🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org
Python agentai-societiesartificial-intelligencecommunicative-aicooperative-aideep-learninglarge-language-modelsmulti-agent-systemsnatural-language-processing
chore: Update model doc and zhipu model (#3722)
Tao Sunceb2afbd0cd7
diff --git a/camel/types/enums.py b/camel/types/enums.pyindex 01d23edf6..986cf578e 100644--- a/camel/types/enums.py+++ b/camel/types/enums.py@@ -69,6 +69,11 @@ class ModelType(UnifiedModelType, Enum):AMD_GPT4 = "dvue-aoai-001-gpt-4.1"+ GLM_4_7 = "glm-4.7"+ GLM_4_7_FLASH = "glm-4.7-flash"+ GLM_4_6 = "glm-4.6"+ GLM_4_6V = "glm-4.6v"+ GLM_4_6V_FLASH = "glm-4.6v-flash"GLM_4 = "glm-4"GLM_4V = "glm-4v"GLM_4V_FLASH = "glm-4v-flash"@@ -672,6 +677,11 @@ class ModelType(UnifiedModelType, Enum):ModelType.GLM_4_FLASHX,ModelType.GLM_4_FLASH,ModelType.GLM_ZERO_PREVIEW,+ ModelType.GLM_4_7,+ ModelType.GLM_4_7_FLASH,+ ModelType.GLM_4_6,+ ModelType.GLM_4_6V,+ ModelType.GLM_4_6V_FLASH,}@property@@ -1481,6 +1491,8 @@ class ModelType(UnifiedModelType, Enum):ModelType.MODELSCOPE_ERNIE_4_5_VL_28B_A3B_THINKING,ModelType.ERNIE_5_0_THINKING,ModelType.ERNIE_4_5_TURBO_VL,+ ModelType.GLM_4_6V,+ ModelType.GLM_4_6V_FLASH,}:return 128_000elif self in {@@ -1545,6 +1557,9 @@ class ModelType(UnifiedModelType, Enum):ModelType.AWS_CLAUDE_OPUS_4_1,ModelType.O4_MINI,ModelType.O3,+ ModelType.GLM_4_7,+ ModelType.GLM_4_7_FLASH,+ ModelType.GLM_4_6,}:return 200_000elif self in {diff --git a/docs/mintlify/key_modules/models.mdx b/docs/mintlify/key_modules/models.mdxindex 65348e239..b9b5ce2d2 100644--- a/docs/mintlify/key_modules/models.mdx+++ b/docs/mintlify/key_modules/models.mdx@@ -47,7 +47,7 @@ CAMEL supports a wide range of models, including [OpenAI’s GPT series](https:/| **DeepSeek** | deepseek-chat<br/>deepseek-reasoner || **CometAPI** | **All models available on [CometAPI](https://api.cometapi.com/pricing)**<br/>Including: gpt-5-chat-latest, gpt-5, gpt-5-mini, gpt-5-nano<br/>claude-opus-4-1-20250805, claude-sonnet-4-20250514, claude-3-7-sonnet-latest<br/>gemini-2.5-pro, gemini-2.5-flash, grok-4-0709, grok-3<br/>deepseek-v3.1, deepseek-v3, deepseek-r1-0528, qwen3-30b-a3b || **Nebius** | **All models available on [Nebius AI Studio](https://studio.nebius.com/)**<br/>Including: gpt-oss-120b, gpt-oss-20b, GLM-4.5<br/>DeepSeek V3 & R1, LLaMA, Mistral, and more |-| **ZhipuAI** | glm-4, glm-4v, glm-4v-flash<br/>glm-4v-plus-0111, glm-4-plus, glm-4-air<br/>glm-4-air-0111, glm-4-airx, glm-4-long<br/>glm-4-flashx, glm-zero-preview, glm-4-flash, glm-3-turbo |+| **ZhipuAI** | glm-4.7, glm-4.7-flash<br/>glm-4.6, glm-4.6v, glm-4.6v-flash<br/>glm-4, glm-4v, glm-4v-flash<br/>glm-4v-plus-0111, glm-4-plus, glm-4-air<br/>glm-4-air-0111, glm-4-airx, glm-4-long<br/>glm-4-flashx, glm-zero-preview, glm-4-flash, glm-3-turbo || **InternLM** | internlm3-latest, internlm3-8b-instruct<br/>internlm2.5-latest, internlm2-pro-chat || **Reka** | reka-core, reka-flash, reka-edge || **COHERE** | command-r-plus, command-r, command-light, command, command-nightly |@@ -456,6 +456,41 @@ Integrate your favorite models into CAMEL-AI with straightforward Python calls.</Tabs>+## Using OpenAI-Compatible Models++If your provider exposes an OpenAI-compatible API, you can connect it by+using `OPENAI_COMPATIBLE_MODEL` and passing the model name as a string. This+lets you reuse the same request patterns while pointing to a different+endpoint.++```python+import os+from camel.agents import ChatAgent+from camel.models import ModelFactory+from camel.types import ModelPlatformType++model = ModelFactory.create(+ model_platform=ModelPlatformType.OPENAI_COMPATIBLE_MODEL,+ model_type="your-model-name", #e.g. "gpt-4o"+ url="https://your-openai-compatible-endpoint/v1",+ api_key=os.getenv("OPENAI_COMPATIBLE_API_KEY"),+ model_config_dict={"temperature": 0.2},+)++agent = ChatAgent(+ system_message="You are a helpful assistant.",+ model=model+)++response = agent.step("Explain quantum computing in simple terms.")+print(response.msg.content)+```++<Note type="info">+ Replace the model name, base URL, and API key with values provided by your+ OpenAI-compatible service.+</Note>+## Using On-Device Open Source Models