Mistral Large 3

curl https://api.therouter.ai/v1/chat/completions \
  -H "Authorization: Bearer $THEROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistral/mistral-large-3",
    "messages": [{"role": "user", "content": "Explain sparse MoE architectures to a junior developer."}]
  }'

curl https://api.therouter.ai/v1/chat/completions \
  -H "Authorization: Bearer $THEROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistral/mistral-large-3",
    "stream": true,
    "messages": [{"role": "user", "content": "Write a 50-word haiku about GPU clusters."}]
  }'

curl https://api.therouter.ai/v1/chat/completions \
  -H "Authorization: Bearer $THEROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistral/mistral-large-3",
    "messages": [{"role": "user", "content": "What is the weather in Paris?"}],
    "tools": [{
      "type": "function",
      "function": {
        "name": "get_weather",
        "parameters": {"type": "object", "properties": {"city": {"type": "string"}}}
      }
    }]
  }'

curl https://api.therouter.ai/v1/chat/completions \
  -H "Authorization: Bearer $THEROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistral/mistral-large-3",
    "response_format": {"type": "json_object"},
    "messages": [
      {"role": "system", "content": "Return JSON with fields: name, age, department."},
      {"role": "user", "content": "Extract employee info from this email..."}
    ]
  }'

# Reference vLLM launch. See HF model card for exact tensor-parallel sizing.
python -m vllm.entrypoints.openai.api_server \
  --model mistralai/Mistral-Large-3 \
  --tensor-parallel-size 8 \
  --port 8000

# Then call it through TheRouter as model="mistral/mistral-large-3"
# with TheRouter configured to use your self-hosted endpoint as the upstream.