• delete structured outputs (xgrammar) and fix ci build (#4856)latest11Docs270a7be2026-08-06 08:12

  Change detail

  2 changes across 1 operation and 1 model

  AllBreakingWarningInfo

  • POST/v1/chat/completions
    • warning

      removed the request property response_format

  • Models
    • info

      removed the schema ResponseFormat

• Add TTS streaming support to cpp_server (#4803)13Docs332bbca2026-08-05 19:51

  Change detail

  4 changes across 2 operations

  AllBreakingWarningInfo

  • GET/info
    • breaking

      removed the required property tt_blaze from the response with the 200 status

    • info

      added the required property model_service to the response with the 200 status

    • info

      added the required property tt_llm_engine to the response with the 200 status

  • POST/v1/audio/speech
    • info

      endpoint added

• 1.0.0no API changesDocs2026-07-17 12:12
• Remove responses api (#4228)13Docs54bef262026-06-16 09:41

  No leveled API changes in this revision.

• Remove /v1/models api (#4212)1Docs556c5fb2026-06-15 15:34

  Change detail

  1 change across 1 operation

  AllBreakingWarningInfo

  • GET/v1/models
    • breaking

      api path removed without deprecation

• Migrate image models to cpp_server (SDXL) (#3391)27Docs4edeb452026-05-15 11:05

  Change detail

  9 changes across 4 operations

  AllBreakingWarningInfo

  • GET/tt-liveness
    • warning

      removed the optional property workers from the response with the 200 status

    • warning

      removed the optional property workers from the response with the 500 status

    • info

      added the optional property runner_in_use to the response with the 200 status

    • info

      added the optional property runner_in_use to the response with the 500 status

    • info

      added the optional property worker_info to the response with the 200 status

    • info

      added the optional property worker_info to the response with the 500 status

  • POST/v1/images/edits
    • info

      endpoint added

  • POST/v1/images/generations
    • info

      endpoint added

  • POST/v1/images/image-to-image
    • info

      endpoint added

• Add V1 Responses Endpoint (#3007)1Docse3a5baa2026-05-08 13:56
• Controller initial cleanup (#3389)3Docs71dd1e42026-05-06 15:55
• Implement info controller for getting build versions across stack (#3308)1Docse27ad8e2026-05-06 13:08
• adding enable reasoning param (#3239)1Docs862b11b2026-04-29 11:28
• Set max session count through an API (#3208)2Docs97a62b32026-04-28 09:57
• spec1Docs0d6fba62026-04-16 11:03
• OpenAPI Spec Validation (#2957)1Docsaf7416a2026-04-15 17:36
• Support structured outputs (#2807)1Docs007df842026-04-15 08:11
• introduce openapi static json file (#2761)7616Docs14266702026-04-03 18:35

Revisions go back to the API's first capture.