AnyRouter SDK — Changelog

Release notes for the AnyRouter TypeScript SDK packages.

@anyr/sdk

Official TypeScript SDK for the AnyRouter API.

Unreleased

⚠ BREAKING CHANGES

• sdk: removed the cacheKey request option. The API no longer forwards a client cf-aig-cache-key (a custom key was shared across all callers of the gateway), so the option did nothing. cacheTtl and skipCache are unchanged.

🐛 Bug Fixes

• docs: error-handling table now lists every mapped status — added BadRequestError (400) and UnprocessableEntityError (422), and documents that AnyRouterError is the catch-all base class

🏗️ Internal

• declare "sideEffects": false so downstream bundlers can tree-shake unused resources — the SDK has no top-level side effects

1.0.4 (2026-11-04)

♻️ Refactoring

• sdk: drop section banner comments (fa700dc)

1.0.3 (2026-10-02)

🐛 Bug Fixes

• catalog: show BYOK-only models as billed by your provider, not $0 (#4125) (8e8e15d)

1.0.2 (2026-09-28)

✨ Features

• models: expose reasoning and completion metadata (#3511) (d3bebfe)

🐛 Bug Fixes

• release: repair version drift from stale release-please branch merges (#3555) (ff0a89f)

1.0.0 (2026-09-24)

✨ Features

• routing: honor exacto, tools, and 1M context on auto and presets (#2979) (1df73ef), closes #2978

⚡ Performance

• api: bound and trim the keys-list KV payload (#2597) (#3081) (8bd0a93)

1.0.1 (2026-09-24)

✨ Features

• routing: honor exacto, tools, and 1M context on auto and presets (#2979) (1df73ef), closes #2978

⚡ Performance

• api: bound and trim the keys-list KV payload (#2597) (#3081) (8bd0a93)

1.0.0 (2026-09-23)

✨ Features

• routing: honor exacto, tools, and 1M context on auto and presets (#2979) (1df73ef), closes #2978

⚡ Performance

• api: bound and trim the keys-list KV payload (#2597) (#3081) (8bd0a93)

1.0.0 (2026-08-28)

✨ Features

• api: add display_name to model objects for Claude Code gateway discovery (77520dd)
• errors: tell plan_required apart from out-of-credits in clients (4497f6a)

🐛 Bug Fixes

• catalog: default /models and GET /api/v1/models to reachable rows (#2354) (fe92824)

0.1.5 (2026-08-20)

✨ Features

• errors: tell plan_required apart from out-of-credits in clients (4497f6a)

🐛 Bug Fixes

• catalog: default /models and GET /api/v1/models to reachable rows (#2354) (fe92824)
• docs: title-case sidebar folders and slash model ids (55100ae)

0.1.4 (2026-08-01)

✨ Features

• sdk: cacheTtl/cacheKey/skipCache request options (1e2ff95)
• telemetry: email engagement tracking and client-type attribution (ebbdc9d)

0.1.3 (2026-06-18)

🐛 Bug Fixes

• transport: automatically retry transient failures — connection errors, timeouts, and 408/409/429/5xx responses — with exponential backoff + jitter, honoring Retry-After / Retry-After-Ms and the x-should-retry override header
• transport: per-request timeout (default 10 min) via AbortController, cleared once response headers arrive so it never aborts an in-progress stream
• per-request options on every resource method — signal, timeout, maxRetries, headers
• add APIUserAbortError, raised when the caller aborts via an AbortSignal (never retried)

0.1.2 (2026-06-18)

✨ Features

• initial public release of the official AnyRouter TypeScript SDK
• resources: chat completions, embeddings, images, models, credits, API keys, presets, the OpenAI Responses API, and the Anthropic Messages API
• typed request/response/error envelope, dependency-free SSE streaming, OpenRouter-style provider routing (provider, models, route, session_id)
• custom fetch implementation and per-client headers

@anyr/ai-sdk-provider

The AnyRouter provider for the Vercel AI SDK.

