Test Inference Models
We are currently supporting the following models as "Test inference" models. You can use them in Prompt Book and Knowledge Book.:
| Model Provider | Model | Model type |
|---|---|---|
| Anthropic | Claude 3 Haiku | Chat |
| Anthropic | Claude 3 Opus | Chat |
| Anthropic | Claude 3 Sonnet | Chat |
| Anthropic | Claude 3.5 Haiku | Chat |
| Anthropic | Claude 3.5 Sonnet | Chat |
| Anthropic | Claude 3.5 Sonnet v2 | Chat |
| Anthropic | Claude 3.7 Sonnet | Chat |
| Deepseek | DeepSeek R1 Distill Llama 70B | Chat |
| Deepseek | DeepSeek R1 Distill Qwen 1.5B | Chat |
| Deepseek | DeepSeek R1 Distill Qwen 14B | Chat |
| Deepseek | DeepSeek-R1 | Chat |
| Deepseek | DeepSeek-V3-0324 | Chat |
| Deepseek | Deepseek-67B | Chat |
| Gemini | Gemini 1.5 Flash | Chat |
| Gemini | Gemini 1.5 Flash 8B | Chat |
| Gemini | Gemini 1.5 Flash-8B | Chat |
| Gemini | Gemini 1.5 Pro | Chat |
| Gemini | Gemini 2.0 Flash | Chat |
| Gemini | Gemini 2.0 Flash Lite | Chat |
| Gemini | Gemini 2.0 Flash-Lite | Chat |
| Gemini | Gemini 2.5 Flash | Chat |
| Gemini | Gemini 2.5 Flash Preview | Chat |
| Gemini | Gemini 2.5 Pro | Chat |
| Gemini | Gemini 2.5 Pro (Experimental) | Chat |
| Gemini | Gemini 2.5 Pro Preview | Chat |
| Gemini | text-embedding-005 | Embedding |
| Meta | Llama 3 70B Instruct | Chat |
| Meta | Llama 3 70B Instruct Lite | Chat |
| Meta | Llama 3 70B Instruct Reference | Chat |
| Meta | Llama 3 70B Instruct Turbo | Chat |
| Meta | Llama 3 8B Instruct | Chat |
| Meta | Llama 3 8B Instruct Lite | Chat |
| Meta | Llama 3 8B Instruct Reference | Chat |
| Meta | Llama 3 8B Instruct Turbo | Chat |
| Meta | Llama 3.1 405B | Chat |
| Meta | Llama 3.1 405B Instruct | Chat |
| Meta | Llama 3.1 405B Instruct Turbo | Chat |
| Meta | Llama 3.1 70B Instruct | Chat |
| Meta | Llama 3.1 70B Instruct Turbo | Chat |
| Meta | Llama 3.1 8B | Chat |
| Meta | Llama 3.1 8B Instruct | Chat |
| Meta | Llama 3.1 8B Instruct Turbo | Chat |
| Meta | Llama 3.2 11B | Chat |
| Meta | Llama 3.2 11B Instruct | Chat |
| Meta | Llama 3.2 1B | Chat |
| Meta | Llama 3.2 1B Instruct | Chat |
| Meta | Llama 3.2 3B | Chat |
| Meta | Llama 3.2 3B Instruct | Chat |
| Meta | Llama 3.2 3B Instruct Turbo | Chat |
| Meta | Llama 3.2 90B | Chat |
| Meta | Llama 3.2 90B Instruct | Chat |
| Meta | Llama 3.3 70B | Chat |
| Meta | Llama 3.3 70B Instruct | Chat |
| Meta | Llama 3.3 70B Instruct Turbo | Chat |
| Meta | Llama 4 Maverick (17Bx128E) | Chat |
| Meta | Llama 4 Scout (17Bx16E) | Chat |
| Mistral | Ministral 3B 24.10 | Chat |
| Mistral | Ministral 8B 24.10 | Chat |
| Mistral | Mistral (7B) Instruct | Chat |
| Mistral | Mistral (7B) Instruct v0.2 | Chat |
| Mistral | Mistral (7B) Instruct v0.3 | Chat |
| Mistral | Mistral 7B | Chat |
| Mistral | Mistral 7B Instruct | Chat |
| Mistral | Mistral Embed | Embedding |
| Mistral | Mistral Large | Chat |
| Mistral | Mistral Large (24.02) | Chat |
| Mistral | Mistral Large (24.07) | Chat |
