docs(readme): update provider model counts

Author: github-actions[bot]

README.md

@@ -18,29 +18,29 @@ LLM model configs change often — prices drop, features expand, limits shift. T
 
 | Provider | Models | Description |
 |----------|--------|-------------|
-| OpenRouter | 785 | Unified API for open source models |
-| Google Vertex AI | 409 | Gemini, PaLM on GCP |
-| Together AI | 363 | Open source model hosting |
+| OpenRouter | 787 | Unified API for open source models |
+| Google Vertex AI | 414 | Gemini, PaLM on GCP |
+| Together AI | 365 | Open source model hosting |
 | DeepInfra | 231 | Open source model hosting |
-| AWS Bedrock | 212 | Claude, Llama, Titan, Mistral on AWS |
+| AWS Bedrock | 214 | Claude, Llama, Titan, Mistral on AWS |
 | Azure OpenAI | 199 | OpenAI models on Azure |
 | Deepgram | 143 | Speech-to-text and text-to-speech models |
-| OpenAI | 141 | GPT-4, GPT-4o, GPT-5, o1, o3, DALL-E, Whisper, TTS |
-| Mistral AI | 96 | Mistral, Mixtral, Codestral |
+| OpenAI | 143 | GPT-4, GPT-4o, GPT-5, o1, o3, DALL-E, Whisper, TTS |
+| Mistral AI | 98 | Mistral, Mixtral, Codestral |
 | xAI | 87 | Grok models |
+| Google Gemini | 72 | Gemini Pro, Ultra, Flash |
 | Azure AI Foundry | 70 | Azure AI models |
-| Google Gemini | 70 | Gemini Pro, Ultra, Flash |
-| Aws Bedrock Mantle | 49 |  |
+| Aws Bedrock Mantle | 50 |  |
 | Cohere | 38 | Command, Embed models |
 | Databricks | 31 | Databricks-hosted models |
 | SambaNova | 30 | Enterprise AI models |
-| Anthropic | 25 | Claude 3, Claude 3.5, Claude 4 |
+| Anthropic | 26 | Claude 3, Claude 3.5, Claude 4 |
 | Perplexity | 24 | Search-augmented models |
 | Groq | 23 | Fast inference models |
 | AI21 | 12 | Jamba models |
 | ElevenLabs | 10 | Voice synthesis and text-to-speech models |
 | Wafer | 10 |  |
-| Cerebras | 5 | Fast inference models |
+| Cerebras | 6 | Fast inference models |
 
 ## Installation