FREE APIs for using LLMs like GLM 4.7, Qwen 3, GPT oss 120b, llama 70b/8b, Kimi k2 family and Dee...

FREE APIs for using LLMs like GLM 4.7, Qwen 3, GPT oss 120b, llama 70b/8b, Kimi k2 family and Deepseek.

Welcome to this list of high-performance API providers. These services offer access to cutting-edge large language models (LLMs) like Llama 3, DeepSeek, and Qwen, often featuring generous free tiers or industry-leading inference speeds. Whether you are building real-time applications or roleplaying on plarforms like SillyTavern or Janitor Ai, these providers offer the infrastructure needed for low-latency AI interactions. Gathered by yours truly, Rusteez.

This list will continue to be updated as new providers become available. It excludes API providers and aggregators that do not offer free requests per day (RPD), including only those that give you daily free access to LLMs. last updated: 17th February 2025

1. Samba Nova

Supported Free LLMs: Deepseek v3.1 / v3 0324 / R1 / Distilled 70b llama, Mistral, Gpt oss, Qwen and more.

Get your Api key here:
https://cloud.sambanova.ai/apis

Model Name: Choose from the Rate Limits page.

Proxy url: https://api.sambanova.ai/v1/chat/completions

Rate limits & Model IDs:
https://docs.sambanova.ai/docs/en/models/rate-limits

2. Cerebras Ai (Currently doesn't provide GLM 4.7 & Qwen 3 as of 17th feb)

Supported Free LLMs: ~~GLM 4.7~~, Llama 70b/8b, ~~Qwen 3~~ and Gpt oss.

Get your Api key here:
https://cloud.cerebras.ai/?utm_source=3pi_quickstart&utm_campaign=docs

Model Name: Choose from the Rate Limits page.

Proxy url: https://api.cerebras.ai/v1/chat/completions

Rate limits & Model IDs:
https://inference-docs.cerebras.ai/support/rate-limits

3. Groq Ai

Supported Free LLMs: Moonshot kimi k2, Gpt oss and Llama 4 scout / 3.3.

Get your Api key here:
https://console.groq.com/keys

Model Name: Choose from the Rate Limits page.

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

Rate limits & Model IDs:
https://console.groq.com/docs/rate-limits

4. Literouter

Supported Free LLMs: Has a vast library of Models to choose from, including Deepseek family to Gemini and Mistral, even Claude.

Get your Api key here:
https://literouter.com/api_dashboard_api_keys.php

Model Name: Choose from the Rate Limits page.

Proxy url: https://api.literouter.com/v1

Rate limits & Model IDs:
https://literouter.com/api_dashboard_models.php

Literouter's own integration guide for platforms like Janitor Ai & Silly Tavern: https://literouter.com/api_dashboard_integration.php

5. Openrouter

Supported Free LLMs: One of the leading Api aggregators with various models to its disposal. From Deepseek (may vary depending on the timeline of depreciation on Free Tier) to Mistral and Glm. With free models added weekly to monthly.

Get your Api key here:
https://openrouter.ai/settings/keys

Model Name: Choose from the Rate Limits page.

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

Rate limits & Model IDs:
https://openrouter.ai/models

These are all the FREE Providers I could find at the moment. I will continue to add more in the future. If you have any questions or suggestions, don't hesitate to ask/tell me on Discord, My username: _rustylover_