{
  "title": "AI API rate limits and tiers",
  "url": "https://ernd.ai/ai-api-rate-limits",
  "checked": "2026-11-02",
  "vendors": [
    {
      "id": "openai",
      "name": "OpenAI",
      "moves_up": "Automatic, on total credit purchases",
      "top_tier": "Grow at $500 purchased",
      "top_monthly_cap": "$200,000 a month",
      "how_to_get_more": "Upgrade tier button. For enterprises, Scale Tier or Reserved Tier",
      "source_url": "https://developers.openai.com/api/docs/guides/rate-limits",
      "table": {
        "columns": [
          "Tier",
          "Total credit purchases",
          "Monthly usage limit",
          "Astra, Sol, Terra RPM",
          "Astra, Sol, Terra TPM"
        ],
        "rows": [
          [
            "Free",
            "Allowed geography",
            "$100",
            "None listed",
            "None listed"
          ],
          [
            "Build",
            "$5",
            "$500",
            "5,000",
            "1,000,000"
          ],
          [
            "Launch",
            "$100",
            "$5,000",
            "10,000",
            "4,000,000"
          ],
          [
            "Grow",
            "$500",
            "$200,000",
            "15,000",
            "40,000,000"
          ]
        ]
      },
      "notes": [
        {
          "text": "If traffic keeps hitting ramp-rate limits, OpenAI points enterprise customers at Scale Tier, or Reserved Tier for GPT-5.6 and later.",
          "source_url": "https://developers.openai.com/api/docs/guides/rate-limits"
        }
      ]
    },
    {
      "id": "anthropic",
      "name": "Anthropic",
      "moves_up": "Automatic, on usage history and account standing",
      "top_tier": "Scale, no published threshold",
      "top_monthly_cap": "$200,000 a month",
      "how_to_get_more": "Request tier increase in the Console, then sales",
      "source_url": "https://platform.claude.com/docs/en/api/rate-limits",
      "table": {
        "columns": [
          "Tier",
          "Monthly spend cap",
          "Opus 5.5 RPM",
          "Opus 5.5 input TPM",
          "Opus 5.5 output TPM"
        ],
        "rows": [
          [
            "Start",
            "$500",
            "4,000",
            "2,000,000",
            "400,000"
          ],
          [
            "Build",
            "$1,000",
            "10,000",
            "5,000,000",
            "1,000,000"
          ],
          [
            "Scale",
            "$200,000",
            "13,000",
            "10,000,000",
            "2,000,000"
          ],
          [
            "Custom",
            "None",
            "Set with sales",
            "Set with sales",
            "Set with sales"
          ]
        ]
      },
      "notes": [
        {
          "text": "Hit the spend cap and usage pauses until the first of next month, unless you get a higher limit sooner.",
          "source_url": "https://platform.claude.com/docs/en/api/rate-limits"
        },
        {
          "text": "On most Claude models, tokens read from the prompt cache don't count toward input TPM.",
          "source_url": "https://platform.claude.com/docs/en/api/rate-limits"
        },
        {
          "text": "New Priority Tier commitments are no longer sold. For guaranteed capacity, Anthropic says to contact sales.",
          "source_url": "https://platform.claude.com/docs/en/api/service-tiers"
        }
      ]
    },
    {
      "id": "gemini",
      "name": "Google Gemini API",
      "moves_up": "Automatic, on spend plus days since first payment",
      "top_tier": "Tier 3 at $1,000 paid and 30 days",
      "top_monthly_cap": "$20,000 to $100,000+ a month",
      "how_to_get_more": "Request form, no guarantee",
      "source_url": "https://ai.google.dev/gemini-api/docs/rate-limits",
      "table": {
        "columns": [
          "Tier",
          "You get there at",
          "Monthly cap",
          "Spend limit per 10 minutes"
        ],
        "rows": [
          [
            "Free",
            "Active project or free trial",
            "None listed",
            "None listed"
          ],
          [
            "Tier 1",
            "Linked active billing account",
            "$250",
            "$10"
          ],
          [
            "Tier 2",
            "$100 paid, 3 days after first payment",
            "$2,000",
            "$50"
          ],
          [
            "Tier 3",
            "$1,000 paid, 30 days after first payment",
            "$20,000 to $100,000+",
            "$200"
          ]
        ]
      },
      "notes": [
        {
          "text": "Reach the monthly cap and service pauses for every project on that billing account until the next billing cycle.",
          "source_url": "https://ai.google.dev/gemini-api/docs/billing"
        }
      ]
    },
    {
      "id": "xai",
      "name": "xAI",
      "moves_up": "Automatic, on spend since January 1, 2026",
      "top_tier": "Tier 4 at $5,000 spent",
