> ## Documentation Index
> Fetch the complete documentation index at: https://docs.omnimux.ai/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> Public hosts only: console https://omnimux.ai/dashboard · API https://api.omnimux.ai · docs https://docs.omnimux.ai.
> Gateway auth is Authorization: Bearer sk-… on https://api.omnimux.ai/v1 (OpenAI-compatible Chat Completions and related paths).
> Discover pages from /llms.txt; full site dump /llms-full.txt; product skill /skill.md; docs search MCP /mcp. Prefer .md page URLs for Markdown.
> Default docs locale is en; zh mirrors the same relative paths. Do not invent model ids not present on live pricing or the complete API pages.

# API Updates

> Stay informed about the latest model launches, capability changes, pricing, and platform notes on OmniMux.

Stay up to date with OmniMux gateway model launches and platform changes. The full callable catalog is on [console pricing](https://omnimux.ai) / [Pricing](/en/api-reference/account/pricing).

<a id="2026-09-18-gpt-image-tiers" />

<Update label="September 18, 2026" tags={["New models", "Image"]} rss={{ title: "GPT Image 2.5 Flare & Sunburst Tier Routes Live" }}>
  ## GPT Image Tiers

  OmniMux now supports dedicated tier routing models `gpt-image-2.5-flare` and `gpt-image-2.5-sunburst` under the standard image generation endpoint.

  ### Model specification

  * **Endpoint:** `POST /v1/images/generations`
  * **Authentication:** Bearer token (`sk-...`)
  * **Tier models:** `gpt-image-2.5-flare` (discounted tier), `gpt-image-2.5-sunburst` (economy tier)
  * **Parameters:** Fully compatible with baseline `gpt-image-2.5`

  ### Request example

  ```bash theme={null}
  curl --request POST \
    --url https://api.omnimux.ai/v1/images/generations \
    --header 'Authorization: Bearer sk-...' \
    --header 'Content-Type: application/json' \
    --data '{
      "model": "gpt-image-2.5-flare",
      "prompt": "A clean studio product photograph on white background",
      "n": 1
    }'
  ```

  Parameter details are documented in the [GPT Image Reference](/en/api-reference/image-series/gpt-image/generate).

  ### Links

  * [GPT Image Reference](/en/api-reference/image-series/gpt-image/generate)
</Update>

<a id="2026-09-18-video-task-models" />

<Update label="September 18, 2026" tags={["New models", "Video"]} rss={{ title: "Video Per-Call Task Channels and H3 Variants Available" }}>
  ## Video Task and Variant Models

  OmniMux now supports dedicated per-call video task channels and H3 model variants under the standard video endpoint.

  ### Model specification

  * **Endpoint:** `POST /v1/video/generations`
  * **Polling endpoint:** `GET /v1/video/generations/{task_id}`
  * **Per-call models:** `seedance-2-0-task`, `seedance-2-5-task`, `minimax-h3-task` (billed per task call)
  * **H3 variants:** `minimax-h3-turbo` (turbo rendering), `minimax-h3-video` (dedicated video pipeline)

  ### Request example

  ```json theme={null}
  {
    "model": "seedance-2-0-task",
    "prompt": "A cinematic drone shot of coastal mountains at sunset",
    "seconds": 5
  }
  ```

  Full parameter definitions are documented in the [Seedance 2.0 Reference](/en/api-reference/video-series/models/seedance-2-0) and [MiniMax H3 Reference](/en/api-reference/video-series/models/minimax-h3).

  ### Links

  * [Seedance 2.0 Reference](/en/api-reference/video-series/models/seedance-2-0)
  * [MiniMax H3 Reference](/en/api-reference/video-series/models/minimax-h3)
</Update>

<a id="2026-09-18-volc-doubao-asr" />

<Update label="September 18, 2026" tags={["New models", "Audio"]} rss={{ title: "Doubao ASR Speech Recognition Series Available" }}>
  ## Doubao Speech Recognition

  The `doubao-asr-bigmodel`, `seedasr-auc`, and `bigasr-auc` models are now supported on OmniMux.

  ### Model specification

  * **Model IDs:** `doubao-asr-bigmodel`, `seedasr-auc`, `bigasr-auc`
  * **Protocol:** OpenAI-compatible Audio Transcriptions (`POST /v1/audio/transcriptions`)
  * **Authentication:** Bearer token (`sk-...`)
  * **Input format:** Audio file multipart upload (`wav`, `mp3`, `ogg`, `m4a`)

  ### Request example

  ```bash theme={null}
  curl --request POST \
    --url https://api.omnimux.ai/v1/audio/transcriptions \
    --header 'Authorization: Bearer sk-...' \
    --header 'Content-Type: multipart/form-data' \
    --form 'file=@audio.mp3' \
    --form 'model=doubao-asr-bigmodel'
  ```

  Full parameter specifications are documented in the [Doubao ASR Reference](/en/api-reference/audio-series/models/doubao-asr).

  ### Links

  * [Doubao ASR Reference](/en/api-reference/audio-series/models/doubao-asr)
</Update>

<a id="2026-09-18-volc-seed-audio" />

<Update label="September 18, 2026" tags={["New models", "Audio"]} rss={{ title: "VolcEngine Seed Audio (seed-audio-1.0) Available via TTS Endpoint" }}>
  ## Seed Audio 1.0

  The `seed-audio-1.0` model is now supported on OmniMux under standard audio speech endpoints.

