Skip to content

FreeLLMAPI Release Notes

A local OpenAI-compatible router that puts free LLM models from many providers behind one key, with smart routing, automatic failover and encrypted keys.

CaskDeveloper ToolsAuto-updates 56.1K
Install command
brew install --cask freellmapi
30-day installs
94
#971 in App
1-year installs
94
Last 365 days
Latest version
0.16.38
Download size
127MB
dmg
Release cadence
Daily
29 releases in 30 days
  1. 0.16.38

    LatestPatch

    OpenNavo editorial Added to Homebrew

    CompatibilitymacOS 12 or later

    FreeLLMAPI 0.16.38 adds native Puter chat with pinned model IDs, plus image generation, WAV transcription, translation and extraction.

    Puter
    原生 Puter 聊天固定模型 ID。拒绝后不再回退到其他模型。
    新能力
    新增 AI Horde 和 xKiro 生图。新增 Google Live WAV 转写。翻译和抽取不是普通聊天路由。

    FreeLLMAPI 0.16.38, released 21 November 2026, gives people routing free chat models a native Puter chat that pins model IDs and does not fall back after a refusal, using a dedicated free Puter account token.

    Source: https://github.com/tashfeenahmed/freellmapi/releases/tag/v0.16.38

    • Native Puter chat pins model IDs and does not fall back after a refusal. Use a dedicated free Puter account token.
    • Adds AI Horde and xKiro image generation.
    • Adds Google Live WAV transcription.
    • Adds explicit xKiro and Cloudflare translation, and Clairic Flash extraction. Translation and extraction are not ordinary chat routes.
    • Existing signed-catalog access tiers and the 30-day promotion are unchanged.
  2. 0.16.37

    Patch

    OpenNavo editorial Added to Homebrew

    CompatibilitymacOS 12 or later

    FreeLLMAPI 0.16.37, for people routing local and hosted models through one OpenAI-compatible app, adds cheapllm.shop and fails over when a provider returns only an error body.

    Providers
    cheapllm.shop is a provider: one free model, DeepSeek V4.1 Flash 1017.That model supports tools, JSON schema and images. Add the key on the Keys page.The model row is Premium now and Free after 30 days, through the hosted catalog.
    Routing
    An HTTP 200 that is only an error body now fails over with the right cooldown.That response no longer counts as an empty answer.

    FreeLLMAPI 0.16.37, for people routing local and hosted models through one OpenAI-compatible app, adds cheapllm.shop and fails over when a provider returns only an error body.

  3. 0.16.36

    Patch

    OpenNavo editorial Added to Homebrew

    CompatibilitymacOS 12 or later

    FreeLLMAPI 0.16.36 adds translate and summarize endpoints that stay out of general chat and automatic fallback.

    Endpoints
    GET /v1/text/models lists translation and summary models.POST /v1/text/translate translates text.POST /v1/text/summarize summarizes text.These routes stay out of chat and automatic fallback.
    Catalog
    The Premium and 30-day Free schedule is unchanged.

    FreeLLMAPI 0.16.36, released 19 November 2026, adds explicit translation and summarization endpoints that stay out of general chat and automatic fallback. Source: https://github.com/tashfeenahmed/freellmapi/releases/tag/v0.16.36

    • GET /v1/text/models lists the models that can translate or summarize.
    • POST /v1/text/translate translates text.
    • POST /v1/text/summarize summarizes text.
    • These routes stay out of general chat and automatic fallback.
    • The Premium and 30-day Free catalog schedule is unchanged. See https://github.com/tashfeenahmed/freellmapi/pull/2009
  4. 0.16.34

    Expand

    OpenNavo editorial Added to Homebrew

    CompatibilitymacOS 12 or later

    FreeLLMAPI 0.16.34 lists all 21 desktop agents and can connect a gateway.