      "top_monthly_cap": "None listed",
      "how_to_get_more": "Console request, or Enterprise through sales",
      "source_url": "https://docs.x.ai/developers/rate-limits",
      "table": {
        "columns": [
          "Tier",
          "Cumulative spend",
          "grok-4.7 RPS",
          "grok-4.7 TPM"
        ],
        "rows": [
          [
            "Tier 0",
            "$0",
            "150",
            "50M"
          ],
          [
            "Tier 1",
            "$50",
            "172",
            "53M"
          ],
          [
            "Tier 2",
            "$250",
            "208",
            "60M"
          ],
          [
            "Tier 3",
            "$1,000",
            "312",
            "74M"
          ],
          [
            "Tier 4",
            "$5,000",
            "500",
            "100M"
          ]
        ]
      },
      "notes": [
        {
          "text": "Cached prompt tokens still count toward TPM on xAI, even though they're billed at a lower rate.",
          "source_url": "https://docs.x.ai/developers/rate-limits"
        }
      ]
    },
    {
      "id": "mistral",
      "name": "Mistral",
      "moves_up": "No published tiers",
      "top_tier": "None listed",
      "top_monthly_cap": "Set by your organization",
      "how_to_get_more": "Contact support with your targets",
      "source_url": "https://docs.mistral.ai/admin/billing-usage/usage-limits",
      "table": null,
      "notes": [
        {
          "text": "If the organization reaches its monthly spending limit, API access can be suspended until the next month or until an admin raises it.",
          "source_url": "https://docs.mistral.ai/admin/billing-usage/usage-limits"
        }
      ]
    },
    {
      "id": "azure",
      "name": "Azure OpenAI",
      "moves_up": "Automatic, on consumption and your Microsoft relationship",
      "top_tier": "Tier 6, no published threshold",
      "top_monthly_cap": "None listed",
      "how_to_get_more": "Quota request form",
      "source_url": "https://learn.microsoft.com/en-us/azure/foundry/openai/quotas-limits",
      "table": {
        "columns": [
          "Tier",
          "gpt-6-sol Global Standard RPM",
          "gpt-6-sol Global Standard TPM"
        ],
        "rows": [
          [
            "Tier 1",
            "250",
            "250,000"
          ],
          [
            "Tier 2",
            "1,000",
            "1,000,000"
          ],
          [
            "Tier 3",
            "2,500",
            "2,500,000"
          ],
          [
            "Tier 4",
            "7,000",
            "7,000,000"
          ],
          [
            "Tier 5",
            "10,000",
            "10,000,000"
          ],
          [
            "Tier 6",
            "15,000",
            "15,000,000"
          ]
        ]
      },
      "notes": [
        {
          "text": "You can opt out of automatic upgrades if you use quota to control billing. Microsoft marks this as a preview that may change.",
          "source_url": "https://learn.microsoft.com/en-us/azure/foundry/openai/quotas-limits"
        }
      ]
    },
    {
      "id": "bedrock",
      "name": "Amazon Bedrock",
      "moves_up": "No tiers, quotas per model and Region",
      "top_tier": "None listed",
      "top_monthly_cap": "None listed",
      "how_to_get_more": "Service Quotas request, or an AWS Support case",
      "source_url": "https://docs.aws.amazon.com/bedrock/latest/userguide/quotas.html",
      "table": null,
      "notes": [
        {
          "text": "Increases go first to customers whose traffic consumes their existing quota, and a request can be denied otherwise.",
          "source_url": "https://docs.aws.amazon.com/bedrock/latest/userguide/quotas-runtime.html"
        },
        {
          "text": "AWS doesn't grant increases for models in Legacy or Deprecated status.",
          "source_url": "https://docs.aws.amazon.com/bedrock/latest/userguide/quotas-runtime.html"
        },
        {
          "text": "The two endpoints, bedrock-runtime and bedrock-mantle, track quotas separately, and mantle increases go through an AWS Support form.",
          "source_url": "https://docs.aws.amazon.com/bedrock/latest/userguide/quotas-mantle.html"
        }
      ]
    },
    {
      "id": "cohere",
      "name": "Cohere",
      "moves_up": "Switch from a trial key to a production key",
      "top_tier": "Production key",
      "top_monthly_cap": "None listed",
      "how_to_get_more": "Email support or sales",
      "source_url": "https://docs.cohere.com/docs/rate-limits",
      "table": {
        "columns": [
          "Model",
          "Trial key",
          "Production key"
        ],
        "rows": [
          [
            "Command A",
            "20 req/min",
            "500 req/min"
          ],
          [
            "Command A Reasoning",
            "20 req/min",
            "Contact sales"
          ]
        ]
      },
