Skip to main content
The VLM Run Gateway is free during the alpha, subject to the per-tier rate limits.
The VLM Run Gateway bills per token, metered on every request. The rates below come straight from the live model catalog (GET /v1/models/{model_id}), so they always match what you are actually charged. Two signals let you wire up cost tracking today:
  • Per-model rate card. Each model exposes a pricing object with USD-per-1M-token rates for prompt, completion, input_cache_read, input_cache_write, and image, plus flat request and per_page rates.
  • Per-request cost. usage.cost on every chat completion, embeddings, and streaming response is the actual metered charge for that request.
While the Gateway is in alpha and available at no cost, the rates below are the currently published rates and may change during or after the alpha. Always read pricing from the model catalog (or usage.cost on a response) as the source of truth.

​
How billing works

  • All rates are USD per 1M tokens unless noted.
  • Input is prompt tokens, Cached input is input_cache_read, Output is completion tokens, and Image is priced per 1M image-token equivalents.
  • input_cache_write, request, and per_page are $0.00 across all models today.
  • Context tier. Requests up to 272K input tokens bill at short-context rates. Above 272K, all rates (input, cached input, and output) bill at 2x. The tier applies to chat, vision, and document requests; embeddings and transcription are single-rate.

​
What 1M tokens buys

A 1M-token budget covers roughly the following:
  • ~3,000 image captions at ~200 input + 130 output tokens / image
  • Markdown from a ~2K-page slide deck with figures at ~500 output tokens / page
  • ~4,000 visual questions at ~200 input + 50 output tokens / question
  • ~2,000 text passages embedded at ~512 tokens / passage
  • Markdown from ~1K pages of legal docs with dense text at ~1,000 output tokens / page

​
Vision and document models

method (ocr, markdown, detect, chat) does not change the rate; you pay the per-token prices below for whichever model serves the request.

Prices in USD per 1M tokens

​
Embeddings

Prices in USD per 1M tokens

​
Transcription

Transcription bills the audio it ingests as input tokens; there is no separate output charge.

Prices in USD per 1M tokens

​
How to get model pricing

cURL

Get Model

Full response schema, including pricing.

Rate Limits

Per-tier request quotas.