Join early access

Elsewhere X @myriaxlabs (opens in a new tab)

Models · planned, early access

Every task, one compatible API.

Text, speech, images and, later, video, through one OpenAI-compatible API. Each model's price, license and status will be listed in the catalog at launch.

Models at launch

One key for every task.

Organised by task, so you can pick by the job you need done. At launch, the catalog lists every model with its price, license and status. Launch models depend on signed provider agreements, so this list can change before launch.

01 / TEXT

Text generation

At launch
POST /v1/chat/completions
  • Llama 3.3 70B
  • Qwen3
  • DeepSeek V3.2
  • gpt-oss
  • Gemma 3
  • Mistral Small 3.2

Proprietary models through your own key (BYOK), provider by provider as each is cleared.

02 / STT

Speech to text

At launch
POST /v1/audio/transcriptions
  • Whisper large-v3
  • Whisper large-v3-turbo

03 / TTS

Text to speech

At launch
POST /v1/audio/speech
  • Kokoro
  • Chatterbox
  • Orpheus

Preset voices only at launch.

04 / IMAGES

Image generation and editing

At launch once image safety screening is approved
POST /v1/images/generations, /edits
  • FLUX.1 schnell
  • FLUX 1.1 pro
  • Seedream 4.0

Every image will be hash-checked before delivery.

05 / VIDEO

Video

Not at launch
POST /v1/jobs
  • Wan 2.2
  • p-video

Off at launch. Opens as a staged unlock once video moderation is in place.

Early access

Get in before launch.

Early access opens to a small group of teams first. Tell us what you'd run through Myriax.

Join early access