Skip to main content

AI

Agentic Coding Tools​

Claude code:

curl -fsSL https://claude.ai/install.sh | bash

Hermes:

curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash

Codex:

curl -fsSL https://chatgpt.com/codex/install.sh | sh

open code:

curl -fsSL https://opencode.ai/install | bash

antigravity:

curl -fsSL https://antigravity.google/cli/install.sh | bash

Model APIs​

Gemini​

url: https://generativelanguage.googleapis.com/v1beta/openai/chat/completions

api key: https://aistudio.google.com/api-keys?

docs: https://ai.google.dev/gemini-api/docs/openai#rest

OpenRouter​

https://openrouter.ai/api/v1/chat/completions

https://openrouter.ai/api/v1

Groq​

url: https://api.groq.com/openai/v1/chat/completions

api key: https://console.groq.com/keys

docs: https://console.groq.com/playground?model=llama-3.3-70b-versatile


2. DeepSeek​

Extremely generous rate limits and initial free credits for high-performance models.

  • Base URL: [https://api.deepseek.com/chat/completions](https://api.deepseek.com/chat/completions)
  • API Key: [https://platform.deepseek.com/api_keys](https://platform.deepseek.com/api_keys)
  • Docs: [https://platform.deepseek.com/api-docs/](https://platform.deepseek.com/api-docs/)
  • Models: deepseek-chat, deepseek-reasoner

3. GitHub Models​

Completely free playground and API tier if you have a GitHub account (uses standard GitHub Personal Access Tokens).

  • Base URL: [https://models.inference.ai.azure.com/chat/completions](https://models.inference.ai.azure.com/chat/completions)
  • API Key: [https://github.com/settings/tokens](https://github.com/settings/tokens)
  • Docs: [https://docs.github.com/en/github-models](https://docs.github.com/en/github-models)
  • Models: meta-llama-3.3-70b-instruct, gpt-4o-mini, mistral-large-2407, phi-4

5. Mistral AI (La Plateforme - Free Tier)​

Offers free rate-limited access to their lightweight models.

  • Base URL: [https://api.mistral.ai/v1/chat/completions](https://api.mistral.ai/v1/chat/completions)
  • API Key: [https://console.mistral.ai/api-keys/](https://console.mistral.ai/api-keys/)
  • Docs: [https://docs.mistral.ai/getting-started/client/](https://docs.mistral.ai/getting-started/client/)
  • Models: mistral-small-latest, pixtral-12b-2409 (vision)

Cloudflare Workers AI​

Cloudflare explicitly supports an OpenAI-compatible /v1/chat/completions endpoint.

URL: https://api.cloudflare.com/client/v4/accounts/{ACCOUNT\_ID}/ai/v1/chat/completions

API key: Cloudflare API token

Model: @cf/meta/llama-3.1-8b-instruct

This is particularly nice if you're already using Cloudflare.

  1. Hugging Face

Hugging Face Inference Providers

Good if your goal is to experiment with lots of open-source models rather than sticking to one provider.


Vibe Coding Tools​

OpenCode

OpenAI Codex

Claude Code

Hermes

full coding​

Google antigravity?

Model Providers:

Gemini, GPT, Claude, Grok, DeepSeek, Qwen, Open Router