Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.mountsea.ai/llms.txt

Use this file to discover all available pages before exploring further.

​
Introduction to Hub

Hub is Mountsea’s premium AI Gateway — a single unified API for the world’s best image, video, audio and transcription models.
One endpoint per capability, many models. Switch models without changing your code — just change the model field in the request body.

​
Why Hub?

Flagship Quality

Official flagship models only. No knock-offs, no lossy distillations. Same model weights, same outputs — Veo 3.1, Nano Banana Pro, GPT Image 2, Kling v3 Pro, WAN 2.7, Seedance 2.0, ElevenLabs Music.

Production Stable

Built for 24/7 production traffic. Multi-region routing, automatic failover, transparent retries, and queue-aware load balancing. No surprise rate-limit walls, no flaky upstreams.

Cheaper Than Official

Pay only for successful generations, billed in unified credits at a meaningful discount versus going direct to the model provider. No per-provider minimums, no monthly subscriptions.

​
A Closer Look

HubGoing direct to each provider
ModelsOfficial flagship models across 4 capabilities — image, video, audio, transcribeSign up & maintain 6+ separate accounts (Google, OpenAI, Kuaishou, Alibaba, ByteDance, ElevenLabs, …)
PricingLower than the official list price, paid only on status=completed — failed tasks are freePay full retail; failures still consume quota on most providers
StabilitySmart routing across redundant upstream channels, automatic retry on transient errorsSingle point of failure; manual retry logic & rate-limit handling on your side
OnboardingOne Bearer token, one Base URL, one credit balancePer-provider keys, per-provider billing, per-provider SDKs
MaintenanceNew models added & old ones routed for youTrack every provider’s deprecations & migration notices yourself
Same outputs at a lower price. Hub forwards your request to the original provider’s flagship endpoint — what comes back is the same media you’d get going direct, just at Hub’s discounted rate and with stability guarantees baked in.

​
Capabilities

Image

Nano Banana (Fast / 2 / Pro) + GPT Image 2 — text-to-image and image editing

Video

Veo 3.1 · Kling v3 · WAN 2.7 · Seedance 2.0 — t2v, i2v, multi-ref, first-last, video edit

Audio (Music)

ElevenLabs Music — text-to-music with length & instrumental control

Transcribe

Whisper / Wizper — audio & video speech-to-text and translation

​
The Hub Pattern

Every Hub task follows the same simple pattern. Submit a task → get a task_id → poll until ready=true.
1

Discover available models (optional)

Call GET /hub/v1/models?capability=image|video|audio|transcribe to see all models for a capability. For a specific model, GET /hub/v1/models/:model returns its full input_schema plus a ready-to-copy example payload.
2

Submit a task

Send POST /hub/v1/{image|video|audio|transcribe} with { model, input }. You get back { task_id }.
3

Poll for the result

GET /hub/v1/tasks/:task_id — poll every 3–5 seconds until ready=true. The result is in data.

​
🖼️ Image

ModelProviderCapabilityHighlights
nano-bananaGoogletext-to-imageGemini 2.5 Flash Image — fast & cheap
nano-banana-2Googletext-to-imageGemini 3.1 — extreme aspect ratios (1:8 / 8:1)
nano-banana-proGoogletext-to-imageGemini 3 Pro — studio quality, up to 4K
gpt-image-2OpenAItext-to-imageDetailed images with fine typography
*-edit variants—image-to-imageEdit existing images with reference URLs

​
🎬 Video

ModelProviderCapabilityHighlights
veo-3.1 / -fast / -liteGoogletext-to-videoNative audio, 4s / 6s / 8s, up to 4K
veo-3.1-imageGoogleimage-to-videoAnimate a single reference image
veo-3.1-refGooglereference-to-videoMulti-image consistent character
veo-3.1-first-lastGooglefirst-last frameTransition between two frames
kling-v3-pro / -standardKuaishoutext/image-to-video3–15s, native audio, multi-shot
wan-2.7Alibabatext-to-videoHigh quality, default 1080p
wan-2.7-imageAlibabaimage-to-videoFirst-and-last frame, audio driving
wan-2.7-refAlibabareference-to-videoMulti-subject reference
wan-2.7-editAlibabavideo-to-videoInstruction-based video editing
seedance-2.0 / -fastByteDancetext/image-to-videoCinematic, native audio, physics

​
🎵 Audio (Music)

ModelProviderCapabilityHighlights
elevenlabs-musicElevenLabsmusic-generateText-to-music, 3s–10min, instrumental switch

​
🎙️ Transcribe

ModelProviderCapabilityHighlights
Whisper / Wizper—transcribe / translateBCP-47 language codes, word / segment timestamps
Use GET /hub/v1/models?capability=transcribe for the up-to-date list.

​
Quick Example — Image

# 1. Submit
curl -X POST "https://api.mountsea.ai/hub/v1/image" \
  -H "Authorization: Bearer your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nano-banana-pro",
    "input": {
      "prompt": "A photorealistic black labrador swimming, half above water, half underwater",
      "resolution": "2K",
      "aspect_ratio": "1:1"
    }
  }'
# → { "task_id": "hub-xxxxxxxx-..." }

# 2. Poll
curl -H "Authorization: Bearer your-api-key" \
  "https://api.mountsea.ai/hub/v1/tasks/hub-xxxxxxxx-..."

​
Quick Example — Video

curl -X POST "https://api.mountsea.ai/hub/v1/video" \
  -H "Authorization: Bearer your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "veo-3.1-fast",
    "input": {
      "prompt": "Cinematic drone shot flying through ancient stone ruins at golden hour",
      "duration": "8s",
      "resolution": "720p",
      "aspect_ratio": "16:9",
      "generate_audio": true
    }
  }'

​
Quick Example — Music

curl -X POST "https://api.mountsea.ai/hub/v1/audio" \
  -H "Authorization: Bearer your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "elevenlabs-music",
    "input": {
      "prompt": "Uplifting lo-fi hip-hop with mellow piano and vinyl crackle",
      "music_length_ms": 30000
    }
  }'

​
Quick Example — Transcribe

curl -X POST "https://api.mountsea.ai/hub/v1/transcribe" \
  -H "Authorization: Bearer your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "whisper-v3",
    "input": {
      "audio_url": "https://example.com/audio.mp3",
      "language": "en",
      "timestamps": "word"
    }
  }'

​
Endpoints at a Glance

EndpointMethodDescription
/hub/v1/imagePOSTSubmit an image generation / edit task
/hub/v1/videoPOSTSubmit a video generation / edit task
/hub/v1/audioPOSTSubmit a music generation task
/hub/v1/transcribePOSTSubmit a transcription / translation task
/hub/v1/tasks/{task_id}GETPoll task status & result
/hub/v1/modelsGETList every model (optionally filtered by capability)
/hub/v1/models/{model}GETGet a single model’s full input schema + example

​
Task Status

StatusMeaning
pendingQueued, waiting for a worker
processingActively running
completed✅ Done — data contains the result
failed❌ Failed — see error_code / error_message
timeoutExceeded the processing time limit
cancelledCancelled by user or system
Recommended polling interval: 3–5 seconds. Generated assets are stored for two weeks — download promptly.

​
Authentication

All endpoints require Bearer token authentication: 
Authorization: Bearer your-api-key

​
Base URL

https://api.mountsea.ai

​
Explore the API Documentation