  ### Model specification

  * **Model ID:** `seed-audio-1.0`
  * **Protocol:** OpenAI-compatible Audio Speech (`POST /v1/audio/speech`)
  * **Authentication:** Bearer token (`sk-...`)
  * **Output limit:** Up to 120 seconds per generation
  * **Prompt limit:** Up to 3000 characters

  ### Request example

  ```bash theme={null}
  curl --request POST \
    --url https://api.omnimux.ai/v1/audio/speech \
    --header 'Authorization: Bearer sk-...' \
    --header 'Content-Type: application/json' \
    --data '{
      "model": "seed-audio-1.0",
      "input": "Text to synthesize into speech",
      "voice": "zh_female_cancan",
      "response_format": "mp3"
    }' \
    --output output.mp3
  ```

  Full parameter specifications are documented in the [Seed Audio Reference](/en/api-reference/audio-series/models/seed-audio).

  ### Links

  * [Seed Audio Reference](/en/api-reference/audio-series/models/seed-audio)
</Update>

<a id="2026-09-18-indextts-2" />

<Update label="September 18, 2026" tags={["New models", "Audio"]} rss={{ title: "Index TTS Voice Clone (indextts-2) Available" }}>
  ## Index TTS 2

  The `indextts-2` voice clone model is now supported on OmniMux.

  ### Model specification

  * **Model ID:** `indextts-2`
  * **Create endpoint:** `POST /v1/tasks/autodl`
  * **Polling endpoint:** `GET /v1/tasks/{task_id}`
  * **Artifact endpoint:** `GET /v1/tasks/{task_id}/artifacts`
  * **Authentication:** Bearer token (`sk-...`)

  ### Request example

  ```json theme={null}
  {
    "model": "indextts-2",
    "prompt_text": "Hello, this is a cloned voice generation test.",
    "prompt_simple": "https://example.com/reference_audio.wav",
    "emo_control_method": "same_as_reference"
  }
  ```

  Full parameter specifications are documented in the [Index TTS Reference](/en/api-reference/audio-series/models/index-tts).

  ### Links

  * [Index TTS Reference](/en/api-reference/audio-series/models/index-tts)
</Update>

<a id="2026-09-18-suno-sounds" />

<Update label="September 18, 2026" tags={["New models", "Audio"]} rss={{ title: "Suno Sound Effects Generation (suno-sounds) Available" }}>
  ## Suno Sound Effects

  The dedicated sound effect generation model `suno-sounds` is now supported on OmniMux.

  ### Model specification

  * **Model ID:** `suno-sounds`
  * **Endpoint:** `POST /v1/video/generations`
  * **Polling endpoint:** `GET /v1/video/generations/{task_id}`
  * **Authentication:** Bearer token (`sk-...`)
  * **Modality:** Ambient and scene sound effects without vocal lyrics

  ### Request example

  ```bash theme={null}
  curl --request POST \
    --url https://api.omnimux.ai/v1/video/generations \
    --header 'Authorization: Bearer sk-...' \
    --header 'Content-Type: application/json' \
    --data '{
      "model": "suno-sounds",
      "prompt": "footsteps on gravel followed by heavy rain and distant thunder"
    }'
  ```

  Details are available in the [Suno API Reference](/en/api-reference/audio-series/models/suno).

  ### Links

  * [Suno API Reference](/en/api-reference/audio-series/models/suno)
</Update>

<a id="2026-09-18-gemini-3-8-flash" />

<Update label="September 18, 2026" tags={["New models", "Text"]} rss={{ title: "Gemini 3.8 Flash Available via Chat Completions" }}>
  ## Gemini 3.8 Flash

  The `gemini-3.8-flash` model is now supported on OmniMux under the standard Gemini Chat Completions endpoint.

  ### Model specification

  * **Model ID:** `gemini-3.8-flash`
  * **Protocol:** OpenAI-compatible Chat Completions
  * **Endpoint:** `POST /v1/chat/completions`
  * **Authentication:** Bearer token (`sk-...`)
  * **Streaming:** Supported via `"stream": true`

  ### Request example

  ```json theme={null}
  {
    "model": "gemini-3.8-flash",
    "messages": [
      {
        "role": "user",
        "content": "Hello"
      }
    ]
  }
  ```

  Full parameter schema and status codes are documented in the [Gemini Complete API Reference](/en/api-reference/text-series/gemini/complete).

  ### Links

  * [Gemini Complete Reference](/en/api-reference/text-series/gemini/complete)
</Update>

<a id="2026-09-18-doubao-seed-evolving" />

<Update label="September 18, 2026" tags={["New models", "Text"]} rss={{ title: "ByteDance Doubao official direct model seed-evolving is now live" }}>
  ## What is new

  * **Official Direct Channel**: Added VolcEngine Ark direct route `#73` for ByteDance Doubao `seed-evolving`.
  * **Full Multimodal Reasoning**: 1024K context window, 256K max output tokens, native deep thinking, tool calling, and structured outputs.
  * **Transparent 1:1 Parity Pricing**: Token billing expressions anchor official list prices ($0.8824/M input, $4.4118/M output, \$0.1765/M cache hit; FX 6.8).
  * **Local OmniMux CLI Verification**: Verified live invocation and pricing queries using the local `omnimux` CLI (`omnimux models`, `omnimux pricing`, `omnimux tokens exec`).

