DeepSeek
Connect chat and reasoning models while preserving reasoning content and tool-call fields.
- Chat
- Messages
- Responses
Skip to content
Chinese model integration guide → CHINESE MODELS CHINESE MODELS CHINESE MODELS CHINESE MODELS GLOBAL MODELS GLOBAL MODELS GLOBAL MODELS GLOBAL MODELS
MODEL EXPLORER
The right model. For your next idea.
Compare models for chat, reasoning, embeddings, images, and video by protocol, streaming support, and published rates.
MODELS, CONNECTED
Chinese and global models. One integration.
DeepSeek, Kimi, MiniMax, and Zhipu GLM join OpenAI, Claude, Gemini, and Grok through platform credentials, compatible protocols, and Credits billing.
Kimi
Connect Kimi / Moonshot models with model-specific context, thinking, and tool calling.
- Chat
- Messages
- Responses
MiniMax
Access text and reasoning capabilities using the request formats declared for each model.
- Chat
- Messages
- Responses
Zhipu GLM
Connect through Chat and Messages. Responses is not an implemented integration in this profile.
- Chat
- Messages
OpenAI
Use familiar conversation APIs and select embeddings or image capabilities from the catalog.
- Chat
- Responses
- Messages
Claude
Use Messages and Chat / Responses compatibility, with token counting where configured.
- Messages
- Chat
- Responses
Gemini
Use native generation, streaming, and token counting, or a declared compatible protocol.
- Gemini
- Chat
- Messages
Grok
Connect conversation and reasoning, plus enabled image or video models from the catalog.
- Chat
- Responses
- Messages
These are implemented integrations. Callable model IDs, protocols, streaming, and rates depend on the published catalog and your plan. A family name does not imply support for every API.
Design preview · Sample models and rates.
Text
| Model | Capability | Modalities | Context | Protocol | Streaming | Rate | Status / Sunset date |
|---|---|---|---|---|---|---|---|
| Text Standard (fixture)fixture-text-standard | chat, tools | text → text | 128,000 | openai_chat_completions, openai_responsesOpenAI SDK | Yes | 25 Credits / per 1M tokens (same input/output rate) | Available |
Multimodal
| Model | Capability | Modalities | Context | Protocol | Streaming | Rate | Status / Sunset date |
|---|---|---|---|---|---|---|---|
| Multimodal Preview (fixture)fixture-multimodal-preview | chat, vision | text, image → text | 64,000 | openai_responses, anthropic_messagesOpenAI SDKAnthropic SDK | Yes | 40 Credits / per 1M tokens (same input/output rate) | Preview |
Image
| Model | Capability | Modalities | Context | Protocol | Streaming | Rate | Status / Sunset date |
|---|---|---|---|---|---|---|---|
| Image Legacy (fixture)fixture-image-legacy | image_generation | text, image → image | Not provided | openai_imagesOpenAI SDK | No | 8 Credits / per image | DeprecatingDec 31, 2030Replacement: fixture-multimodal-preview |
Check declared protocols and capabilities, then confirm access with your credential. Parameters, tools, and outputs vary by model. Read integration notes →