跳转到主要内容

Supported models

This page lists all models supported by AI Search and their lifecycle status.

:::note[Request model support] If you would like to use a model that is not currently supported, reach out to us on Discord to request it. :::

Production models

Production models are the actively supported and recommended models that are stable and fully available.

Text generation

AI Search supports the following Workers AI models for text generation:

Provider Alias Context window (tokens)
Workers AI @cf/meta/llama-3.3-70b-instruct-fp8-fast 24,000
@cf/meta/llama-3.1-8b-instruct-fast 60,000
@cf/meta/llama-3.1-8b-instruct-fp8 32,000
@cf/meta/llama-4-scout-17b-16e-instruct 131,000
@cf/deepseek-ai/deepseek-v4-flash-0731 1,048,576
@cf/deepseek-ai/deepseek-v4-pro-0813 1,048,576
@cf/openai/gpt-oss-120b 128,000
@cf/openai/gpt-oss-20b 128,000
@cf/qwen/qwen3.8-27b 262,144
@cf/moonshotai/kimi-k2.7-code 262,144
@cf/zai-org/glm-4.7-flash 131,072
@cf/zai-org/glm-5.3-flash 1,048,576
@cf/zai-org/glm-5.3 1,310,720
@cf/qwen/qwen3-30b-a3b-fp8 32,000

For external generation models, AI Search supports any provider compatible with the AI Gateway chat completions endpoint.

Embedding

Provider Alias Vector dims Input tokens Image support Default Metric
Google AI Studio google-ai-studio/gemini-embedding-001 1,536 2,048 No No cosine
google-ai-studio/gemini-embedding-2 1,536 8,192 Yes No cosine
OpenAI openai/text-embedding-3-small 1,536 8,192 No No cosine
openai/text-embedding-3-large 1,536 8,192 No No cosine
Workers AI @cf/baai/bge-m3 1,024 512 No No cosine
@cf/baai/bge-large-en-v1.5 1,024 512 No No cosine
@cf/qwen/qwen3-embedding-0.6b 1,024 8,192 No Yes cosine
@cf/qwen/qwen3-vl-embedding-2b 1,024 32,768 Yes No cosine
@cf/google/embeddinggemma-300m 768 512 No No cosine

Reranking

Provider Alias Input tokens Default
Workers AI @cf/baai/bge-reranker-base 512 Yes

Transition models

There are currently no models marked for end-of-life.

这篇文档对你有帮助吗？
想留言或继续讨论？请到 Cyberforums 赛博论坛参与。 参与讨论 / 回复