axond 0.3.39

Axond — a stateless, single-binary, self-hosted AI gateway: one place for provider keys, model routing, usage, and telemetry.
Documentation
{
  "models": {
    "openai/gpt-5.5": {
      "id": "openai/gpt-5.5",
      "name": "GPT-5.5",
      "description": "Default frontier GPT for coding, computer use, research, and knowledge work",
      "family": "gpt",
      "attachment": true,
      "reasoning": true,
      "tool_call": true,
      "structured_output": true,
      "temperature": false,
      "knowledge": "2025-12-01",
      "release_date": "2026-04-23",
      "last_updated": "2026-04-23",
      "modalities": {
        "input": [
          "text",
          "image",
          "pdf"
        ],
        "output": [
          "text"
        ]
      },
      "open_weights": false,
      "limit": {
        "context": 1050000,
        "input": 922000,
        "output": 128000
      },
      "benchmarks": [
        {
          "name": "SWE-Bench Pro",
          "score": 58.6,
          "metric": "resolve rate",
          "source": "https://www.anthropic.com/news/claude-opus-4-8",
          "date": "2026-05-28"
        },
        {
          "name": "Terminal-Bench",
          "score": 78.2,
          "metric": "success rate",
          "harness": "Terminus-2",
          "version": "2.1",
          "source": "https://www.anthropic.com/news/claude-opus-4-8",
          "date": "2026-05-28"
        }
      ]
    }
  },
  "providers": {
    "openai": {
      "id": "openai",
      "env": [
        "OPENAI_API_KEY"
      ],
      "npm": "@ai-sdk/openai",
      "name": "OpenAI",
      "doc": "https://platform.openai.com/docs/models",
      "models": {
        "gpt-4o": {
          "id": "gpt-4o",
          "name": "GPT-4o",
          "description": "Omni-era GPT for multimodal chat, practical coding, and general assistants",
          "family": "gpt",
          "attachment": true,
          "reasoning": false,
          "tool_call": true,
          "structured_output": true,
          "temperature": true,
          "knowledge": "2023-09",
          "release_date": "2024-05-13",
          "last_updated": "2024-08-06",
          "modalities": {
            "input": [
              "text",
              "image",
              "pdf"
            ],
            "output": [
              "text"
            ]
          },
          "open_weights": false,
          "limit": {
            "context": 128000,
            "output": 16384
          },
          "cost": {
            "input": 2.5,
            "output": 10,
            "cache_read": 1.25
          }
        },
        "gpt-5.5": {
          "id": "gpt-5.5",
          "name": "GPT-5.5",
          "description": "Default frontier GPT for coding, computer use, research, and knowledge work",
          "family": "gpt",
          "attachment": true,
          "reasoning": true,
          "reasoning_options": [
            {
              "type": "effort",
              "values": [
                "none",
                "low",
                "medium",
                "high",
                "xhigh"
              ]
            }
          ],
          "tool_call": true,
          "structured_output": true,
          "temperature": false,
          "knowledge": "2025-12-01",
          "release_date": "2026-04-23",
          "last_updated": "2026-04-23",
          "modalities": {
            "input": [
              "text",
              "image",
              "pdf"
            ],
            "output": [
              "text"
            ]
          },
          "open_weights": false,
          "limit": {
            "context": 1050000,
            "input": 922000,
            "output": 128000
          },
          "experimental": {
            "modes": {
              "fast": {
                "cost": {
                  "input": 12.5,
                  "output": 75,
                  "cache_read": 1.25
                },
                "provider": {
                  "body": {
                    "service_tier": "priority"
                  }
                }
              }
            }
          },
          "cost": {
            "input": 5,
            "output": 30,
            "cache_read": 0.5,
            "tiers": [
              {
                "input": 10,
                "output": 45,
                "cache_read": 1,
                "tier": {
                  "type": "context",
                  "size": 272000
                }
              }
            ],
            "context_over_200k": {
              "input": 10,
              "output": 45,
              "cache_read": 1
