Comparison Table of all supported Language Models
Provider | Streaming | Tools (sync/streaming/partial/complete) | JSON Schema | JSON Mode | Thinking (Reasoning) | Supported Modalities (Input) | Observability | Customizable HTTP Client | Local Deployment | Supports Native Image | Comments |
---|---|---|---|---|---|---|---|---|---|---|---|
Amazon Bedrock | ✅ | ✅/✅/❌/✅ | ✅ | text, image, PDF | ✅ | ||||||
Anthropic | ✅ | ✅/✅/✅/✅ | ✅ | text, image | ✅ | ✅ | ✅ | ||||
Azure OpenAI | ✅ | ✅/✅/✅/✅ | ✅ | ✅ | text, image | ✅ | |||||
ChatGLM | text | ||||||||||
DashScope | ✅ | ✅/✅ | text, image, audio | ✅ | |||||||
GitHub Models | ✅ | ✅/✅/🆘/🆘 | 🔜 #1911 | ✅ | text, image | ✅ | |||||
Google AI Gemini | ✅ | ✅/✅/❌/✅ | ✅ | ✅ | ✅ | text, image, audio, video, PDF | ✅ | ✅ | |||
Google Vertex AI Gemini | ✅ | ✅/✅/❌/✅ | ✅ | ✅ | text, image, audio, video, PDF | ✅ | |||||
Google Vertex AI PaLM 2 | text | ✅ | |||||||||
Hugging Face | text | ||||||||||
Jlama | ✅ | ✅/✅/🆘/🆘 | text | ✅ | ✅ | ||||||
LocalAI | ✅ | ✅/✅ | text, image, audio | ✅ | |||||||
Mistral AI | ✅ | ✅/✅/❌/✅ | ✅ | ✅ | text, image | ✅ | ✅ | ||||
Ollama | ✅ | ✅/✅/❌/✅ | ✅ | ✅ | ✅ | text, image | ✅ | ✅ | ✅ | ||
OpenAI | ✅ | ✅/✅/✅/✅ | ✅ | ✅ | ✅ (DeepSeek) | text, image, audio, PDF | ✅ | ✅ | See OpenAI-Compatible Language Models (Ollama, LM Studio, GPT4All, Docker Model Runner, etc.) | ✅ | See OpenAI-Compatible Language Models(Groq, ...) |
Oracle Cloud Infrastructure GenAI | ✅ | ✅/✅ | text, image | ✅ | |||||||
Qianfan | ✅ | ✅/✅ | text | ||||||||
Cloudflare Workers AI | text | ||||||||||
Zhipu AI | ✅ | ✅/✅ | text, image | ✅ |
Legend:
- ✅ means "supported"
- 🆘 means "not supported yet; please help us implement it"
- 🔜 means "it is being implemented; please wait"
- ❌ means "not supported by the LLM provider"
- no mark means "not sure, need to double-check"