Z.ai · Text
Hermes Agent x GLM
GLM models from Z.ai are MIT-licensed MoE LLMs spanning 128K–200K context. GLM-5.1 leads open-weight models on SWE-bench Pro. Through RunAPI they share a single API key with pay-as-you-go token billing, callable from the OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages surfaces.
Public versions and endpoints
| Model ID | Version | Endpoints | Starting price | Catalog |
|---|---|---|---|---|
glm-4.5 | 355B / 32B active; 128K context; flagship open-weight MoE baseline | /v1/chat/completions | $0.0004 | Model detail |
glm-4.5-air | Lighter GLM-4.5 tier for fast, lower-cost everyday work | /v1/chat/completions | $0.0001 | Model detail |
glm-4.6 | 200K context; first GLM on Cambricon chips; sharper code generation | /v1/chat/completions | $0.0006 | Model detail |
glm-4.7 | 200K context; 73.8% SWE-bench; persistent thinking across turns | /v1/chat/completions | $0.0006 | Model detail |
glm-5 | 744B / 40B active; 200K context; 77.8% SWE-bench Verified | /v1/chat/completions | $0.0010 | Model detail |
glm-5-turbo | Speed-optimized GLM-5 tier for lower latency | /v1/chat/completions | $0.0012 | Model detail |
glm-5.1 | 754B / 40B active; 58.4% SWE-bench Pro — top open-weight score | /v1/chat/completions | $0.0014 | Model detail |
glm-5.2 | Current flagship foundation model for text generation | /v1/chat/completions | $0.0007 | Model detail |
Configuration
Guide endpoint: <endpoint>
Select <model-id> to generate a request with the endpoint's public input contract.Verify
Select <model-id> to generate verification commands.How it works
- 1. Choose a model ID
Select a public catalog model ID and review its endpoint and current starting price.
- 2. Configure RunAPI
Add the provider configuration for this agent.
- 3. Verify the result
Run the agent status and model-selection commands shown below.
FAQ
Which model ID should I use?
Choose a public model ID from the version table. Each ID exposes the endpoints shown for that version.
Does this guide configure a chat model?
Yes. This Model Line supports a client-facing LLM protocol.