{"data":{"slug":"mnfst-awesome-free-llm-apis","name":"awesome-free-llm-apis","tagline":"List of Permanent Free LLM API","github_url":"https://github.com/mnfst/awesome-free-llm-apis","owner":"mnfst","repo":"awesome-free-llm-apis","owner_avatar_url":"https://avatars.githubusercontent.com/u/8403534?v=4","primary_language":"JavaScript","stars":7852,"forks":746,"topics":["ai-agents","anthropic","awesome","awesome-list","gemini","llm","llm-router","llm-routing","ollama","openai","openclaw","openclaw-plugin","router"],"archived":false,"github_pushed_at":"2026-08-21T05:32:48+00:00","maintenance_label":"Active","stars_delta_30d":1320,"url":"https://www.graphcanon.com/tools/mnfst-awesome-free-llm-apis","markdown_url":"https://www.graphcanon.com/tools/mnfst-awesome-free-llm-apis.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/mnfst-awesome-free-llm-apis","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=mnfst-awesome-free-llm-apis","description":"List of Permanent Free LLM API (API Keys)","homepage_url":null,"license":"CC0-1.0","open_issues":17,"watchers":105,"ai_summary":"Curates a list of permanent free Large Language Model APIs with information on their limitations and access methods.","readme_excerpt":"

\n\t\n\t\t\"Awesome\n\t\n

\n\n

\n\t\n\t\t\"Awesome\"\n\t\n

\n\n

LLM APIs with permanent free tiers for text inference.

\n\n

All endpoints are OpenAI SDK-compatible unless noted. Each link points to the provider's API key page.

\n\n
\n\n

\n\t\n\t\t\n\t\t\t\n\t\t\t\"Manifest\"\n\t\t\n\t\n

\n\n

All of those free LLM APIs are available at manifest.build - make reliable agents.

