One unified API, Any Visual Model.

Document OCR, captioning, and multi-modal chat: every visual capability behind one MCP server.

Read the Docs Get an API Key

Supported providers

Explore models

29 visual models. One endpoint.

Qwen3.8 27B

qwen/qwen3.8-27b

Usage
Context: 164K
Input / 1M: $0.35
Cached / 1M: $0.05
Output / 1M: $2.55

PP-OCRv6

paddleocr/pp-ocrv6

Usage
Context: —
Input / 1M: $0.02
Cached / 1M: $0.02
Output / 1M: $0.40

ViTPose+ Large

usyd-community/vitpose-plus-large

Usage
Context: —
Input / 1M: $0
Cached / 1M: —
Output / 1M: —

Gemini 3.8 Flash

google/gemini-3.8-flash

Usage
Context: 1M
Input / 1M: $0.75
Cached / 1M: $0.075
Output / 1M: $3.75

Qwen3.5 0.8B

qwen/qwen3.5-0.8b

Usage
Context: 80K
Input / 1M: $0.08
Cached / 1M: $0.02
Output / 1M: $0.15

HaMeR

geopavlakos/hamer

Usage
Context: —
Input / 1M: $0
Cached / 1M: —
Output / 1M: —

DiffusionGemma 26B-A4B

google/diffusiongemma-26b-a4b-it

Usage
Context: 80K
Input / 1M: $0.35
Cached / 1M: $0.05
Output / 1M: $1.50

SAM 3.1

facebook/sam3.1

Usage
Context: —
Input / 1M: $1/1K
Cached / 1M: —
Output / 1M: —

LightOnOCR-3 4B

lightonai/lightonocr-3-4b

Usage
Context: 16K
Input / 1M: $0.20
Cached / 1M: $0.20
Output / 1M: $0.50

PaddleOCR-VL 1.6

paddlepaddle/paddleocr-vl-1.6

Usage
Context: 16K
Input / 1M: $0.15
Cached / 1M: $0.15
Output / 1M: $0.35

Florence-2

microsoft/florence-2-base-ft

Usage
Context: —
Input / 1M: $0
Cached / 1M: —
Output / 1M: —

DeepSeek-OCR-2

deepseek-ai/deepseek-ocr-2

Usage
Context: 8K
Input / 1M: $0.25
Cached / 1M: $0.25
Output / 1M: $0.80

GLM-OCR

zai-org/glm-ocr

Usage
Context: 8K
Input / 1M: $0.10
Cached / 1M: $0.02
Output / 1M: $0.20

Gemini 3.5 Flash Lite

google/gemini-3.5-flash-lite

Usage
Context: 1M
Input / 1M: $0.30
Cached / 1M: $0.03
Output / 1M: $2.50

Gemma 4 26B-A4B Instruct

google/gemma-4-26b-a4b-it

Usage
Context: 80K
Input / 1M: $0.10
Cached / 1M: $0.05
Output / 1M: $0.30

dots.mocr

rednote-hilab/dots.mocr

Usage
Context: 24K
Input / 1M: $0.20
Cached / 1M: $0.03
Output / 1M: $0.40

MiniMax M3

minimax/minimax-m3

Usage
Context: 1M
Input / 1M: $0.30
Cached / 1M: $0.06
Output / 1M: $1.20

Kimi K3

moonshotai/kimi-k3

Usage
Context: 256K
Input / 1M: $3
Cached / 1M: $0.30
Output / 1M: $15

Gemini 3.7 Flash

google/gemini-3.7-flash

Usage
Context: 1M
Input / 1M: $0.75
Cached / 1M: $0.075
Output / 1M: $3.75

Gemini 4 Argon

google/gemini-4-argon

Usage
Context: 1M
Input / 1M: $2
Cached / 1M: $0.10
Output / 1M: $10

Muse Spark 1.2

meta/muse-spark-1.2

Usage
Context: 1M
Input / 1M: $1.25
Cached / 1M: $0.15
Output / 1M: $4.25

Muse Glimmer 30B

meta/muse-glimmer-30b

Usage
Context: 128K
Input / 1M: $0.35
Cached / 1M: $0.04
Output / 1M: $1.50

OCR Auto

vlm-run/ocr:auto

Usage
Context: —
Input / 1M: —
Cached / 1M: —
Output / 1M: —

Gemini Robotics-ER 2 (preview)