  ## Documentation

  * Doubao API Reference: `/en/api-reference/text-series/doubao/complete`

  ### Links

  * [Doubao Complete API Reference](/en/api-reference/text-series/doubao/complete)
</Update>

<a id="2026-09-14-image-reference-fields" />

<Update label="September 14, 2026" tags={["Improvements", "Image"]} rss={{ title: "Image model pages now document the reference-image field and its limits" }}>
  ## What changed

  * Image-generation model pages now document the reference-image request field `images` (`string[]`, image URL or base64) together with the accepted aliases `image`, `image_urls` and `input_reference`, which the gateway normalizes to `images` before the upstream call.
  * Each page states the limits its vendor publishes for that model: maximum count, minimum, accepted formats and per-file size ceiling.

  ## Limits we do not state

  * Where a value is not published by the vendor, the page says so instead of carrying a number; nothing is rounded or copied from a sibling model.
  * Where no model spec exists yet, the reference-image note marks the capability **unverified** and states no limit at all.

  ## Withdrawn figure

  * The previously stated per-file reference-image cap of 50 MB is withdrawn. In the vendor's image guide that figure sits under mask requirements and covers the image being edited together with its mask; it is not a reference-image ceiling. `gpt-image-2.5` therefore carries no per-file size limit.

  ## Documentation

  * Image series model pages: `/en/api-reference/image-series/models/*`
  * GPT Image generation: `/en/api-reference/image-series/gpt-image/generate`

  ### Links

  * [Image series model pages](/en/api-reference/image-series/models/nano-banana-2)
  * [GPT Image generation](/en/api-reference/image-series/gpt-image/generate)
  * [Midjourney image generation](/en/api-reference/image-series/models/midjourney)
</Update>

<a id="2026-09-13-midjourney-two-ids" />

<Update label="September 13, 2026" tags={["Breaking", "Image"]} rss={{ title: "Midjourney now uses two version IDs with per-request actions" }}>
  ## Required migration

  * Replace the legacy `midjourney` ID and every per-action ID (for example `mj-v7-upscale`, `mj-v8-1-remove-bg`) with one of two version IDs: `mj-v7` or `mj-v8-1`.
  * Select the action in the request body: `model_params.operation` = `generate` | `enhance` | `pan` | `outpaint` | `remove-bg` | `upscale` | `variation` | `edit` | `inpaint` | `remix` | `retexture` | `upload-paint`. Omit it for plain generation.
  * Keep using `POST /v1/images/generations`; the request shape, the async task id and the polling behaviour are unchanged.

  The old IDs are not compatibility aliases. An unknown or unpriced `operation` is rejected with **400**, never silently downgraded to plain generation.

  ## Pricing

  Per-call prices are tiered by action, and the tiers are the same on both versions:

  | Action tier                                                                     | Price        | Credits |
  | ------------------------------------------------------------------------------- | ------------ | ------- |
  | `generate`, `enhance`, `pan`, `outpaint`, `remove-bg`                           | USD 0.113446 | 1.134   |
  | `upscale`, `variation`, `edit`, `inpaint`, `remix`, `retexture`, `upload-paint` | USD 0.170169 | 1.702   |

  Multipliers stack on the action tier: `quality: "hd"` (mj-v8-1) ×1.5, `model_params.speed: "turbo"` ×2, upscale `type: "creative"` ×4/3. `draft`/`fast` and `type: "standard"` stay ×1. Measured example: mj-v8-1 + hd + upscale + creative = USD 0.255251 per call.

  The `mj-v7` per-call price moved from USD 0.056723 to USD 0.113446 to match what upstream bills for generation; the action tiers above are unchanged in absolute terms.

  ## Inpaint

  Use the mask-image form: `model_params.mask.url` (an image URL or a `data:` URL, black = keep, white = regenerate). The polygon form `model_params.mask.areas[]` is rejected upstream with `invalid_parameters: Image dimensions out of range` in our measurements (2026-09-13), including with the upstream documentation's own example coordinates.

  ### Links

  * [Midjourney image generation](/en/api-reference/image-series/models/midjourney)
</Update>

<a id="2026-09-12-console-playground-generation" />

<Update label="September 12, 2026" tags={["Platform"]} rss={{ title: "Model page playground generates through the gateway session" }}>
  ## Overview

  The model page at `omnimux.ai/pricing/<model-id>` now runs real generations. Its **Playground** section submits through the gateway using the signed-in browser session, so a user who has already logged in to OmniMux can try a model without creating an API token first.

  ## Which path to call

  * **From the console**: the page posts to the session-authenticated `POST /pg/video/generations`. This path accepts a browser session only and is not part of the token API surface.
  * **From your own code**: keep using `POST /v1/video/generations` with an API token — the same contract documented in the video-series model pages. Nothing about the token path changed.

  ## Task results

  Submitted tasks are read back through the same session: `GET /api/task/self` for status, progress and quota, and `GET /api/task/:task_id/artifacts` for the media projection. Tasks submitted from the console appear in the account's task list like any other task.

  ## Billing

  Console submissions use the standard precharge and settle path. No separate ledger, pricing rule or quota bucket is introduced for the console path.

