Routed Models

The Gateway also routes to frontier vision AI models via upstream providers, so you can use the same API key and baseURL to access them as well. These models are passthrough VLMs supporting the same methods and method_params reported by their providers. On GET /v1/openai/models a routed model carries a non-empty provider field. Prices are the provider’s listed prices in USD per 1M tokens (input / output).

Model	Provider	Modalities	Context	Input	Output
`google/gemini-3.5-flash-lite`	`google-vertex`	text, image, video	1M	$0.30	$2.50
`google/gemini-3.7-flash`	`google-vertex`	text, image, video	1M	$0.75	$3.75
`google/gemini-robotics-er-2-preview`	`google-gemini`	text, image, video	1M	$0.30	$2.50
`google/gemma-4-26b-a4b-it`	`google-vertex`	text, image	131K	$0.10	$0.30
`google/gemma-4-31b-it`	`huggingface`	text, image, video	131K	$0.15	$0.40
`meta/muse-glimmer-30b`	`fireworks`	text, image, video	131K	$0.35	$1.50
`meta/muse-spark-1.2`	`meta`	text, image, video	1M	$1.25	$4.25
`minimax/minimax-m3`	`fireworks`	text, image, video	1M	$0.30	$1.20
`moonshotai/kimi-k3`	`fireworks`	text, image, video	262K	$3.00	$15.00

Prices in USD per 1M tokens

Every routed model accepts a JSON Schema response_format, except meta/muse-glimmer-30b, which accepts json_object only. See Methods & Response Format. qwen/qwen3.8-27b is not listed here. It runs on VLM Run GPUs, so it carries no provider, and it is documented with the Gateway VQA models.

Overview

Guides

API Reference

Misc

Next steps

Models

Chat Completions API

​Next steps

Models

Chat Completions API

Next steps