> ## Documentation Index
> Fetch the complete documentation index at: https://docs.vlm.run/llms.txt
> Use this file to discover all available pages before exploring further.

# Frontier Models

> Frontier vision AI models the Gateway routes to via upstream providers.

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`](/gateway/api-reference/get-models) a frontier model
carries an upstream vendor in its `provider` field. Which vendor serves a given
model can change as capacity and price move, so read it from the catalog at call
time rather than pinning it here.

Prices are the provider's listed prices in USD per 1M tokens (input / output).

| Model                                 | Modalities         | Context |  Input |  Output |
| ------------------------------------- | ------------------ | ------: | -----: | ------: |
| `google/gemini-3.5-flash-lite`        | text, image, video |      1M | \$0.30 |  \$2.50 |
| `google/gemini-3.7-flash`             | text, image, video |      1M | \$0.75 |  \$3.75 |
| `google/gemini-robotics-er-2-preview` | text, image, video |      1M | \$0.30 |  \$2.50 |
| `google/gemma-4-26b-a4b-it`           | text, image, video |    128K | \$0.10 |  \$0.30 |
| `meta/muse-glimmer-30b`               | text, image, video |    128K | \$0.35 |  \$1.50 |
| `meta/muse-spark-1.2`                 | text, image, video |      1M | \$1.25 |  \$4.25 |
| `minimax/minimax-m3`                  | text, image, video |      1M | \$0.30 |  \$1.20 |
| `moonshotai/kimi-k3`                  | text, image, video |    256K | \$3.00 | \$15.00 |

<p className="table-note">Prices in USD per 1M tokens</p>

Every frontier model accepts a JSON Schema `response_format`, except
`meta/muse-glimmer-30b`, which accepts `json_object` only. See
[Methods & Response Format](/gateway/methods).

[`qwen/qwen3.8-27b`](/gateway/models/qwen-qwen3.8-27b) is not listed here. It runs
on VLM Run GPUs, so its `provider` reads `vlm-run` rather than an upstream
vendor, and it is documented with the Gateway
[VQA models](/gateway/models#visual-question-answering-vqa). Treat `vlm-run`,
and an empty `provider`, as the two ways the catalog says "self-hosted".

## Next steps

<CardGroup cols={2}>
  <Card title="Models" icon="table-list" href="/gateway/models">
    The full Gateway model catalog.
  </Card>

  <Card title="Chat Completions API" icon="code" href="/gateway/api-reference/post-chat-completions">
    Full request parameters, streaming, and error handling.
  </Card>
</CardGroup>