Llama 3.3 70B

Models

Model details

Llama 3.3 70B

Model
meta-llama/Llama-3.3-70B-Instruct-Turbo
Provider
together
API
openai-completions
Base URL
https://api.together.ai/v1
Input
text
Reasoning
No
Context window
131,072
Max tokens
131,072
Cost / million input
$0.88
Cost / million output
$0.88
Cost / million cache read
$0
Cost / million cache write
$0

Also available from other providers

Model config JSON
{
  "providers": {
    "together": {
      "apiKey": "YOUR_API_KEY",
      "models": [
        {
          "id": "meta-llama/Llama-3.3-70B-Instruct-Turbo",
          "name": "Llama 3.3 70B",
          "reasoning": false,
          "input": [
            "text"
          ],
          "contextWindow": 131072,
          "maxTokens": 131072,
          "cost": {
            "input": 0.88,
            "output": 0.88,
            "cacheRead": 0,
            "cacheWrite": 0
          },
          "compat": {
            "supportsStore": false,
            "supportsDeveloperRole": false,
            "supportsReasoningEffort": false,
            "maxTokensField": "max_tokens",
            "supportsStrictMode": false,
            "supportsLongCacheRetention": false
          }
        }
      ],
      "api": "openai-completions",
      "baseUrl": "https://api.together.ai/v1"
    }
  }
}