GLM 4.7 Flash

curl https://api.therouter.ai/v1/chat/completions \
  -H "Authorization: Bearer $THEROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "zhipu/glm-4.7-flash",
    "messages": [{"role": "user", "content": "Explain MoE architectures in one paragraph."}]
  }'

curl https://api.therouter.ai/v1/chat/completions \
  -H "Authorization: Bearer $THEROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "zhipu/glm-4.7-flash",
    "messages": [{"role": "user", "content": "What is the weather in Shanghai?"}],
    "tools": [{
      "type": "function",
      "function": {
        "name": "get_weather",
        "description": "Get current weather for a city",
        "parameters": {
          "type": "object",
          "properties": {"city": {"type": "string"}},
          "required": ["city"]
        }
      }
    }],
    "tool_choice": "auto"
  }'

curl https://api.therouter.ai/v1/chat/completions \
  -H "Authorization: Bearer $THEROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "zhipu/glm-4.7-flash",
    "stream": true,
    "messages": [{"role": "user", "content": "Write a bubble sort in TypeScript."}]
  }'

# Start local vLLM server (requires vLLM main branch)
vllm serve zai-org/GLM-4.7-Flash \
  --tensor-parallel-size 1 \
  --speculative-config.method mtp \
  --speculative-config.num_speculative_tokens 1 \
  --tool-call-parser glm47 \
  --reasoning-parser glm45 \
  --enable-auto-tool-choice \
  --served-model-name glm-4.7-flash

# Then call it like any OpenAI endpoint
curl http://localhost:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"model":"glm-4.7-flash","messages":[{"role":"user","content":"Hello"}]}'