    Agents
    Open Agents on macOS or Windows to see all 21 supported agents.Search by name, and clear the search to see the full list again.Connect to FreeLLMAPI next to Claude Code, Cline, OpenCode, or another agent.The app saves supported setups and guides you when a manual step is required.
    Fixes
    Audio buffers for transcription uploads are handled correctly.

    FreeLLMAPI 0.16.34, published on November 17, 2026, is a local OpenAI-compatible router for people connecting desktop coding agents. This release lists all 21 supported agents and can start a gateway connection from the app.

    Source: https://github.com/tashfeenahmed/freellmapi/releases/tag/v0.16.34

    • Open Agents on macOS or Windows to see all 21 supported agents.
    • Search by name, and clear the search to see the full list again.
    • Connect to FreeLLMAPI next to Claude Code, Cline, OpenCode, or another agent.
    • The app saves supported setups and guides you when a manual step is required.
    • Audio buffers for transcription uploads are handled correctly.
  5. 0.16.33

    Expand

    OpenNavo editorial Added to Homebrew

    CompatibilitymacOS 12 or later

    Meldport chat and Solaria-3 transcription

    FreeLLMAPI 0.16.33 adds Meldport chat for the free GPT-6 Luna alias and keyless OVHcloud Solaria-3 transcription for people routing free models locally.

    FreeLLMAPI 0.16.33, released on 2026-11-17, adds two new routes for people who route free models through a local OpenAI-compatible key.

    • Meldport chat supports the free alias of GPT-6 Luna. The adapter requests promotional funding only, checks the response funding and model identity, and supports streaming. Meldport GLM stays off.
    • Keyless OVHcloud Solaria-3 transcription accepts English PCM16 WAV uploads. Existing OVH Whisper transcription keeps its original endpoint.
    • Model availability still follows the signed catalog: Premium on publication, Free after 30 days. Existing model routing and catalog eligibility are unchanged.

    Source: https://github.com/tashfeenahmed/freellmapi/releases/tag/v0.16.33

  6. 0.16.32

    Expand

    OpenNavo editorial Added to Homebrew

    CompatibilitymacOS 12 or later

    FreeLLMAPI 0.16.32, released on 2026-11-17, adds SpeechFlow file transcription and more embedding sizes for people routing free models through one local key. Source: https://github.com/tashfeenahmed/freellmapi/releases/tag/v0.16.32

    Added
    SpeechFlow file transcription uses a key ID and secret.Free.ai embeddings and two more SilvR Nemotron sizes.
    Notes
    Five routes use the signed catalog; local disables stay.Premium gets them now; Free waits 30 days.
  7. 0.16.31

    Expand

    OpenNavo editorial Added to Homebrew

    CompatibilitymacOS 12 or later

    FreeLLMAPI 0.16.31, released on 2026-11-16, adds tested chat, image and transcription routes for people routing free models through one local key.

    Added
    NovAI GLM 4.7 Flash chat works in normal and streaming modes.ElectronHub FLUX.2 Klein Base 4B can generate images.SilvR Whisper Large V3 can transcribe audio.
    Notes
    Model identity checks and bounded image decoding stay in place.Premium gets the Nov 16 catalog now; Free waits 30 days.
  8. 0.16.30

    Expand

    GitHub Release Added to Homebrew

    CompatibilitymacOS 12 or later

    Native routing for the November 15 renewable-free catalog additions:

    • SilvR AI: three embedding models, Whisper Large V3 Turbo transcription, and Gemini Decision 1 predicate questions.
    • Cartesia Ink 2 transcription: PCM16 WAV upload over the native, proxy-aware WebSocket with finalization checks and no ffmpeg dependency.
    • ElectronHub images: Qwen Image 2512 plus dispatch for the two existing catalog image routes; bounded image decoding and safe timeout/error handling.

    Also includes the current main-branch fixes for Windows bootstrap root resolution, explicit non-streaming chat requests, key health evidence, the Codex model catalog endpoint, and advertising the router's effective context window in model listings. Concurrently merged README contributor credits are preserved.

