Weekly diffs of API rate limits across major LLM providers https://github.com/llerandi/llm-rate-limits-tracker/ 2026-08-03T00:00:00Z LLM Rate Limits Tracker https://github.com/llerandi/llm-rate-limits-tracker https://github.com/llerandi/llm-rate-limits-tracker/blob/main/data/history/2026-08-03.json 2026-08-03T00:00:00Z <h3>New models</h3><ul><li>AI21 Labs Jamba Large (new model)</li><li>AI21 Labs Jamba Mini (new model)</li><li>Qwen Qwen3.7-Max (new model)</li><li>Qwen Qwen3.5-Plus (new model)</li><li>Qwen Qwen3.5-Flash (new model)</li><li>Qwen Qwen-Plus (new model)</li><li>Qwen Qwen-Turbo (new model)</li></ul><p>Full data: <a href="https://cdn.jsdelivr.net/gh/llerandi/llm-rate-limits-tracker@main/data/rate-limits.json">rate-limits.json</a> | <a href="https://llerandi.github.io/llm-rate-limits-tracker/">Live site</a></p> https://github.com/llerandi/llm-rate-limits-tracker/blob/main/data/history/2026-07-30.json 2026-07-30T00:00:00Z <h3>New models</h3><ul><li>Cerebras GPT-OSS 120B (Cerebras) (new model)</li><li>Cerebras GLM-4.7 (Cerebras) (new model)</li><li>Cerebras Gemma 4 31B (Cerebras) (new model)</li><li>SambaNova Llama 3.3 70B (SambaNova) (new model)</li><li>SambaNova DeepSeek V3.1 (SambaNova) (new model)</li><li>NVIDIA NIM NVIDIA NIM API (all models) (new model)</li><li>Perplexity Sonar Reasoning Pro (new model)</li><li>Perplexity Sonar Deep Research (new model)</li><li>Azure OpenAI GPT-5.1 (new model)</li><li>Azure OpenAI GPT-5.4 (new model)</li><li>Azure OpenAI GPT-5.4 Nano (new model)</li><li>Azure OpenAI o3 (new model)</li><li>Azure OpenAI o4-mini (new model)</li></ul><p>Full data: <a href="https://cdn.jsdelivr.net/gh/llerandi/llm-rate-limits-tracker@main/data/rate-limits.json">rate-limits.json</a> | <a href="https://llerandi.github.io/llm-rate-limits-tracker/">Live site</a></p>