Model Catalog¶

This page lists all models currently available on WS AI Gateway. The list is generated from the live /v1/models endpoint — you can query it yourself at any time.

Listing Models via API¶

curl http://baseurl/v1/models \
  -H "Authorization: Bearer $WS_API_KEY"

Response Example:

{
  "data": [
    {
      "id": "claude-sonnet-4-6",
      "object": "model",
      "owned_by": "vertex-ai",
      "supported_endpoint_types": ["anthropic", "openai"]
    },
    {
      "id": "gemini-2.5-flash",
      "object": "model",
      "owned_by": "vertex-ai",
      "supported_endpoint_types": ["gemini", "openai"]
    }
  ]
}

The supported_endpoint_types field tells you which API formats a model accepts:

Endpoint Type	Endpoint	Documentation
`openai`	`POST /v1/chat/completions`	OpenAI Format
`anthropic`	`POST /v1/messages`	Anthropic Format
`gemini`	`POST /v1beta/models/{model}:generateContent`	Google Format

Chat Models¶

Anthropic Claude¶

All Claude models support both the Anthropic and OpenAI formats.

Model ID	Notes
`claude-fable-5`	Latest flagship, Claude 5 family
`claude-opus-4-8`	Opus 4.8
`claude-opus-4-7`	Opus 4.7
`claude-opus-4-6`	Opus 4.6
`claude-opus-4-5-20251101`	Opus 4.5 (dated snapshot)
`claude-sonnet-4-6`	Sonnet 4.6 — balanced performance and cost
`claude-sonnet-4-5-20250929`	Sonnet 4.5 (dated snapshot)
`claude-haiku-4-5-20251001`	Haiku 4.5 — fastest, lowest cost

OpenAI GPT¶

GPT models are served through the OpenAI format.

Model ID	Notes
`gpt-5.6-sol`	Latest GPT series
`gpt-5.5`
`gpt-5.4` / `gpt-5.4-pro`	Full-size
`gpt-5.4-mini` / `gpt-5.4-nano`	Lightweight, low latency
`gpt-5.3-codex`	Code-optimized
`gpt-5.2` / `gpt-5.2-codex`
`gpt-5.1` / `gpt-5.1-codex`
`gpt-5`

Google Gemini¶

All Gemini models support both the Gemini and OpenAI formats.

Model ID	Notes
`gemini-3.5-flash`	Latest Flash
`gemini-3.1-pro-preview`	Pro preview
`gemini-3.1-pro-preview-customtools`	Pro preview with custom tools
`gemini-3-flash-preview`
`gemini-2.5-pro`
`gemini-2.5-flash`
`gemini-2.5-flash-lite`	Lowest latency

Other Providers¶

Served through the OpenAI format.

Model ID	Provider
`deepseek-v4-pro`	DeepSeek
`deepseek-v4-flash`	DeepSeek
`glm-5` / `glm-5.1`	Zhipu GLM
`kimi-k2.6`	Moonshot Kimi
`MiniMax-M2.5`	MiniMax
`qwen3.6-plus`	Alibaba Qwen
`xai.grok-4.3`	xAI Grok

Embedding Models¶

Served through POST /v1/embeddings — see Embeddings.

Model ID	Dimensions
`text-embedding-3-large`	up to 3072
`text-embedding-3-small`	up to 1536
`text-embedding-ada-002`	1536

Image Generation Models¶

See Image Generation.

Model ID	Provider	Format
`gpt-image-2`	OpenAI	`/v1/images/generations`
`gemini-3.1-flash-image-preview`	Google	Gemini / OpenAI
`gemini-3-pro-image-preview`	Google	Gemini / OpenAI
`gemini-2.5-flash-image`	Google	Gemini / OpenAI
`viduq1-image` / `viduq2-image`	Vidu	`/v1/images/generations`

Video Generation Models¶

See Video Generation.

Model ID	Provider
`veo-3.1-generate-preview` / `veo-3.1-fast-generate-preview`	Google Veo
`veo-3.0-generate-001` / `veo-3.0-fast-generate-001`	Google Veo
`kling-v3` / `kling-v2-6` / `kling-v2-5-turbo`	Kling
`viduq3-pro` / `viduq3-turbo` / `viduq3-fast`	Vidu
`happyhorse-1.0-t2v`	HappyHorse (text-to-video)

Speech Models¶

Model ID	Capability
`gemini-3.1-flash-tts-preview`	Text-to-speech (Gemini format)

Model availability

The model list may change over time as new models are launched and old ones are retired. Always rely on GET /v1/models for the authoritative, real-time list available to your key.