    Provider free allowances remain shared, renewable and subject to availability. No new app quotas, paid fallback, Mistral catalog changes or premium/Free release-timing changes. Catalog publication is separate: seven additions and one retired Kenari route disabled, with premium access immediately and Free eligibility after the existing 30-day window.

  9. 0.16.29

    Expand

    GitHub Release Added to Homebrew

    CompatibilitymacOS 12 or later

    New providers

    • Typecast: native SSFM 3.1, 3.0 and 2.1 text-to-speech.
    • Cartesia: Sonic 3.6, 3.5 and 3 speech, plus Ink Whisper batch transcription.
    • SilvR AI: OpenAI-compatible chat with normal and streaming model-identity checks.

    The new providers appear in local key setup/import. Typecast Free output is non-commercial and requires attribution; Cartesia's commercial-use license is on a paid plan. Free allowances are shared account pools, not credits per model.

    Native speech adapters preserve error/backoff information for failover, refuse credential redirects, bound downloads and validate actual audio / transcription responses. Chat cannot accidentally route to a speech model. This release also includes the recent URL-guard, Hugging Face video-download and request-lease fixes already merged into main.

    Model rows are delivered separately through the signed catalog. Premium receives updates immediately; Free receives them after the existing 30-day aging rule. Mistral and local disabled choices are unchanged.

  10. 0.16.28

    Expand

    GitHub Release Added to Homebrew

    CompatibilitymacOS 12 or later

    v0.16.28 — November catalog adapters

    New catalog adapter support

    • Cloudflare EmbeddingGemma 2: native text embeddings with fixed 768-dimensional vectors, batch ordering and model-identity validation. Uses its own embedding family so existing indexes never silently switch vector spaces.
    • Google Gemini Decisions: native typed decisions using existing Google credentials, with validated answers, confidence and token usage.
    • ElectronHub transcription: Voxtral Mini Transcribe 2 and Deepgram Nova 3 through the existing key pool and multipart speech endpoint.

    Quota errors and retry hints remain available to the normal router. Existing providers, Mistral behavior and user overrides are unchanged.

    The accompanying catalog update is delivered separately: ten additions, three retired routes disabled (net enabled +7), and corrected Speechify allowance metadata. Premium receives the Live catalog immediately; Free receives new entries through the existing 30-day release process.

    Validation

    Production builds, lint, migration round-trip tests, full server/CLI/client suites and desktop tests passed locally. Native adapters have regression coverage for malformed responses, model substitutions, vector dimensions and rate limits. Live catalog tests use the actual local application API without saving provider credentials.

  11. 0.16.27

    Expand

    GitHub Release Added to Homebrew

    v0.16.27 — Zro daily-free provider

    Zro by MoonMath.ai

    • Add your own Zro API key in the Keys dashboard; imports recognize ZRO_API_KEY and MOONMATH_API_KEY.
    • OpenAI-compatible normal and streaming chat, tool calls and JSON output use the existing routing and failover behavior.
    • Credential validation uses the authenticated model-list endpoint without spending inference tokens.
    • Reject mismatched response model identities, credential redirects and in-band streaming errors.
    • Account-wide Free usage resets daily; it is not a monthly cash grant. Model availability is managed through the signed catalog rather than bundled seeds.

    Catalog compatibility

    This release supplies the Zro adapter needed by the November 12 catalog update. The existing Premium-immediate / Free-after-30-days catalog logic is unchanged. Mistral and other providers' application behavior are unchanged.

    The catalog publication is separate from the app release. The validated update holds three dated/non-renewing promotions rather than mislabeling them as recurring free, retains stored history, and adds only tested routes.

    Local validation: full server/CLI/client suites, locale validation, migration round trips, lint, workspace build and desktop tests. Zro was also tested through the real app router against the Free account with an in-memory database.

  12. 0.16.26

    Expand

    OpenNavo editorial Added to Homebrew

    CompatibilitymacOS 12 or later

    FreeLLMAPI 0.16.26 fixes provider routing, the local dashboard, and model discovery.

