\n
\n \n \n \n
\n ๐ŸŽ†\n
\n

Fireworks AI

\n

Lightning-fast inference for 500+ open models including all major code LLMs.

\n
\n
\n
\n Llama-3.1-CodeQwen-CoderDeepSeek Coder\n
\n
\n pay as you go\n
\n Signup โ†’\n Docs\n
\n
\n \n \n \n
\n โšก\n
\n

Anyscale

\n

Elastic compute for any model โ€” CodeLlama, CodeQwen, StarCoder via unified API.

\n
\n
\n
\n CodeLlama-70BQwen-CoderStarCoder2-15B\n
\n
\n pay as you go\n
\n Signup โ†’\n Docs\n
\n
\n \n \n \n
\n ๐Ÿ”ท\n
\n

Novita AI

\n

Ultra-cheap inference APIs for thousands of open-source models including code versions.

\n
\n
\n
\n DeepSeek-Coder-V2CodeQwen-1.5CodeLlama-Instruct\n
\n
\n pay as you go\n
\n Signup โ†’\n Docs\n
\n
\n \n \n \n
\n ๐Ÿ’Ž\n
\n

SiliconFlow

\n

Chinese cloud giant's inference platform with free tier for developers.

\n
\n
\n
\n Qwen-CoderDeepSeek CoderInternLM2-Coder\n
\n
\n free\n
\n Signup โ†’\n Docs\n
\n
\n \n \n \n
\n โ˜๏ธ\n
\n

vLLM Cloud

\n

Deploy your own fine-tuned code models with high throughput inference.

\n
\n
\n
\n Any custom SFT/fine-tune\n
\n
\n pay as you go\n
\n Signup โ†’\n Docs\n
\n
\n \n \n \n
\n ๐ŸŸฃ\n
\n

NVIDIA Build

\n

NVIDIA-hosted Codestral and other code LLMs via their build platform.

\n
\n
\n
\n Codestral-22BCodetoolNemotron-4\n
\n
\n pay as you go\n
\n Signup โ†’\n Docs\n
\n
\n \n \n \n
\n ๐Ÿ”ฎ\n
\n

OctoAI

\n

GPU-powered inference with zero-latency edge delivery for code models.

\n
\n
\n
\n CodeLlama-70BStarcoder-3BWizardCoder\n
\n
\n pay as you go\n
\n Signup โ†’\n Docs\n
\n
\n \n \n \n
\n ๐Ÿงช\n
\n

Replicate Coding

\n

Run thousands of open-source code LLMs via simple REST API.

\n
\n
\n
\n stabilityai/stable-code-3bcodellama/CodeLlama-70B-Instruct\n
\n
\n pay as you go\n
\n Signup โ†’\n Docs\n
\n
\n \n \n
\n
\n\n\n\n"