      "notes": [
        {
          "text": "Trial keys are limited to 1,000 API calls a month.",
          "source_url": "https://docs.cohere.com/docs/rate-limits"
        }
      ]
    },
    {
      "id": "groq",
      "name": "Groq",
      "moves_up": "Upgrade to the Developer plan",
      "top_tier": "Developer plan",
      "top_monthly_cap": "None listed",
      "how_to_get_more": "Higher limits for select workloads",
      "source_url": "https://console.groq.com/docs/rate-limits",
      "table": {
        "columns": [
          "Plan",
          "gpt-oss-120b RPM",
          "Requests a day",
          "TPM",
          "Tokens a day"
        ],
        "rows": [
          [
            "Free",
            "30",
            "1K",
            "8K",
            "200K"
          ],
          [
            "Developer",
            "1K",
            "500K",
            "250K",
            "None listed"
          ]
        ]
      },
      "notes": []
    },
    {
      "id": "fireworks",
      "name": "Fireworks AI",
      "moves_up": "Automatic, on credits added or spend",
      "top_tier": "Tier 4 at $5,000",
      "top_monthly_cap": "Prepaid accounts set their own limit",
      "how_to_get_more": "Contact Fireworks for Unlimited",
      "source_url": "https://docs.fireworks.ai/guides/quotas_usage/account-quotas",
      "table": {
        "columns": [
          "Tier",
          "You get there at",
          "Legacy postpaid monthly cap"
        ],
        "rows": [
          [
            "Tier 1",
            "Valid payment method and billing profile",
            "$50"
          ],
          [
            "Tier 2",
            "$50 in spend or credits",
            "$500"
          ],
          [
            "Tier 3",
            "$500 in spend or credits",
            "$5,000"
          ],
          [
            "Tier 4",
            "$5,000 in spend or credits",
            "$50,000"
          ],
          [
            "Unlimited",
            "Contact Fireworks",
            "Unlimited"
          ]
        ]
      },
      "notes": [
        {
          "text": "All API usage on an account shares one ceiling of 6,000 requests a minute, or 10 with no payment method or no credits.",
          "source_url": "https://docs.fireworks.ai/guides/quotas_usage/account-quotas"
        }
      ]
    },
    {
      "id": "together",
      "name": "Together AI",
      "moves_up": "No published tiers",
      "top_tier": "None listed",
      "top_monthly_cap": "None listed",
      "how_to_get_more": "Provisioned throughput through sales",
      "source_url": "https://docs.together.ai/docs/serverless/rate-limits",
      "table": null,
      "notes": [
        {
          "text": "When a model is in especially high demand, Together may apply custom limits to that model.",
          "source_url": "https://docs.together.ai/docs/serverless/rate-limits"
        }
      ]
    },
    {
      "id": "perplexity",
      "name": "Perplexity",
      "moves_up": "Automatic, on credits purchased",
      "top_tier": "Tier 5 at $5,000 purchased",
      "top_monthly_cap": "None listed",
      "how_to_get_more": "Rate limit increase form",
      "source_url": "https://docs.perplexity.ai/docs/admin/rate-limits-usage-tiers",
      "table": {
        "columns": [
          "Tier",
          "Total credits purchased"
        ],
        "rows": [
          [
            "Tier 0",
            "$0"
          ],
          [
            "Tier 1",
            "$50+"
          ],
          [
            "Tier 2",
            "$250+"
          ],
          [
            "Tier 3",
            "$500+"
          ],
          [
            "Tier 4",
            "$1,000+"
          ],
          [
            "Tier 5",
            "$5,000+"
          ]
        ]
      },
      "notes": []
    },
    {
      "id": "cerebras",
      "name": "Cerebras",
      "moves_up": "First credit purchase moves you to Developer",
      "top_tier": "Developer, pay as you go",
      "top_monthly_cap": "None listed",
      "how_to_get_more": "Contact Cerebras for Enterprise limits",
      "source_url": "https://inference-docs.cerebras.ai/support/rate-limits",
      "table": {
        "columns": [
          "Tier",
          "gpt-oss-120b RPM",
          "Uncached TPM",
          "Total TPM"
        ],
        "rows": [
          [
            "Free Trial",
            "5",
            "30K",
            "90K"
          ],
          [
            "Developer",
            "1K",
            "1M",
            "3M"
          ],
          [
            "Enterprise",
            "Set per organization",
            "Set per organization",
            "Set per organization"
          ]
        ]
      },
      "notes": []
    }
  ],
  "changelog": [
    {
      "date": "2026-11-02",
      "text": "First version, 13 vendors. Anthropic no longer sells new Priority Tier commitments. OpenAI's paid tiers are Build, Launch and Grow, so older tier numbers won't match."
    }
  ]
}