  ### Links

  * [Video generation API](/en/api-reference/video-series/models/seedance-2-5)
</Update>

<a id="2026-09-10-r2-file-storage" />

<Update label="September 10, 2026" tags={["Platform"]} rss={{ title: "Cloudflare R2 storage & Evolink-compatible file upload API released" }}>
  ## Overview

  OmniMux now provides Cloudflare R2 object storage integration alongside a local disk fallback driver. File series endpoints are available under `/api/v1/files/*` and `/v1/files/*`.

  ## Capabilities

  * **Base64 upload**: `POST /api/v1/files/upload/base64` supporting Data URL and raw Base64.
  * **Stream upload**: `POST /api/v1/files/upload/stream` via `multipart/form-data`.
  * **URL upload**: `POST /api/v1/files/upload/url` with SSRF protection.
  * **Quota & Expiration**: 2,000 active files per user quota, 72-hour automated expiration with background cleanup.

  ### Links

  * [Base64 upload](/en/api-reference/file-series/upload-base64)
  * [File quota](/en/api-reference/file-series/quota)
</Update>

<a id="2026-09-10-gpt-image-25-rename" />

<Update label="September 10, 2026" tags={["Breaking", "Image"]} rss={{ title: "GPT Image per-call model IDs renamed to 2.5" }}>
  ## Required migration

  * Replace `gpt-image-2` with `gpt-image-2.5`.
  * Replace `gpt-image-2-hd` with `gpt-image-2.5-hd`.
  * Keep using `POST /v1/images/generations`. Update the `model` value in saved requests, integrations, and any model allowlists.

  The old IDs are not compatibility aliases. The `gpt-image-2-5` spelling is not supported.

  ## Pricing and scope

  Base per-call prices remain USD 0.0441 for `gpt-image-2.5` and USD 0.005479 for `gpt-image-2.5-hd`; group multipliers may affect final charges. This is a public ID migration, not a claim of a newly verified resolution or upstream capability.

  Flare and Sunburst are separate token-billed models and are not available as part of this change.

  ### Links

  * [GPT Image generation](/en/api-reference/image-series/gpt-image/generate)
</Update>

<a id="2026-09-09-h3-media-task-contracts" />

<Update label="September 9, 2026" tags={["Breaking", "Video"]} rss={{ title: "H3 ordered references and task result handling" }}>
  Use operation to select text, first-frame or Max multi-reference generation. Media arrays retain order and conflicting aliases are rejected. Replace legacy 720p with explicit 768P. Temporary result unavailability is retried; failures and cancellations are not masked by stale video URLs. Status reads no longer persist terminal transitions ahead of settlement polling.

  ### Links

  * [H3 Max API](/en/api-reference/video-series/models/minimax-h3-max)
</Update>

<a id="2026-09-08-fal-minimax-h3" />

<Update label="September 8, 2026" tags={["New models", "Video"]} rss={{ title: "fal.ai MiniMax H3 Max & Turbo Video Models Live with Dynamic Multimodal Dispatch" }}>
  ## fal.ai MiniMax H3 Max & Turbo

  **MiniMax H3 Max** and **MiniMax H3 Max Turbo** video generation models are now live on OmniMux.

  ### Highlights

  * **Dynamic Multimodal Dispatch**: Clients only need to configure two base models (`minimax/h3-max` and `minimax/h3-max-turbo`). Passing prompt-only routes to text-to-video, adding `image_url` routes to image-to-video, and passing `video_url` routes to reference-to-video automatically.
  * **Ultra-Fast Turbo Performance**: Sub-3-second end-to-end rendering for 5-second video clips.
  * **Two-Phase Resilient Polling**: Transparent inline result resolution with CDN 404 lag tolerance.
  * **Standard API**: Create via `POST /v1/video/generations` and query via `GET /v1/tasks/{task_id}`.

  ### Links

  * [MiniMax H3 Max](/en/api-reference/video-series/models/minimax-h3-max)
  * [MiniMax H3 Max Turbo](/en/api-reference/video-series/models/minimax-h3-max-turbo)
  * [Pricing](/en/api-reference/account/pricing)
</Update>

<a id="2026-09-07-social-provider-required" />

<Update label="September 7, 2026" tags={["Breaking", "Publishing"]} rss={{ title: "Social operations require an explicit provider" }}>
  The gateway began requiring `provider` at **2026-09-07 07:25:20 UTC+8 (2026-09-06T23:25:20Z)** for listing accounts, starting a connection, disconnecting, creating a post and reading post status. Use `tiktok_direct` for official TikTok accounts or `zernio` for Zernio accounts. GET/DELETE carry it in the query; POST carries it in JSON. Missing or unknown values return `400 invalid-provider`; a resource from another source returns `409 account-provider-mismatch` or `409 post-provider-mismatch`. There is no default source.

  ### CLI migration

  Use CLI **0.4.0**: `omnimux update` for binaries, or `npm install -g @omnimux/cli@0.4.0` for npm. Update all saved commands to include `--provider`, for example `omnimux social accounts --provider zernio`. For a read without upstream refresh, use `omnimux social post-status <post-id> --provider zernio --no-refresh`. Updating a binary does not update your scripts or prove all clients have upgraded.

  CLI 0.4.0 also includes the previously merged hosted commands and video skill updates. Credentials use a mode-0600 file on every platform; Keychain-only installations need credentials configured securely. The Agent RPC envelope remains `contract_version: 1`.

  CLI 0.4.0 was published on **2026-09-07 at 01:47:36 UTC (09:47:36 UTC+8)**. Both the public binary release and npm package are version 0.4.0.

