GLM uses the same gd-… key and shared Guard balance. The public catalog contains exactly two models: GLM 5.3 (glm-5.3) and GLM 5.3 Flash (glm-5.3-flash); setup guides default to glm-5.3.
| Model | Input | Format status |
|---|---|---|
glm-5.3 | Text | Text contract |
glm-5.3-flash | Text, images, PDF; MP4 in Chat | PNG and PDF were read through all three protocols; MP4 video is confirmed through Chat only; native TXT, DOCX, and XLSX are not confirmed |
| API | Shared route | Family route |
|---|---|---|
| Messages | POST /v1/messages | POST /glm/v1/messages |
| Chat Completions | POST /v1/chat/completions | POST /glm/v1/chat/completions |
| Responses | POST /v1/responses | POST /glm/v1/responses |
bash
curl https://api.guardrelay.ai/glm/v1/messages \
-H "Authorization: Bearer $GUARD_API_KEY" \
-H "anthropic-version: 2023-06-01" \
-H "content-type: application/json" \
-d '{"model":"glm-5.3","max_tokens":128,"messages":[{"role":"user","content":"Reply with OK"}]}'bash
curl https://api.guardrelay.ai/glm/v1/chat/completions \
-H "Authorization: Bearer $GUARD_API_KEY" \
-H "content-type: application/json" \
-d '{"model":"glm-5.3","messages":[{"role":"user","content":"Reply with OK"}],"stream":true}'bash
curl https://api.guardrelay.ai/glm/v1/responses \
-H "Authorization: Bearer $GUARD_API_KEY" \
-H "content-type: application/json" \
-d '{"model":"glm-5.3","input":"Reply with OK","max_output_tokens":128,"store":false}'| Model ID | Input / 1M | Cache read / 1M | Output / 1M | Web search |
|---|---|---|---|---|
glm-5.3 | $1.40 | $0.26 | $4.40 | $0.10 / confirmed call |
glm-5.3-flash | $0.15 | $0.03 | $0.50 | $0.10 / confirmed call |
The multiplier is 1, including PRIVATE. An applied server prompt is part of actual billable input. Messages reports input excluding cache reads, while Chat and Responses include cache in total input; Guard normalizes these shapes without subtracting cache twice.
bash
curl https://api.guardrelay.ai/glm/v1/messages/count_tokens \
-H "Authorization: Bearer $GUARD_API_KEY" \
-H "anthropic-version: 2023-06-01" \
-H "content-type: application/json" \
-d '{"model":"glm-5.3","messages":[{"role":"user","content":"Count this text"}]}'- Responses defaults to
store: trueand preserves explicitstore: false. previous_response_idcontinues only with the same Guard key and provider account. If that account is unavailable, Guard returns an explicit error before reserve and does not move state to another account.- The GLM server prompt is off by default. Applying it requires a separate entitlement, an enabled toggle, and an active server revision. Model replacement is also off by default and is limited to GLM requests with an applied prompt.