GLM 5.2
FP4
ZDR
- Context
- 1.0M
- Input /M
- $0.0063/M
- Output /M
- $7.14/M
- Cache read /M
- $0.00525/M
- TTFT
- 0.5s
- Throughput
- 130 tps
Wafer US
US
4 models available
All available routes ZDR
Privacy can differ by model. See each model’s label.
Models served by Wafer US
ZDR
- Context
- 1.0M
- Input /M
- $0.0063/M
- Output /M
- $7.14/M
- Cache read /M
- $0.00525/M
- TTFT
- 0.5s
- Throughput
- 130 tps
GLM 5.3
FP4
ZDR
- Context
- 1.0M
- Input /M
- $0.0734/M
- Output /M
- $1.47/M
- Cache read /M
- $0.0723/M
- TTFT
- 0.4s
- Throughput
- 123 tps
ZDR
- Context
- 1.0M
- Input /M
- $0.0734/M
- Output /M
- $1.47/M
- Cache read /M
- $0.0723/M
- TTFT
- 0.4s
- Throughput
- 123 tps
Prices are per million tokens. TTFT is the observed time to first token. Selectable routes include the applicable provider-selection markup; fixed routes show the standard model price. Availability and pricing refresh continuously; each model page shows the live provider comparison.
Using Wafer US via the API
Call a model served by Wafer US using its displayed model ID, including the provider suffix when selection is supported.
cURL
curl https://nano-gpt.com/api/v1/chat/completions \
-H "Authorization: Bearer $NANOGPT_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "z-ai/glm-5.2:wafer-us",
"messages": [{"role": "user", "content": "Hello"}]
}'For models with provider selection, append :wafer-us to the model ID, set "provider": "wafer-us" in the request body, or send an X-Provider: wafer-us header. Explicit provider selection adds a route-specific markup over that provider's base price; the prices in the table above already include it. Models without provider selection use the displayed model ID without a provider suffix or selection surcharge.
See the API documentation for provider preferences, price-aware routing, and error behavior.