    FreeLLMAPI 0.16.26, released on 2026-11-11, is for people who route one local API across several free and paid language-model providers. This build fixes provider routing, the local dashboard, and model discovery. Official notes: https://github.com/tashfeenahmed/freellmapi/releases/tag/v0.16.26

    • Fixes the default model route when an explicit provider is set.
    • Fixes the local dashboard when the port is already in use.
    • Fixes NVIDIA NIM model discovery and a missing type.
    • Fixes the LongCat image model id and the provider settings panel.
  13. 0.16.25

    Expand

    OpenNavo editorial Added to Homebrew

    CompatibilitymacOS 12 or later

    FreeTTS: local personal speech

    FreeLLMAPI 0.16.25 adds local FreeTTS speech: bring your own key and get native MP3 with voice selection.

    FreeLLMAPI 0.16.25, released 11 November 2026, adds local bring-your-own-key speech for people who run FreeLLMAPI as their own gateway. You add a personal FreeTTS key and get native MP3 text-to-speech with voice selection.

    Source: https://github.com/tashfeenahmed/freellmapi/releases/tag/v0.16.25

    • Adds FreeTTS key setup and import for a local account.
    • Speaks MP3 with voice selection, fixed-host downloads, bounded responses, audio checks and rate-limit failover.
    • Adds one catalog entry, neural-tts. Voices are parameters, not separate models.
    • Keeps Gemini schema fixes, overloaded-model key fallback, and Start on system startup from main since 0.16.24.

    FreeTTS Free stays personal and non-commercial. No provider key is bundled. Premium gets neural-tts now; Free gets it after the existing 30-day aging rule.

  14. 0.16.24

    Expand

    OpenNavo editorial Added to Homebrew

    CompatibilitymacOS 12 or later

    FreeLLMAPI 0.16.24 adds PowerTokens as a fallback OpenAI-compatible provider for people routing local LLM requests, and rotates custom-endpoint keys across image, speech, transcription, and embeddings.

    Providers
    PowerTokens joins as an OpenAI-compatible fallback; glm-4.7-flash is $0.429s cool that key, and the router moves on.
    Fixes
    Custom endpoints rotate image, speech, transcription, and embedding keys.Probe now leaves room for a reasoning model's hidden thinking (#1862).

    FreeLLMAPI 0.16.24, released on November 10, 2026, adds the PowerTokens provider for people routing local OpenAI-compatible requests, and fixes key rotation on custom endpoints. Source: https://github.com/tashfeenahmed/freellmapi/releases/tag/v0.16.24

    • PowerTokens (api.powertokens.ai) is an OpenAI-compatible provider; glm-4.7-flash is listed at $0 and was tested for chat, streaming, and tool calling.
    • PowerTokens often returns 429, so the router cools that key and moves on; treat it as a fallback, and allow glm-4.7-flash on restricted keys.
    • The model arrives through the signed catalog: Premium gets it live, and Free gets it after the existing 30-day wait.
    • Custom endpoints with several keys now rotate image, speech, transcription, and embedding requests when a key is disabled, over budget, rate limited, or rejected (#1738).
  15. 0.16.23

    Expand

    OpenNavo editorial Added to Homebrew

    CompatibilitymacOS 12 or later

    FreeLLMAPI 0.16.23 lets people routing one OpenAI-compatible endpoint across free model providers speak English and Saudi Arabic through Groq Orpheus.