Unreleased

⚠ BREAKING CHANGES

• removed the cacheKey provider setting and providerOptions.anyrouter.cacheKey. The API no longer forwards a client cf-aig-cache-key (a custom key was shared across all callers of the gateway), so it did nothing. cacheTtl and skipCache are unchanged.

Bug Fixes

• a mid-stream data: {"error":{...}} frame now ends the stream with an error part (an APICallError that keeps the gateway code and message in responseBody) and finish reason error. Before, the frame was dropped and the turn ended as an empty answer.

1.0.3 (2026-11-04)

♻️ Refactoring

• ai-sdk-provider: drop section banner comments (82941d1)

Dependencies

• The following workspace dependencies were updated
  • dependencies
    • @anyr/sdk bumped from ^1.0.3 to ^1.0.4

1.0.2 (2026-10-02)

Dependencies

• The following workspace dependencies were updated
  • dependencies
    • @anyr/sdk bumped from ^1.0.2 to ^1.0.3

1.0.1 (2026-09-28)

🐛 Bug Fixes

• release: repair version drift from stale release-please branch merges (#3555) (ff0a89f)

Dependencies

• The following workspace dependencies were updated
  • dependencies
    • @anyr/sdk bumped from ^1.0.1 to ^1.0.2

1.0.0 (2026-09-24)

🐛 Bug Fixes

• sdk: align ai-sdk-provider range with workspace @anyr/sdk 1.0.0 (#2846) (7cd866e)
• sdk: restore ai-sdk-provider @anyr/sdk pin to workspace 1.0.0 (#3041) (1e14da4)

Dependencies

• The following workspace dependencies were updated
  • dependencies
    • @anyr/sdk bumped from ^1.0.1 to ^1.0.0

0.1.10 (2026-09-24)

Dependencies

• The following workspace dependencies were updated
  • dependencies
    • @anyr/sdk bumped from ^1.0.1 to ^1.0.0

0.1.9 (2026-09-24)

🐛 Bug Fixes

• sdk: restore ai-sdk-provider @anyr/sdk pin to workspace 1.0.0 (#3041) (1e14da4)

Dependencies

• The following workspace dependencies were updated
  • dependencies
    • @anyr/sdk bumped from ^1.0.0 to ^1.0.1

0.1.8 (2026-09-04)

🐛 Bug Fixes

• sdk: align ai-sdk-provider range with workspace @anyr/sdk 1.0.0 (#2846) (7cd866e)

Dependencies

• The following workspace dependencies were updated
  • dependencies
    • @anyr/sdk bumped from ^1.0.0 to ^0.1.6

0.1.7 (2026-08-20)

Dependencies

• The following workspace dependencies were updated
  • dependencies
    • @anyr/sdk bumped from ^0.1.3 to ^0.1.5

0.1.5 (2026-07-31)

✨ Features

• ai-sdk-provider: cache passthrough options (4090989)
• telemetry: email engagement tracking and client-type attribution (ebbdc9d)

Dependencies

• The following workspace dependencies were updated
  • dependencies
    • @anyr/sdk bumped from ^0.1.1 to ^0.1.4

0.1.4 (2026-06-18)

🐛 Bug Fixes

• surface reasoning_content from reasoning models (DeepSeek-R1, GLM thinking, …) as the AI SDK's standard reasoning parts — reasoning / reasoningText and the full-stream reasoning-start / reasoning-delta / reasoning-end parts now work

0.1.3 (2026-06-18)

✨ Features

• support the Vercel AI SDK v7 (beta) alongside v6 — widened ai, @ai-sdk/provider, and @ai-sdk/provider-utils peer ranges

0.1.2 (2026-06-18)

✨ Features

• initial public release of the AnyRouter provider for the Vercel AI SDK
• createAnyRouter() / anyrouter — chat (LanguageModelV3), embeddings, and image models
• tool calling, structured output, streaming, and provider routing / session_id / extraBody passthrough via provider settings and per-call providerOptions.anyrouter