  Standalone binaries do not include skill files. Install the npm package to use or update the bundled skills; a binary-only update can report that the skill tree is missing even when the CLI upgrade succeeds.

  ### Links

  * [List accounts](/en/api-reference/publishing/list-accounts)
</Update>

<a id="2026-09-07-account-quota-errors" />

<Update label="September 7, 2026" tags={["Platform", "Text"]} rss={{ title: "Account quota errors on OpenAI text endpoints" }}>
  OpenAI Completions, Chat Completions, Responses, and Responses Compact return HTTP **402** with `error.type` and `error.code` set to `insufficient_quota` when the local account balance or subscription allowance cannot cover pre-consume. Streaming requests receive the JSON error before SSE starts. Check balance or allowance before trying again; do not treat this as invalid credentials or temporary rate limiting. Token errors, upstream provider errors, other protocols, actual 401/403, ordinary 429, and 5xx behavior are unchanged.

  Gateway enforcement began on September 7, 2026 at 07:25:20 UTC+8 (2026-09-06T23:25:20Z).

  ### Links

  * [Connection and usage](/en/faqs/connection-usage)
</Update>

<a id="2026-08-31-catalog-sync" />

<Update label="August 31, 2026" tags={["New models", "Text", "Image", "Video", "Audio"]} rss={{ title: "Catalog synchronization: Gemini 3.7, GLM 5.3, Wan 3.0, Seedance 2.0, Grok Imagine, Audio TTS & STT" }}>
  ## Language series

  * **Gemini:** Added `gemini-3.7-flash`
  * **GLM:** Added `glm-5.3`
  * **Grok:** Added `grok-4.6`
  * **DeepSeek:** Added `deepseek-v4-flash-vision-exp`

  ## Image & Video series

  * Canonical model ID hyphenation and full coverage for **Wan 3.0** (`wan-3.0`, `wan-3.0-prime`, `wan-3.0-prime-ref`, `wan-3.0-ref`), **Seedance 2.0** (`seedance-2-0`, `seedance-2-0-fast`, `seedance-2-0-mini`, `seedance-2-5`), **Kling** (`kling-v3`, `kling-v2-6`, `kling-avatar`, `kling-o3`, `kling-v3-motion-control`), **Grok Imagine**, and **Midjourney**.
  * Retired legacy Omni Flash duration-fixed SKUs.

  ## Audio series

  * `gpt-4o-mini-tts` (`POST /v1/audio/speech`)
  * `whisper-1` (`POST /v1/audio/transcriptions`)
  * `suno` (`POST /v1/video/generations`)

  ### Links

  * [Pricing](/en/api-reference/account/pricing)
  * [Audio Speech](/en/api-reference/audio-series/models/gpt-4o-mini-tts)
</Update>

<a id="2026-08-31-media-catalog" />

<Update label="August 31, 2026" tags={["New models", "Image", "Video"]} rss={{ title: "Seedream 5.0 Pro, Qwen Image 3.0, Grok Imagine Image 2.0, Kling O3, Omni 1.1, PixVerse v6, Vidu Q3" }}>
  ## Image

  * **Model IDs:** `seedream-5-0-pro`, `qwen-image-3-0`, `grok-imagine-image-2-0`
  * **API:** `POST /v1/images/generations`

  ## Video

  * **Model IDs:** `kling-o3`, `gemini-omni-1.1`, `pixverse-v6`, `vidu-q3`
  * **API:** async `POST` / `GET` `/v1/video/generations`

  `kling-o3` is a new id and does not replace `kling-v3`. `gemini-omni-1.1` is distinct from `gemini-omni-flash`. Pin IDs from live pricing.

  ### Links

  * [Pricing](/en/api-reference/account/pricing)
  * [Video task poll](/en/api-reference/tasks/video-task)
</Update>

<a id="2026-08-25-social-analytics-reader-seats" />

<Update label="August 25, 2026" tags={["Platform", "Text"]} rss={{ title: "Social analytics & inbox suite, Jina Reader extractor, and social seats" }}>
  ## Social Analytics & Inbox Suite

  OmniMux now exposes 11 RESTful analytics endpoints under `/api/social/v1` for comprehensive audience and engagement intelligence:

  * **Analytics:** Daily metrics timeseries, 7x24 weekly best time to post heatmap, posting frequency cadence model, content decay curve, follower growth snapshots, posts performance ranking, and external posts incremental synchronization.
  * **Inbox Analytics:** Message volume trends, response time (TTR) distribution, 7x24 incoming activity heatmap, and source breakdown across connected platforms.

  ## Jina Reader Relay (`POST /v1/reader`)

  * **Model ID:** `jina-reader-v1`
  * **Capability:** URL to clean Markdown / structured JSON text extraction with CSS selectors filtering and output-token billing.
  * **Auth:** Standard gateway Bearer `sk-...` token.

  ## Social Seats Management (`GET /api/social/v1/seats`)

  * Inspects current active connected social accounts, total quota capacity, and vacant seat availability.