    FreeLLMAPI 0.16.23, released on November 9, 2026, adds Groq Orpheus speech for people who route chat, image, and audio calls through one OpenAI-compatible endpoint. Source: https://github.com/tashfeenahmed/freellmapi/releases/tag/v0.16.23

    • Generates English and Saudi Arabic speech with an existing Groq key through the normal audio router.
    • Returns validated PCM16 WAV, normalizes Groq's streamed WAV headers, and keeps failover and rate-limit backoff.
    • Maps standard OpenAI voice names to tested native defaults, and still accepts explicit native voices.
    • Premium receives the live signed catalog; Free receives new rows after the unchanged 30-day wait.
    • A Groq organization administrator must accept each Orpheus model's terms. TwelveLabs and Mistral are unchanged.
  16. 0.16.22

    Expand

    OpenNavo editorial Added to Homebrew

    CompatibilitymacOS 12 or later

    FreeLLMAPI 0.16.22 was released on 2026-11-08. This update adds Rime speech models and transcription, and includes Varosity media adapters.

    FreeLLMAPI 0.16.22 was released on 2026-11-08. This update adds Rime speech models and transcription, and includes Varosity media adapters.

    • Rime Coda v2 and Mist v3 text-to-speech are added, plus Rime transcription.
    • Rime is in encrypted key management and imports. No project ID is required. Models arrive through the hosted catalog.
    • Varosity's already merged image, speech and music, and video adapters are included.
    • Recent APINex check-in recovery, web-search readiness and cache diagnostics, and Waterfall onboarding fixes are included.
    • Rime text-to-speech currently returns WAV.
    • Transcription accepts PCM16 WAV, mono or stereo, 8–48 kHz, in English or Spanish, and does not need an external ffmpeg.
    • Prism realtime is not included.
    • The catalog update adds 18 tested entries and disables two retired BeatAPI JEV routes, a net of 16 enabled.
    • Provider allowances are shared, not a new grant per model.
    • Existing catalog access is unchanged: Premium receives the live catalog; Free receives each addition after 30 days.
    • Mistral catalog entries are unchanged.
  17. 0.16.21

    Expand

    OpenNavo editorial Added to Homebrew

    CompatibilitymacOS 12 or later

    FreeLLMAPI 0.16.21 was released on 2026-11-07. This update adds tested FreeInference DeepSeek V4 Flash support for chat and streaming.

    FreeLLMAPI 0.16.21 was released on 2026-11-07. This update adds tested FreeInference DeepSeek V4 Flash support for chat and streaming.

    • Adds tested FreeInference DeepSeek V4 Flash support for chat and streaming, and keeps exact response-model validation.
    • Upgrade to use the new DeepSeek catalog route.
    • Signed catalog delivery, local model preferences, and the 30-day Free and Premium rollout stay as they are.
    • Catalog publication is handled separately after release verification.
    • Includes PR #1834.
  18. 0.16.20

    Expand

    OpenNavo editorial Added to Homebrew

    CompatibilitymacOS 12 or later

    FreeModel personal BYOK chat, with a signed catalog that adds 24 enabled routes.

    FreeLLMAPI 0.16.20 was released on 2026-11-06. This update adds FreeModel personal BYOK chat and 24 enabled catalog routes.

    • Add FreeModel to provider selection and environment and key imports.
    • Support text chat and streaming with strict model-identity checks, empty-response protection, and normal HTTP and backoff failover.
    • Track the provider's shared account quota without inventing a monthly balance from rate-limit headers.
    • Preserve signed catalog delivery: Premium receives new entries immediately; Free receives them after the existing 30-day window. No new model seeds bypass this gate.
    • FreeModel requires your own API key and Telegram verification. Its advertised 1M-token monthly allowance is shared across models. Keep its wallet unfunded for free-only use; funded wallets can be charged after the allowance. Review the provider terms before shared or commercial gateway use; this integration does not establish permission for resale or a competing service.
    • The separate catalog update adds 29 tested FreeModel routes and 2 Kenari routes, disables 7 retired routes without deleting them, and increases the enabled catalog by 24. Text and streaming passed on all 29 FreeModel routes through the shipped adapter; tools and vision are not advertised without tests.
    • Verification: 22 focused FreeModel adapter tests and provider key-form coverage; full server, CLI, and client regression suites, plus build, lint, and migration round trip; signed-catalog shape, import, and idempotency checks; unchanged day-0, day-29, and day-30 gate.

