Models

All models below are available serverless. Models also included in standard Wafer Pass are marked with a Wafer Pass badge.

Quick start

1curl -sS "https://pass.wafer.ai/v1/chat/completions" \
2  -H "Authorization: Bearer <YOUR_API_KEY>" \
3  -H "Content-Type: application/json" \
4  -d '{
5    "model": "GLM-5.1",
6    "messages": [{"role": "user", "content": "Hello!"}],
7    "max_tokens": 128
8  }'

Use your Wafer API key as <YOUR_API_KEY> or set WAFER_API_KEY for SDK snippets. Manage keys on your Wafer API key.

Quick start

1curl -sS "https://pass.wafer.ai/v1/chat/completions" \
2  -H "Authorization: Bearer <YOUR_API_KEY>" \
3  -H "Content-Type: application/json" \
4  -d '{
5    "model": "Qwen3.5-397B-A17B",
6    "messages": [{"role": "user", "content": "Hello!"}],
7    "max_tokens": 128
8  }'

Use your Wafer API key as <YOUR_API_KEY> or set WAFER_API_KEY for SDK snippets. Manage keys on your Wafer API key.

Quick start

1curl -sS "https://pass.wafer.ai/v1/chat/completions" \
2  -H "Authorization: Bearer <YOUR_API_KEY>" \
3  -H "Content-Type: application/json" \
4  -d '{
5    "model": "Qwen3.6-35B-A3B",
6    "messages": [{"role": "user", "content": "Hello!"}],
7    "max_tokens": 128
8  }'

Use your Wafer API key as <YOUR_API_KEY> or set WAFER_API_KEY for SDK snippets. Manage keys on your Wafer API key.

More coming soon

New models added regularly. Stay tuned.

1curl -sS "https://pass.wafer.ai/v1/chat/completions" \ 2 -H "Authorization: Bearer <YOUR_API_KEY>" \ 3 -H "Content-Type: application/json" \ 4 -d '{ 5 "model": "GLM-5.1", 6 "messages": [{"role": "user", "content": "Hello!"}], 7 "max_tokens": 128 8 }'

1curl -sS "https://pass.wafer.ai/v1/chat/completions" \ 2 -H "Authorization: Bearer <YOUR_API_KEY>" \ 3 -H "Content-Type: application/json" \ 4 -d '{ 5 "model": "Qwen3.5-397B-A17B", 6 "messages": [{"role": "user", "content": "Hello!"}], 7 "max_tokens": 128 8 }'

1curl -sS "https://pass.wafer.ai/v1/chat/completions" \ 2 -H "Authorization: Bearer <YOUR_API_KEY>" \ 3 -H "Content-Type: application/json" \ 4 -d '{ 5 "model": "Qwen3.6-35B-A3B", 6 "messages": [{"role": "user", "content": "Hello!"}], 7 "max_tokens": 128 8 }'