  ### Links

  * [Jina Reader Extractor](/en/api-reference/reader-series/models/jina-reader-v1)
  * [Daily Metrics](/en/api-reference/publishing/analytics/daily-metrics)
  * [Social Seats](/en/api-reference/publishing/seats)
</Update>

<a id="2026-08-16-index-tts-ltx-docs" />

<Update label="August 16, 2026" tags={["New models", "Audio", "Video"]} rss={{ title: "Index TTS voice clone plus LTX digital-human contract" }}>
  ## New model

  * **Model ID:** `index-tts`
  * **Path:** `POST` / `GET` `/v1/video/generations` (GxgenAI task path; result is audio)
  * **Contract:** `metadata.nodeInfoList` required — node `4/audio` (reference clip) and `7/text` (script)

  ## Docs fix

  * **`ltx-2-3-kj`** is a photo + audio lip-sync model. Prompt-only text-to-video examples were incorrect. Send image node `444` and audio node `1755`.

  ### Links

  * [Index TTS](/en/api-reference/audio-series/models/index-tts)
  * [LTX digital human](/en/api-reference/video-series/models/ltx-2-3-kj)
</Update>

<a id="2026-08-09-platform-api-updates" />

<Update label="August 9, 2026" tags={["Platform"]} rss={{ title: "API Updates timeline opens" }}>
  ## API Updates

  OmniMux now publishes a dated **API Updates** feed so you can track gateway model launches and platform changes in one place.

  ### What we log

  * **New models** — callable model IDs on live pricing
  * **Model updates** — modes, durations, resolutions, parameters
  * **Pricing** — material rate changes
  * **Platform** — auth, domains, public HTTP surfaces

  ### How to call OmniMux

  | Surface               | URL                         |
  | --------------------- | --------------------------- |
  | Console               | `https://omnimux.ai`        |
  | OpenAI-compatible API | `https://api.omnimux.ai/v1` |
  | Docs                  | `https://docs.omnimux.ai`   |
  | Status                | `https://status.omnimux.ai` |

  Auth for relay: Bearer `sk-…` from the console. Full catalog always lives on console pricing — this page is the **change timeline**.

  ### Links

  * [Quickstart](/en/quickstart)
  * [Pricing](/en/api-reference/account/pricing)
</Update>

<a id="2026-08-09-social-data" />

<Update label="August 9, 2026" tags={["New models", "Social data"]} rss={{ title: "Social data models — TikTok, Instagram, X, YouTube" }}>
  ## Social data (read-only)

  **Social data** model IDs are available on OmniMux for read-only public profile and content style access. This is **not** social publishing.

  ### Model IDs

  | Platform  | IDs                                                                       |
  | --------- | ------------------------------------------------------------------------- |
  | TikTok    | `tiktok-user`, `tiktok-posts`, `tiktok-video`, `tiktok-search`            |
  | Instagram | `instagram-user`, `instagram-posts`, `instagram-post`, `instagram-search` |
  | X         | `x-user`, `x-posts`, `x-tweet`, `x-search`                                |
  | YouTube   | `youtube-user`, `youtube-posts`, `youtube-video`, `youtube-search`        |

  ### Publishing (different surface)

  Connect accounts and create posts use **`/api/social/v1/*`** with access token + `New-Api-User`. Do not mix that auth with gateway `sk-` Chat Completions.

  ### Links

  * [TikTok user profile](/en/api-reference/social-data/tiktok/user-profile)
  * [X tweet detail](/en/api-reference/social-data/x/tweet-detail)
  * [Create post (publishing)](/en/api-reference/publishing/create-post)
</Update>

<a id="2026-08-07-seedance-2-5" />

<Update label="August 7, 2026" tags={["New models", "Video"]} rss={{ title: "Seedance 2.5 — longer video with multimodal references" }}>
  ## Seedance 2.5

  **Seedance 2.5** is now available on OmniMux for async video generation.

  ### New model

  * **Model ID:** `seedance-2-5`
  * **Create:** `POST /v1/video/generations`
  * **Poll:** `GET /v1/video/generations/{task_id}`
  * **Highlights:** longer single-pass generation and multimodal reference inputs (text / image / video / audio style workflows)

  Pin the exact ID from live pricing before integrating.

  ### Links

  * [Video task poll](/en/api-reference/tasks/video-task)
  * [Pricing](/en/api-reference/account/pricing)
</Update>

<a id="2026-07-30-minimax-h3" />

<Update label="July 30, 2026" tags={["New models", "Video"]} rss={{ title: "MiniMax H3 — text-to-video and frame variants" }}>
  ## MiniMax H3

  **MiniMax H3** video models are now available on OmniMux.

  ### New models

  | Model ID              | Role                         |
  | --------------------- | ---------------------------- |
  | `minimax-h3`          | Standard text/image-to-video |
  | `minimax-h3-t2v`      | Text-to-video                |
  | `minimax-h3-flf`      | First/last-frame style I2V   |
  | `minimax-h3-fl2va`    | FL2VA-oriented path          |
  | `minimax-h3-endframe` | End-frame reference I2V      |

  ### API

  * **Create:** `POST /v1/video/generations`
  * **Poll:** `GET /v1/video/generations/{task_id}`

  Async only — submit once, then poll task status.

  ### Links

  * [MiniMax H3 Video](/en/api-reference/video-series/models/minimax-h3)
  * [MiniMax H3 T2V](/en/api-reference/video-series/models/minimax-h3-t2v)
  * [Video task poll](/en/api-reference/tasks/video-task)
</Update>

<a id="2026-07-28-grok-imagine-video-1-5" />

<Update label="July 28, 2026" tags={["New models", "Video"]} rss={{ title: "Grok Imagine Video 1.5" }}>
  ## Grok Imagine Video 1.5

  **Grok Imagine Video 1.5** is now available on OmniMux.

  ### New model

  * **Model ID:** `grok-imagine-video-1-5`
  * **Mode:** image-to-video style generation via async video API
  * **Create / poll:** `POST` / `GET` `/v1/video/generations`

  See the model page for parameters and the task poll contract.

