Skip to content

Latest commit

 

History

History
143 lines (114 loc) · 4.87 KB

API_KEYS.md

File metadata and controls

143 lines (114 loc) · 4.87 KB

guIDE — API Keys Reference

All cloud AI provider API keys used by guIDE. Keep this file updated as you add/remove keys.

How to add keys in guIDE: Click the model picker → expand a provider → paste your key → click "Connect"
Or: Click the 🔑 icon in the chat toolbar to open the API Keys panel

Free Cloud Providers (No Credit Card Required)

1. Google Gemini

  • Sign up: https://aistudio.google.com/apikey
  • Key format: AIza...
  • Free tier: 1M context window, 15 RPM, Gemini 2.5 Pro/Flash
  • Models: Gemini 2.5 Pro, Gemini 2.5 Flash, Gemini 2.0 Flash, Gemini 3 Flash Preview
  • Your key: [PASTE KEY HERE]

2. Groq

  • Sign up: https://console.groq.com/keys
  • Key format: gsk_...
  • Free tier: Ultra-fast inference, rate limited
  • Models: Llama 3.3 70B, Llama 3.1 8B, Gemma 2 9B, Mixtral 8x7B, Qwen QWQ 32B, DeepSeek R1 Distill 70B
  • Your key: [PASTE KEY HERE]

3. Cerebras

  • Sign up: https://cloud.cerebras.ai/
  • Key format: csk-...
  • Free tier: Ultra-fast inference (fastest provider)
  • Models: Llama 3.3 70B, Qwen 3 32B, GPT OSS 120B
  • Your key: [PASTE KEY HERE]

4. SambaNova

  • Sign up: https://cloud.sambanova.ai/apis
  • Key format: aaede...
  • Free tier: Fast free inference, generous limits
  • Models: DeepSeek V3.1, Llama 3.3 70B, DeepSeek R1, Qwen 3 235B, Qwen 3 32B, Llama 4 Maverick 17B
  • Your key: [PASTE KEY HERE]

5. OpenRouter

  • Sign up: https://openrouter.ai/keys
  • Key format: sk-or-...
  • Free tier: 100+ free models, generous rate limits
  • Models: Llama 3.3 70B, Qwen3 235B, DeepSeek R1, Gemini 2.0 Flash, Mistral Small 3.1 (all free)
  • Your key: [PASTE KEY HERE]

6. APIFreeLLM

  • Sign up: https://apifreellm.com
  • Key format: apf_...
  • Free tier: Free API access, 200B+ model
  • Models: APIFreeLLM 200B+
  • Your key: [PASTE KEY HERE]

7. NVIDIA NIM

  • Sign up: https://build.nvidia.com/explore
  • Key format: nvapi-...
  • Free tier: Free NIM inference
  • Models: Llama 3.3 70B, DeepSeek R1, Nemotron 70B, QWQ 32B
  • Your key: [PASTE KEY HERE]

8. Cohere

  • Sign up: https://dashboard.cohere.com/api-keys
  • Key format: Trial key (alphanumeric)
  • Free tier: 1000 calls/month, no credit card
  • Models: Command A (flagship), Command R+, Command R, Command R 7B
  • Your key: [PASTE KEY HERE]

9. Mistral AI

  • Sign up: https://console.mistral.ai/api-keys
  • Key format: Alphanumeric key
  • Free tier: Free tier with rate limits
  • Models: Mistral Small 3.2, Mistral Large 3, Ministral 8B, Mistral Nemo 12B, Pixtral 12B Vision
  • Your key: [PASTE KEY HERE]

10. HuggingFace

  • Sign up: https://huggingface.co/settings/tokens
  • Key format: hf_...
  • Free tier: Free inference API
  • Models: DeepSeek V3, Qwen3 235B, Llama 3.3 70B, Mistral Small 3.1
  • Your key: [PASTE KEY HERE]

11. Cloudflare Workers AI

  • Sign up: https://dash.cloudflare.com/
  • Key format: accountId:apiToken
  • Free tier: 10,000 neurons/day free
  • Models: Llama 3.3 70B, QWQ 32B, DeepSeek R1 Distill 32B, Mistral Small 3.1, Gemma 3 12B
  • Your key: [PASTE KEY HERE]

Premium Providers (Paid, Credit Card Required)

12. OpenAI

  • Sign up: https://platform.openai.com/api-keys
  • Key format: sk-...
  • Pricing: Pay-per-token (varies by model)
  • Models: GPT-4o, GPT-4o Mini, GPT-4 Turbo, GPT-3.5 Turbo
  • Your key: [PASTE KEY HERE]

13. Anthropic (Claude)

14. xAI (Grok)

  • Sign up: https://console.x.ai/
  • Key format: xai-...
  • Pricing: Pay-per-token
  • Models: Grok 3, Grok 3 Mini
  • Your key: [PASTE KEY HERE]

15. Together.ai

  • Sign up: https://api.together.xyz/settings/api-keys
  • Key format: Alphanumeric
  • Pricing: Pay-per-token (competitive rates)
  • Models: Llama 3.3 70B Turbo, Llama 3.1 405B Turbo, DeepSeek R1, Qwen 2.5 72B, Mixtral 8x22B, Gemma 2 27B
  • Your key: [PASTE KEY HERE]

16. Fireworks.ai

Quick Setup Recommendation

For the best free experience, set up these 3 providers (takes ~5 minutes):

  1. Google Gemini — Best overall free option (1M context, vision, reasoning)
  2. Cerebras — Fastest inference speed
  3. OpenRouter — Widest model selection (100+ free models)

This gives you access to 15+ models for free with no credit card.

Last updated: $(date)
guIDE v2.0.0 — 16 Cloud Providers, 50+ Languages, 53 MCP Tools