Products

Individual rates and quotas:

Azure AI Foundry Limited-use product

  • Rate - 200K TPM

  • Monthly Quota - 4M tokens IN and 4M tokens OUT (8M total)

Azure AI Foundry Anthropic Limited-use product

  • Rate - 200K TPM

  • Monthly Quota - 4M tokens IN and 4M tokens OUT (8M total)

OpenAI Standard product

  • Rate - 100K TPM

  • Monthly Quota - 4M tokens IN and 4M tokens OUT (8M total)

Rate limits per deployment:

  • Claude-Sonnet-4-5 - 300K TPM

  • Claude-Opus-4-5 - 300K TPM

  • GPT-5.2 - 300K TPM

  • GPT-5.1 - 300K TPM

  • GPT-5.1-codex - 300K TPM

  • GPT-5-chat - 501K TPM

  • GPT-5-nano - 250K TPM

  • GPT-4.1 - 150,000 TPM

  • Text-Embedding-3-Large - 1M TPM

  • Text-Embedding-3-Small - 2.5M TPM