  ### Links

  * [Grok Imagine Video 1.5](/en/api-reference/video-series/models/grok-imagine-video-1-5)
  * [Video task poll](/en/api-reference/tasks/video-task)
</Update>

<a id="2026-07-25-claude-opus-5" />

<Update label="July 25, 2026" tags={["New models", "Text"]} rss={{ title: "Claude Opus 5" }}>
  ## Claude Opus 5

  **Claude Opus 5** is now available on OmniMux through OpenAI-compatible Chat Completions.

  ### New model

  * **Model ID:** `claude-opus-5`
  * **Endpoint:** `https://api.omnimux.ai/v1` (Chat Completions)
  * **Docs:** one complete page per brand — `model` is an enum on the Claude complete page

  Related Claude IDs on the gateway include other Opus / Sonnet / Haiku SKUs on live pricing.

  ### Links

  * [Claude complete](/en/api-reference/text-series/claude/complete)
</Update>

<a id="2026-07-22-gemini-3-6-flash" />

<Update label="July 22, 2026" tags={["New models", "Text"]} rss={{ title: "Gemini 3.6 Flash and Gemini 3.5 Flash" }}>
  ## Gemini Flash models

  New Gemini Flash-class models are available on OmniMux.

  ### New models

  * **Model IDs:** `gemini-3.6-flash`, `gemini-3.5-flash`
  * **API:** OpenAI-compatible Chat Completions at `https://api.omnimux.ai/v1`

  Additional Gemini IDs (Pro / preview / lite) may also appear on live pricing — pin the exact ID from the console or Gemini complete page.

  ### Links

  * [Gemini complete](/en/api-reference/text-series/gemini/complete)
</Update>

<a id="2026-07-17-kimi-k3" />

<Update label="July 17, 2026" tags={["New models", "Text"]} rss={{ title: "Kimi K3 — long-context reasoning" }}>
  ## Kimi K3

  **Kimi K3** is now available on OmniMux.

  ### New model

  * **Model ID:** `kimi-k3`
  * **API:** Chat Completions at `https://api.omnimux.ai/v1`
  * **Focus:** long-context reasoning and agent-style workflows

  See the Kimi complete page for the full model enum.

  ### Links

  * [Kimi complete](/en/api-reference/text-series/kimi/complete)
</Update>

<a id="2026-07-16-suno" />

<Update label="July 16, 2026" tags={["New models", "Audio"]} rss={{ title: "Suno — music generation" }}>
  ## Suno

  **Suno** music generation is now available on OmniMux.

  ### New model

  * **Model ID:** `suno`
  * **Use:** AI music generation workflows via the gateway catalog

  Confirm billing and request shape from live pricing / console before production traffic.

  ### Links

  * [Pricing](/en/api-reference/account/pricing)
</Update>

<a id="2026-07-01-nano-banana" />

<Update label="July 1, 2026" tags={["New models", "Image"]} rss={{ title: "Nano Banana 2 and Nano Banana Pro" }}>
  ## Nano Banana

  **Nano Banana 2** and **Nano Banana Pro** are now available on OmniMux.

  ### New models

  * **Model IDs:** `nano-banana-2`, `nano-banana-pro`
  * **Modality:** image generation

  See each model page for request parameters.

  ### Links

  * [Nano Banana 2](/en/api-reference/image-series/models/nano-banana-2)
  * [Nano Banana Pro](/en/api-reference/image-series/models/nano-banana-pro)
</Update>

<a id="2026-06-25-seedance-2-0" />

<Update label="June 25, 2026" tags={["New models", "Video"]} rss={{ title: "Seedance 2.0 family — Standard, Mini, Fast" }}>
  ## Seedance 2.0

  The **Seedance 2.0** family is available on OmniMux for async video generation.

  ### New models

  | Model ID            | Role                        |
  | ------------------- | --------------------------- |
  | `seedance-2-0`      | Standard                    |
  | `seedance-2-0-mini` | Lightweight / cost-oriented |
  | `seedance-2-0-fast` | Speed-oriented              |

  ### API

  * **Create:** `POST /v1/video/generations`
  * **Poll:** `GET /v1/video/generations/{task_id}`

  ### Links

  * [Video task poll](/en/api-reference/tasks/video-task)
  * [Pricing](/en/api-reference/account/pricing)
</Update>

<a id="2026-06-17-glm-5-2" />

<Update label="June 17, 2026" tags={["New models", "Text"]} rss={{ title: "GLM-5.2" }}>
  ## GLM-5.2

  **GLM-5.2** is now available on OmniMux (with related GLM IDs on pricing).

  ### New models

  * **Model IDs:** `glm-5.2`, `glm-5.1`
  * **API:** Chat Completions at `https://api.omnimux.ai/v1`

  ### Links

  * [GLM complete](/en/api-reference/text-series/glm/complete)
</Update>

<a id="2026-06-16-kling" />

<Update label="June 16, 2026" tags={["New models", "Video"]} rss={{ title: "Kling V3 and Kling V2.6" }}>
  ## Kling

  **Kling** video models are available on OmniMux.

  ### New models

  * **Model IDs:** `kling-v3`, `kling-v2-6`
  * **API:** async `POST` / `GET` `/v1/video/generations`

  Pin IDs from live pricing; request parameters follow the video task contract.

