Chat models
This table is auto-generated from the Verlon model registry on every sync — see the live registry for pricing, benchmarks, and deprecation dates.
Other modalities
- audio — 5 models
- embeddings — 3 models
- image generation — 7 models
- text-to-speech — 3 models
- video generation — 3 models
/v1/embeddings, /v1/images/generations, and /v1/audio/speech as drop-in routes. Video generation is drop-in too: the openai package’s async Videos surface (videos.create() / retrieve() / downloadContent()) works against /v1/videos.
Quickstart
First time? Create a gate and grab an API key — the examples below need a
GATE_ID and VERLON_API_KEY.gemini-2.5-pro for gemini-3.5-flash, gemini-flash-latest, or any other ID.
SDK compatibility
Any SDK with a Verlon drop-in endpoint can reach every model on this page — today that’s the OpenAI SDK and the Anthropic SDK: point it at Verlon, reference a gate that routes here, and your code stays unchanged. The quickstart above is all it takes. Verlon also mirrors Gemini’s native API at/v1beta/models/..., so tooling that speaks the Gemini REST shape works unchanged too. The Verlon SDK isn’t needed for inference — its home is agent tracing, observability, and the model registry.
Streaming
What’s supported
Streaming
Streaming
Full support for
stream: true in every supported SDK — identical semantics to the source SDK.Tool / function calling
Tool / function calling
Fully supported. Verlon translates the tool-call shape between OpenAI / Anthropic / Gemini native formats.
Vision
Vision
Image inputs work with any vision-capable Gemini model — including the multimodal Gemini 2.5 Flash and Pro lines.
Standard parameters
Standard parameters
temperature, max_tokens, top_p, stop_sequences, and the rest are passed through and mapped to Gemini’s native fields.Usage + cost tracking
Usage + cost tracking
Every response includes token usage plus Verlon’s
cost field with per-call dollar amount.How it works
- You send a request in your chosen SDK’s format
- Verlon receives — validates the gate, applies routing rules
- Verlon translates to Gemini’s native format and dispatches to Google’s API
- Google responds with the raw Gemini response
- Verlon normalizes back to your SDK’s expected shape (OpenAI, Anthropic, or Gemini-native)
- You receive a response in the format your code already handles, with an added
costfield
Errors
The error shape always matches the SDK you’re calling with. Through the OpenAI SDK it surfaces as a thrown
APIError:
Full non-chat model list
Every non-chat Google model Verlon routes to, grouped by modality. Chat models are in the table near the top of this page.Audio
Embeddings
Image generation
Text-to-speech
Video generation
Related
- OpenAI · Anthropic · Mistral
- Verlon SDK reference — agent tracing, observability, and the model registry
- Gates — set up routing rules and model configuration
- Bring your own key — use your own Google account for provider costs
- Google’s Gemini API docs ↗