| Mistral | Mistral Large (24.11) | Chat |
| Mistral | Mistral Large 24.11 | Chat |
| Mistral | Mistral Nemo | Chat |
| Mistral | Mistral Saba | Chat |
| Mistral | Mistral Small | Chat |
| Mistral | Mistral Small (24.02) | Chat |
| Mistral | Mistral Small 3 Instruct (24B) | Chat |
| Mistral | Mistral Small 3.1 | Chat |
| Mistral | Mistral Small 3.1 (25.03) | Chat |
| Mistral | Mixtral 8x22B | Chat |
| Mistral | Mixtral 8x7B | Chat |
| Mistral | Mixtral 8x7B Instruct | Chat |
| Mistral | Pixtral 12B | Chat |
| Mistral | Pixtral Large | Chat |
| Mistral | Pixtral Large (25.02) | Chat |
| Openai | GPT-3.5 Turbo | Chat |
| Openai | GPT-3.5 Turbo (2024-01-25) | Chat |
| Openai | GPT-3.5 Turbo 16k | Chat |
| Openai | GPT-3.5 Turbo 16k (2024-01-25) | Chat |
| Openai | GPT-3.5-Turbo-0125 | Chat |
| Openai | GPT-3.5-Turbo-0301 | Chat |
| Openai | GPT-3.5-Turbo-0613 | Chat |
| Openai | GPT-3.5-Turbo-1106 | Chat |
| Openai | GPT-3.5-Turbo-16k-0613 | Chat |
| Openai | GPT-3.5-Turbo-Instruct | Chat |
| Openai | GPT-4-0125-Preview | Chat |
| Openai | GPT-4-0613 | Chat |
| Openai | GPT-4-32k-0314 | Chat |
| Openai | GPT-4.1 | Chat |
| Openai | GPT-4.1 (2025-04-14) | Chat |
| Openai | GPT-4.1 Mini | Chat |
| Openai | GPT-4.1 Mini (2025-04-14) | Chat |
| Openai | GPT-4.1 Nano | Chat |
| Openai | GPT-4.1 Nano (2025-04-14) | Chat |
| Openai | GPT-4.5 Preview (2025-02-27) | Chat |
| Openai | GPT-4.5-Preview-2025-02-27 | Chat |
| Openai | GPT-4o | Chat |
| Openai | GPT-4o (2024-05-13) | Chat |
| Openai | GPT-4o (2024-08-06) | Chat |
| Openai | GPT-4o (2024-11-20) | Chat |
| Openai | GPT-4o Mini | Chat |
| Openai | GPT-4o Mini (2024-07-18) | Chat |
| Openai | GPT-4o-2024-0513 | Chat |
| Openai | GPT-4o-2024-08-06 | Chat |
| Openai | GPT-4o-2024-1120 | Chat |
| Openai | GPT-4o-mini-0718 | Chat |
| Openai | Text Embedding 3 Large | Embedding |
| Openai | Text Embedding 3 Small | Embedding |
| Openai | Text Embedding Ada 002 | Embedding |
| Openai | gpt-4o | Chat |
| Openai | gpt-4o-mini | Chat |
| Openai | o1 | Chat |
| Openai | o1 (2024-12-17) | Chat |
| Openai | o1 2024-12-17 | Chat |
| Openai | o1 Preview (2024-09-12) | Chat |
| Openai | o1 Pro | Chat |
| Openai | o1 Pro (2025-03-19) | Chat |
| Openai | o1 preview 2024-09-12 | Chat |
| Openai | o1-mini | Chat |
| Openai | o1-mini 2024-09-12 | Chat |
| Openai | o3 | Chat |
| Openai | o3 (2025-04-16) | Chat |
| Openai | o3 mini 2025-01-31 | Chat |
| Openai | o3-mini | Chat |
| Openai | o4 Mini | Chat |
| Openai | o4 Mini (2025-04-16) | Chat |
| Openai | o4-mini | Chat |
| Openai | text-embedding-3-large | Embedding |
| Openai | text-embedding-3-small | Embedding |
| Qwen | QwQ-32B | Chat |
| Qwen | Qwen 2 Instruct (72B) | Chat |
| Qwen | Qwen 2.5 72B | Chat |
| Qwen | Qwen 2.5 72B Instruct Turbo | Chat |
| Qwen | Qwen 2.5 7B | Chat |
| Qwen | Qwen 2.5 7B Instruct Turbo | Chat |
| Qwen | Qwen3 235B A22B | Chat |
| Qwen | Qwen3 235B A22B FP8 | Chat |
You can also refer to them in the Settings -> Platform page.