  ### Links

  * [Video task poll](/en/api-reference/tasks/video-task)
  * [Pricing](/en/api-reference/account/pricing)
</Update>

<a id="2026-06-15-midjourney" />

<Update label="June 15, 2026" tags={["New models", "Image"]} rss={{ title: "Midjourney" }}>
  ## Midjourney

  **Midjourney** is available on OmniMux as model ID `midjourney`.

  ### New model

  * **Model ID:** `midjourney`
  * **Modality:** image generation via the gateway catalog

  Confirm request shape and billing on console pricing before production use.

  ### Links

  * [Pricing](/en/api-reference/account/pricing)
</Update>

<a id="2026-06-01-minimax-m3" />

<Update label="June 1, 2026" tags={["New models", "Text"]} rss={{ title: "MiniMax M3" }}>
  ## MiniMax M3

  **MiniMax M3** is now available on OmniMux Chat Completions.

  ### New model

  * **Model ID:** `minimax-m3`
  * **API:** `https://api.omnimux.ai/v1`

  ### Links

  * [MiniMax complete](/en/api-reference/text-series/minimax/complete)
</Update>

<a id="2026-05-20-omni-flash" />

<Update label="May 20, 2026" tags={["New models", "Video"]} rss={{ title: "Omni Flash — duration video family" }}>
  ## Omni Flash

  **Omni Flash** (`gemini-omni-flash`) is available on OmniMux for fast video generation.

  ### Model

  * **Model ID:** `gemini-omni-flash`
  * **API:** `POST /v1/video/generations` + poll `GET /v1/video/generations/{task_id}`

  ### Links

  * [Omni Flash](/en/api-reference/video-series/models/gemini-omni-flash)
  * [Video task poll](/en/api-reference/tasks/video-task)
</Update>

<a id="2026-05-20-veo-3-1" />

<Update label="May 20, 2026" tags={["New models", "Video"]} rss={{ title: "Veo 3.1" }}>
  ## Veo 3.1

  **Veo 3.1** is now available on OmniMux.

  ### New model

  * **Model ID:** `veo-3.1`
  * **API:** async video create + poll on `/v1/video/generations`

  ### Links

  * [Veo 3.1](/en/api-reference/video-series/models/veo-3.1)
  * [Video task poll](/en/api-reference/tasks/video-task)
</Update>

<a id="2026-05-05-claude-opus-4-7-deepseek-v4" />

<Update label="May 5, 2026" tags={["New models", "Text"]} rss={{ title: "Claude Opus 4.7 and DeepSeek V4" }}>
  ## Claude Opus 4.7 and DeepSeek V4

  New language models are available on OmniMux Chat Completions.

  ### New models

  | Model ID            | Brand    |
  | ------------------- | -------- |
  | `claude-opus-4-7`   | Claude   |
  | `deepseek-v4-flash` | DeepSeek |
  | `deepseek-v4-pro`   | DeepSeek |

  ### API

  * **Endpoint:** `https://api.omnimux.ai/v1` (Chat Completions)

  ### Links

  * [Claude complete](/en/api-reference/text-series/claude/complete)
  * [DeepSeek complete](/en/api-reference/text-series/deepseek/complete)
</Update>

<a id="2026-04-28-gpt-image-2" />

<Update label="April 28, 2026" tags={["New models", "Image"]} rss={{ title: "GPT Image 2" }}>
  ## GPT Image 2

  **GPT Image 2** is now available on OmniMux.

  ### New models

  * **Model IDs:** `gpt-image2`, `gpt-image2-hd`
  * **Modality:** image generation

  See model docs for size / quality parameters.

  ### Links

  * [GPT Image 2](/en/api-reference/image-series/models/gpt-image-2)
  * [GPT Image 2 HD](/en/api-reference/image-series/models/gpt-image-2-hd)
</Update>

<a id="2026-03-08-minimax-m2-5" />

<Update label="March 8, 2026" tags={["New models", "Text"]} rss={{ title: "MiniMax M2.5" }}>
  ## MiniMax M2.5

  **MiniMax M2.5** (and related MiniMax text IDs) are available on OmniMux.

  ### New models

  * **Model IDs:** `minimax-m2.5`, `minimax-m2.7`
  * **API:** Chat Completions

  ### Links

  * [MiniMax complete](/en/api-reference/text-series/minimax/complete)
</Update>

<a id="2026-03-06-gpt-5-4" />

<Update label="March 6, 2026" tags={["New models", "Text"]} rss={{ title: "GPT-5.4 series" }}>
  ## GPT-5.4

  **GPT-5.4** series models are available on OmniMux Chat Completions.

  ### New models

  * **Model IDs:** `gpt-5.4`, `gpt-5.4-mini`
  * **API:** `https://api.omnimux.ai/v1`

  Later GPT-5.x IDs (for example `gpt-5.5`, `gpt-5.6-terra`) may also appear on live pricing — always pin the ID from the console.

  ### Links

  * [GPT complete](/en/api-reference/text-series/gpt/complete)
</Update>

***

**Machine-readable:** [`/data/changelog/index.json`](/data/changelog/index.json) · [`/data/changelog/pages/1.json`](/data/changelog/pages/1.json)