\n\n## Contents\n\n- [Provider APIs](#provider-apis)\n- [Inference providers](#inference-providers)\n- [Glossary](#glossary)\n\n## Provider APIs\n\nAPIs run by the companies that train or fine-tune the models themselves.\n\n### [Aion Labs](https://www.aionlabs.ai/app/api-keys/) 🇮🇱\n\nPermanent free tier, no credit card required. 15 RPM, 20K tokens/day. Specialized for roleplay and storytelling.\n\nBase URL: `https://api.aionlabs.ai/v1`\n\n| Model Name | Context | Max Output | Modality | Rate Limit |\n| -------------------------------- | ------- | ---------- | ---------------- | --------------- |\n| `aion-labs/aion-2.0` | 128K | 32K | Text (reasoning) | 15 RPM, 20K TPD |\n| `aion-labs/aion-rp-llama-3.1-8b` | 32K | 32K | Text | 15 RPM, 20K TPD |\n| `aion-labs/aion-3.0` | 128K | 32K | Text (reasoning) | 15 RPM, 20K TPD |\n| `aion-labs/aion-3.0-mini` | 128K | 32K | Text (reasoning) | 15 RPM, 20K TPD |\n\n### [Cohere](https://dashboard.cohere.com/api-keys) 🇨🇦\n\nFree \"Trial\" API key, no credit card. 1,000 API calls/month. Non-commercial use only.\n\nBase URL: `https://api.cohere.com/v2`\n\n| Model Name | Context | Max Output | Modality | Rate Limit |\n| ------------------- | ------- | ---------- | ---------------- | ---------- |\n| Command A+ (218B) | 128K | 64K | Text + Image | 20 RPM |\n| Command A (111B) | 256K | 8K | Text | 20 RPM |\n| Command R+ | 128K | 4K | Text | 20 RPM |\n| Command R | 128K | 4K | Text | 20 RPM |\n| Command R7B | 128K | 4K | Text | 20 RPM |\n| Command A Reasoning | 256K | 32K | Text (reasoning) | 20 RPM |\n| Command A Translate | 8K | 8K | Text | 20 RPM |\n| Command A Vision | 128K | 8K | Text + Image | 20 RPM |\n| Command R7B Arabic | 128K | ~4K | Text | 20 RPM |\n| Aya Expanse 32B | 128K | 4K | Text | 20 RPM |\n| Aya Vision 32B | 16K | 4K | Text + Image | 20 RPM |\n\n### [Google Gemini](https://aistudio.google.com/app/apikey) 🇺🇸\n\nFree tier, no credit card. Free-tier prompts may be used by Google to improve products. [^1]\n\nBase URL: `https://generativelanguage.googleapis.com/v1beta`\n\n| Model Name | Context | Max Output | Modality | Rate Limit |\n| --------------------- | ------- | ---------- | ---------------------------- | ----------------- |\n| Gemini 3.7 Flash | 1M | 65K | Text + Image + Audio + Video | — |\n| Gemini 3.6 Flash | 1M | 65K | Text + Image + Audio + Video | 15 RPM, 1,500 RPD |\n| Gemini 3.5 Flash | 1M | 65K | Text + Image + Audio + Video | 15 RPM, 1,500 RPD |\n| Gemini 3.5 Flash-Lite | 1M | 65K | Text + Image + Audio + Video | 30 RPM, 1,500 RPD |\n| Gemini 3.1 Flash-Lite | 1M","github_created_at":"2026-03-21T18:14:07+00:00","created_at":"2026-07-15T11:03:44.791818+00:00","updated_at":"2026-09-20T05:12:57.784189+00:00","categories":[{"slug":"inference-serving","name":"Inference & Serving","url":"https://www.graphcanon.com/categories/inference-serving","markdown_url":"https://www.graphcanon.com/categories/inference-serving.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/inference-serving"}],"tags":[{"slug":"ai-agents","name":"ai-agents"},{"slug":"anthropic","name":"anthropic"},{"slug":"gemini","name":"gemini"},{"slug":"llm","name":"llm"},{"slug":"ollama","name":"ollama"},{"slug":"openai","name":"openai"},{"slug":"openclaw","name":"openclaw"},{"slug":"router","name":"router"}],"trust":{"provenance":{"is_fork":false,"github_id":1188180267,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-20T05:12:54.758Z","maintenance":{"label":"Active","score":82,"methodology":"github_public_v1","releases_90d":0,"days_since_push":29,"last_release_at":null,"stars_delta_30d":1320,"open_issues_delta_30d":-8},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-15T11:03:46.166Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-20T05:12:56.142Z"},"languages":{"value":["javascript"],"source":"github.language","observed_at":"2026-09-20T05:12:56.142Z"},"license_spdx":{"value":"CC0-1.0","source":"github.license","observed_at":"2026-09-20T05:12:56.142Z"}},"decision_facts":{"hosting":null,"pricing":{"model":"freemium","summary":"The repository lists APIs with permanent free tiers, detailing rate and token limits for those interested in using free Large Language Model services."},"requirements":{"notes":["Before integration, ensure that the specific requirements for API access are met to utilize these models without restriction.","Users should review the rate and token limits associated with each API provider to determine suitability based on their project's needs."],"min_ram_gb":null},"constraints":{"min_ram_gb":null,"pricing_model":"freemium"},"when_to_use":["When you need text inference with specialized capabilities like roleplay and storytelling, the Aion Labs API offers a dedicated free tier specifically designed for these purposes.","If non-commercial use is your focus, Cohere provides a 'Trial' key that meets this criterion without requiring credit card information, making it suitable for academic or personal projects.","For applications requiring text, image, audio, and video capabilities, Google Gemini's Flash plans offer multi-modal support within free-tier constraints.","Mistral AI can be advantageous when you have extensive token requirements as the 'Experiment' plan offers approximately 1 billion tokens per month without a credit card."],"when_not_to_use":["Avoid using Aion Labs if your project involves heavy commercial activity, given its limited rate and token limits.","Do not use Cohere for projects that will scale beyond 1,000 API calls per month or require credit card details for access to higher-tier plans.","Google Gemini's free tier is inaccessible in the EU/UK/Switzerland regions and requires consent to let Google improve their products through your usage.","Mistral AI should be avoided if you need strict confidentiality, as they use prompts from users' interactions to refine and train additional model iterations."],"source":"enrich:decision_facts","observed_at":"2026-07-17T13:38:16.536Z"},"constraint_facets":{"min_ram_gb":null,"pricing_model":"freemium"},"decision_summary":[{"label":"Pricing","value":"freemium - The repository lists APIs with permanent free tiers, detailing rate and token limits for those interested in using free Large Language Model services."},{"label":"Requirements","value":"Before integration, ensure that the specific requirements for API access are met to utilize these models without restriction.; Users should review the rate and token limits associated with each API provider to determine suitability based on their project's needs."},{"label":"Adopt for","value":"awesome-free-llm-apis curates permanent free Large Language Model APIs with notable details on their limitations and access methods."},{"label":"License detail","value":"This resource is distributed under the Creative Commons Zero v1.0 Universal Public Domain Dedication (CC0-1.0) license."}]}}