    Source: https://github.com/tashfeenahmed/freellmapi/releases/tag/v0.16.20 (provider integration pull request 1830).

  19. 0.16.19

    Expand

    OpenNavo editorial Added to Homebrew

    CompatibilitymacOS 12 or later

    FreeLLMAPI 0.16.19 adds FreeInference chat and embeddings support.

    FreeLLMAPI 0.16.19 was released on 2026-11-04, adding FreeInference chat and embeddings support.

    • FreeInference is now available in the provider picker and key import flow.
    • Tested Qwen3.6 35B chat, including streaming, and BGE-M3 embeddings with 1,024-dimensional vectors are supported.
    • Upstream model identities and embedding shapes are validated, and normal routing errors and failover are preserved.
    • FreeInference's public model roster is no longer treated as API-key validation. Real requests establish key health.
    • The signed catalog adds two entries without removing any existing models. Premium receives the new catalog immediately; Free receives these entries through the unchanged 30-day release gate.
    • FreeInference offers a shared daily research allowance. It logs prompts and responses for research, so do not send sensitive data.
  20. 0.16.18

    Expand

    GitHub Release

    NovAI image generation

    • Add the tested free cogview-3-flash image route to the existing NovAI provider. Use your NovAI API key with /v1/images/generations for one 1024×1024 image.
    • Validate downloaded image data and return PNG base64, including when the upstream labels JPEG bytes as PNG. Output downloads never receive the API key and are restricted to approved HTTPS hosts.
    • Package the native image decoder in desktop builds; unsupported installations fail only this image route and retain existing media failover.

    Catalog update

    The separately published catalog adds six tested routes and disables five retired routes: net +1 enabled entry. It also corrects Router9 allowance descriptions and Cohere embedding input limits.

    Premium receives the live catalog immediately. Free retains the existing 30-day release delay. No release-gating code or existing model ages were changed. Catalog data is published to Oracle, not embedded in this release.

    Validation

    • 79 targeted NovAI tests and a successful live image-generation test.
    • Full workspace tests: 5,470 passed; seven existing skips.
    • Desktop tests: 79 passed; one existing skip.
    • Workspace builds, lint, migrations and desktop bundles passed locally.
    • Signed catalog dry-runs verify Premium/Free routing and the day-0/day-29/day-30 boundary.

    PR: https://github.com/tashfeenahmed/freellmapi/pull/1814

  21. 0.16.17

    Expand

    GitHub Release

    NovAI daily-free chat support

    • Add chat and streaming support for GLM 4.6V Flash and GLM 4.1V Thinking Flash through the existing NovAI provider.
    • Normalize leading reasoning and nested answer envelopes while preserving streaming, tool deltas and retry information.
    • Reject mismatched model identities so the router can fail over safely.
    • Keep existing NovAI video support and the Premium-immediate / Free-after-30-days catalog policy unchanged.

    The separately published catalog enables the two NovAI chat entries and disables three retired onomeo free routes: codestral-latest, ministral-14b-latest and qwen-flash-character. Net enabled change: -1. Existing rows are retained.

    NovAI free models share a daily allowance. GLM 4.6V Flash passed live adapter checks in both modes. The thinking model returned the correct answers and identity in both modes; final formatting normalization is regression-tested, but a post-fix live repeat was blocked by the account's daily quota.

    Upgrade desktop or pull the stable Docker image to use the new adapter.

  22. 0.16.16

    Expand

    GitHub Release

    v0.16.16 — Audio and video catalog expansion

    Audio and video catalog support

    This release includes the adapters for the November 1 catalog update: 13 tested media additions, with three duplicate listings disabled (net +10 enabled entries).

