Providers
Model coverage, routing readiness, API paths, and source freshness across inference providers.
Aleph Alphaaleph-alpha | 1 | 0 | direct | Oct 5, 2026 | Developer and self-hosted provider of Kolibri 1. Its public materials document local OpenAI-compatible serving and sales-led enterprise deployment, but no public managed API route or price. |
Alibaba Cloud Model Studioalibaba-model-studio | 9 | 9 | direct | Sep 3, 2026 | First-party API access to Qwen models from Alibaba Cloud Model Studio. |
Amazon Bedrockamazon-bedrock | 1 | 1 | direct | Aug 29, 2026 | Amazon Bedrock access to Amazon Nova models. |
Anthropicanthropic | 13 | 13 | direct | Oct 19, 2026 | First-party Claude API access from Anthropic. |
Baidu Qianfanbaidu-qianfan | 2 | 2 | direct | Aug 29, 2026 | First-party API access to Baidu ERNIE models. |
Cerebrascerebras | 2 | 2 | direct | Oct 19, 2026 | |
Coherecohere | 4 | 4 | direct | Sep 3, 2026 | First-party Cohere API access to Command models. |
Deepinfradeepinfra | 49 | 49 | direct | Oct 19, 2026 | Serverless and private inference endpoints for open models. |
DeepSeekdeepseek | 4 | 4 | direct | Sep 10, 2026 | First-party API access to DeepSeek models through OpenAI-compatible, Anthropic-compatible, and Responses APIs. |
Fireworks Aifireworks-ai | 22 | 24 | direct | Oct 19, 2026 | Serverless and on-demand inference for open and custom models. |
Google AIgoogle-ai | 16 | 16 | direct | Sep 3, 2026 | First-party Gemini Developer API access from Google. |
Google Geminigoogle-gemini | 18 | 23 | direct | Oct 19, 2026 | |
Groqgroq | 2 | 2 | direct | Aug 28, 2026 | Low-latency hosted inference on GroqCloud. |
Hugging Facehugging-face | 104 | 41 | gateway | Sep 2, 2026 | Unified multi-provider inference routing from Hugging Face Inference Providers. |
IBM watsonx.aiibm-watsonx | 1 | 0 | direct | Aug 29, 2026 | First-party IBM watsonx.ai foundation and embedding model inference. |
Microsoft Foundrymicrosoft-foundry | 1 | 0 | direct | Sep 3, 2026 | First-party Microsoft model access through Foundry and Azure AI services. |
Mistral AImistral | 4 | 3 | direct | Oct 6, 2026 | First-party API access to Mistral models and Document AI. |
Openaiopenai | 30 | 53 | direct | Oct 19, 2026 | First-party API access to OpenAI models. |
Openrouteropenrouter | 94 | 111 | gateway | Oct 19, 2026 | A multi-provider inference gateway with configurable provider routing. |
Perplexityperplexity | 4 | 4 | direct | Aug 29, 2026 | First-party Sonar search and research API access from Perplexity. |
PrismMLprismml | 11 | 0 | direct | Sep 18, 2026 | Open-weight Bonsai model provider with documented local OpenAI-compatible serving. No current public managed API route or price was verified. |
Reflection AIreflection-ai | 1 | 1 | direct | Oct 5, 2026 | Developer and beta inference provider for Beam. Its OpenAI-compatible Chat Completions and Models API is documented, but access is selective and public token pricing and regions are not published. |
Stability AIstability-ai | 2 | 0 | direct | Aug 29, 2026 | First-party Stability Platform image and audio generation APIs. |
Together Aitogether-ai | 38 | 38 | direct | Oct 19, 2026 | Serverless and dedicated inference for open models. |
TypeSafetypesafe | 1 | 1 | direct | Sep 17, 2026 | First-party System One API access from TypeSafe. |
Upstageupstage | 1 | 1 | direct | Sep 18, 2026 | First-party API and private-deployment access to Upstage models. |
Xaixai | 6 | 6 | direct | Oct 19, 2026 | First-party Grok API access from xAI. |
Xiaomi MiMoxiaomi-mimo | 1 | 1 | direct | Sep 22, 2026 | First-party API access to Xiaomi MiMo models. |
Z.aizai | 3 | 3 | direct | Aug 29, 2026 | First-party GLM API access from Z.ai. |
Source coverage describes the observed provider catalog; it is not an endorsement.