            }
          }
        }
      }
    },
    "anthropic": {
      "id": "anthropic",
      "env": [
        "ANTHROPIC_API_KEY"
      ],
      "npm": "@ai-sdk/anthropic",
      "name": "Anthropic",
      "doc": "https://docs.anthropic.com/en/docs/about-claude/models",
      "models": {
        "claude-sonnet-4-5": {
          "id": "claude-sonnet-4-5",
          "name": "Claude Sonnet 4.5 (latest)",
          "description": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
          "family": "claude-sonnet",
          "attachment": true,
          "reasoning": true,
          "reasoning_options": [
            {
              "type": "budget_tokens",
              "min": 1024
            }
          ],
          "tool_call": true,
          "structured_output": true,
          "temperature": true,
          "knowledge": "2025-07-31",
          "release_date": "2025-09-29",
          "last_updated": "2025-09-29",
          "modalities": {
            "input": [
              "text",
              "image",
              "pdf"
            ],
            "output": [
              "text"
            ]
          },
          "open_weights": false,
          "limit": {
            "context": 1000000,
            "output": 64000
          },
          "cost": {
            "input": 3,
            "output": 15,
            "cache_read": 0.3,
            "cache_write": 3.75
          }
        }
      }
    },
    "azure": {
      "id": "azure",
      "env": [
        "AZURE_RESOURCE_NAME",
        "AZURE_API_KEY"
      ],
      "npm": "@ai-sdk/azure",
      "name": "Azure",
      "doc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models",
      "models": {
        "gpt-4o": {
          "id": "gpt-4o",
          "name": "GPT-4o",
          "description": "Omni-era GPT for multimodal chat, practical coding, and general assistants",
          "family": "gpt",
          "attachment": true,
          "reasoning": false,
          "tool_call": true,
          "temperature": true,
          "knowledge": "2023-09",
          "release_date": "2024-05-13",
          "last_updated": "2024-08-06",
          "modalities": {
            "input": [
              "text",
              "image"
            ],
            "output": [
              "text"
            ]
          },
          "open_weights": false,
          "limit": {
            "context": 128000,
            "output": 16384
          },
          "status": "deprecated",
          "cost": {
            "input": 2.5,
            "output": 10,
            "cache_read": 1.25
          }
        }
      }
    },
    "hpc-ai": {
      "id": "hpc-ai",
      "env": [
        "HPC_AI_API_KEY"
      ],
      "npm": "@ai-sdk/openai-compatible",
      "api": "https://api.hpc-ai.com/inference/v1",
      "name": "HPC-AI",
      "doc": "https://www.hpc-ai.com/doc/docs/quickstart/",
      "models": {
        "openai/gpt-5.5": {
          "id": "openai/gpt-5.5",
          "name": "GPT-5.5",
          "description": "Default frontier GPT for coding, computer use, research, and knowledge work",
          "family": "gpt",
          "attachment": true,
          "reasoning": true,
          "reasoning_options": [
            {
              "type": "effort",
              "values": [
                "none",
                "low",
                "medium",
                "high"
              ]
            }
          ],
          "tool_call": true,
          "structured_output": true,
          "temperature": true,
          "interleaved": {
            "field": "reasoning_content"
          },
          "knowledge": "2025-12-01",
          "release_date": "2026-04-23",
          "last_updated": "2026-04-23",
          "modalities": {
            "input": [
              "text",
              "image"
            ],
            "output": [
              "text"
            ]
          },
          "open_weights": false,
          "limit": {
            "context": 1050000,
            "input": 922000,
            "output": 128000
          },
          "cost": {
            "input": 5,
            "output": 30,
            "cache_read": 0.5,
            "tiers": [
              {
                "input": 10,
                "output": 45,
                "cache_read": 1,
                "tier": {
                  "type": "context",
                  "size": 272000
                }
              }
            ],
            "context_over_200k": {
              "input": 10,
              "output": 45,
              "cache_read": 1
            }
          }
        }
      }
    }
  }
}