    • NovAI: daily-free CogVideoX Flash video generation, with asynchronous polling, cancellation, safe media downloads and normal routing/failover.
    • Free.ai: MeloTTS, Chatterbox, Qwen3 TTS and VibeVoice speech; Whisper uploaded-file transcription.
    • OVH: keyless English, German, Spanish and Italian speech, plus Whisper transcription support.
    • Mistral: Voxtral Mini TTS 3.0 speech.
    • Google: Gemini 3.5 Transcribe through the Interactions API.
    • ElectronHub: support for the catalog's GPT-4o Mini TTS route through the existing speech adapter.
    • Cohere: transcription routing and correct classification of its existing speech-recognition entry.

    Fixes

    • Correct Cloudflare Aura speech payloads and binary audio handling, MeloTTS WAV labeling, and Nova 3 transcription parsing.
    • Keep dedicated transcription routes enabled when their legacy duplicate audio listings are disabled. Local user disables remain respected.

    Rollout

    The signed Oracle catalog is already published as 2026.11.01.fbb00f16: 1,221 total entries, 737 enabled, 57 active providers. Premium receives new catalog entries immediately; Free receives them through the existing 30-day promotion. This release does not bypass that gate or seed new models locally.

    Update the app, configure the relevant provider keys, and sync the catalog. Provider allowances are shared and upstream availability/rate limits still apply. NovAI's free output is watermarked.

    Verification

    All 13 additions passed live application-adapter tests. The adapter PR passed Node 20/22/24 CI and Linux amd64/arm64 Docker builds. Local regression checks passed 4,811 server tests, 178 CLI tests and 436 client tests, plus build, lint, migration and localization checks. Oracle signatures and the unchanged day-0/day-29/day-30 promotion behavior were verified.

    Adapter changes: https://github.com/tashfeenahmed/freellmapi/pull/1797

  23. 0.16.15

    Expand

    GitHub Release

    v0.16.15 — nabh.cloud support

    New provider: nabh.cloud

    • Adds built-in nabh.cloud support for normal and streaming chat completions, with API-key setup in the dashboard and environment-file imports.
    • Uses a read-only authenticated model-list request for key health checks, without consuming inference credits.
    • Shares account-level quota across routes, preserves upstream errors for normal fallback, and rejects mismatched response model identities.

    GPT OSS 20B is the tested Free-plan route. Model availability is delivered through the signed live catalog, not bundled model seeds. Premium users receive catalog additions immediately; Free users retain the existing 30-day delay.

    Upgrade

    Install the desktop package for your platform below, or pull ghcr.io/tashfeenahmed/freellmapi:v0.16.15 (also published as latest) for stable Docker. Bring your own nabh.cloud API key.

    Validation

    The adapter passed live normal and streaming tests. Node 20/22/24 CI, both Docker architecture checks, all four desktop packaging checks and macOS updater-metadata validation passed before the release tag. Tagged macOS builds additionally run signing, notarization and packaged-backend smoke checks before publication.


    ⭐ Like the free router? Go Premium — the live signed catalog, $19/yr, cancel anytime.

  24. 0.16.14

    Expand

    GitHub Release

    v0.16.14 — JamAI and macOS release fix

    Includes JamAI Base chat and embeddings with separate PAT and Project ID setup fields, plus the Intel macOS release fix.

    Fixes the Apple CloudKit connection failure documented in actions/runner-images#14924 by using HTTPS over TCP on signed Intel GitHub runners. Notarization, ticket validation, Gatekeeper checks, native-backend smoke tests, and update-metadata verification remain required.

    Validation before merge: all Node 20/22/24 CI jobs, both Docker architectures, all four desktop builds and combined Mac metadata checks passed. Full local server, CLI, dashboard and desktop regression suites, lint, builds and 60-locale checks passed.

    The catalog is already published with 15 additions and 2 disabled routes (net +13). This release does not change catalog data or the existing Premium-immediate / Free-after-30-days policy. Update the app to use the new JamAI adapter.

    This release supersedes the stalled v0.16.13 desktop draft; existing tags are unchanged.

    PRs: https://github.com/tashfeenahmed/freellmapi/pull/1764 and https://github.com/tashfeenahmed/freellmapi/pull/1767