google/gemini-robotics-er-2-preview

Usage
Context: 128K
Input / 1M: $1
Cached / 1M: $0.10
Output / 1M: $5

Parakeet TDT 0.6B v3

nvidia/parakeet-tdt-0.6b-v3

Usage
Context: —
Input / 1M: $16.67/1M s
Cached / 1M: —
Output / 1M: —

Qwen3-VL Embedding 2B

qwen/qwen3-vl-embedding-2b

Usage
Context: 8K
Input / 1M: $0.02
Cached / 1M: $0.02
Output / 1M: —

Gemini 4 Carbon

google/gemini-4-carbon

Usage
Context: 1M
Input / 1M: $2
Cached / 1M: $0.10
Output / 1M: $10

EmbeddingGemma 2

google/embeddinggemma-2

Usage
Context: 8K
Input / 1M: $0.01
Cached / 1M: $0.01
Output / 1M: —

Nemotron 3.5 Parse

nvidia/nemotron-3.5-parse

Usage
Context: 16K
Input / 1M: $0.10
Cached / 1M: $0.02
Output / 1M: $0.20

RF-DETR Large

roboflow/rf-detr-large

Usage: —
Context: —
Input / 1M: —
Cached / 1M: —
Output / 1M: —

Model	Usage	Capabilities	Context	Input	Cached	Output
Qwen3.8 27B qwen/qwen3.8-27b		detectionchat	164K	$0.35	$0.05	$2.55
PP-OCRv6 paddleocr/pp-ocrv6		ocr	—	$0.02	$0.02	$0.40
ViTPose+ Large usyd-community/vitpose-plus-large		pose	—	$0	—	—
Gemini 3.8 Flash google/gemini-3.8-flash		detectionchat	1M	$0.75	$0.075	$3.75
Qwen3.5 0.8B qwen/qwen3.5-0.8b		detectionchat	80K	$0.08	$0.02	$0.15
HaMeR geopavlakos/hamer		pose	—	$0	—	—
DiffusionGemma 26B-A4B google/diffusiongemma-26b-a4b-it		detectionchat	80K	$0.35	$0.05	$1.50
SAM 3.1 facebook/sam3.1		segmentation	—	$1/1K	—	—
LightOnOCR-3 4B lightonai/lightonocr-3-4b		ocrmarkdownlayout	16K	$0.20	$0.20	$0.50
PaddleOCR-VL 1.6 paddlepaddle/paddleocr-vl-1.6		ocrmarkdown	16K	$0.15	$0.15	$0.35
Florence-2 microsoft/florence-2-base-ft		ocrdetection	—	$0	—	—
DeepSeek-OCR-2 deepseek-ai/deepseek-ocr-2		ocrmarkdown	8K	$0.25	$0.25	$0.80
GLM-OCR zai-org/glm-ocr		ocrmarkdown	8K	$0.10	$0.02	$0.20
Gemini 3.5 Flash Lite google/gemini-3.5-flash-lite		detectionchat	1M	$0.30	$0.03	$2.50
Gemma 4 26B-A4B Instruct google/gemma-4-26b-a4b-it		detectionchat	80K	$0.10	$0.05	$0.30
dots.mocr rednote-hilab/dots.mocr		ocrmarkdownlayout	24K	$0.20	$0.03	$0.40
MiniMax M3 minimax/minimax-m3		detectionchat	1M	$0.30	$0.06	$1.20
Kimi K3 moonshotai/kimi-k3		detectionchat	256K	$3	$0.30	$15
Gemini 3.7 Flash google/gemini-3.7-flash		detectionchat	1M	$0.75	$0.075	$3.75
Gemini 4 Argon google/gemini-4-argon		detectionchat	1M	$2	$0.10	$10
Muse Spark 1.2 meta/muse-spark-1.2		detectionchat	1M	$1.25	$0.15	$4.25
Muse Glimmer 30B meta/muse-glimmer-30b		detectionchat	128K	$0.35	$0.04	$1.50
OCR Auto vlm-run/ocr:auto		ocrmarkdownlayout	—	—	—	—
Gemini Robotics-ER 2 (preview) google/gemini-robotics-er-2-preview		detectionchat	128K	$1	$0.10	$5
Parakeet TDT 0.6B v3 nvidia/parakeet-tdt-0.6b-v3		transcription	—	$16.67/1M s	—	—
Qwen3-VL Embedding 2B qwen/qwen3-vl-embedding-2b		embedding	8K	$0.02	$0.02	—
Gemini 4 Carbon google/gemini-4-carbon		detectionchat	1M	$2	$0.10	$10
EmbeddingGemma 2 google/embeddinggemma-2		embedding	8K	$0.01	$0.01	—
Nemotron 3.5 Parse nvidia/nemotron-3.5-parse		ocrmarkdownlayout	16K	$0.10	$0.02	$0.20
RF-DETR LargeComing soon roboflow/rf-detr-large	—	detection	—	—	—	—

30 models

Pricing calculator

Dirt-cheap Document OCR.

Pick a document type, page volume, and OCR model. See cost savings versus closed vision APIs.

Document type

OCR model

Page volume / month

Gateway OCR tokens (in / out)

120M - 250M / 100M

Frontier billed tokens (in / out)

250M / 200M

2.5K image tokens per page; output includes reasoning at 2× OCR text.

Total cost

$45 - $110

Documents / month

100Kpages

Cost comparison (log scale)

Cheapest - most expensive

VLM Run Gateway

Document OCR VLMs

$45 - $110

OCR APIs

Textract, Azure Doc AI

$150 - $1K

Document AI APIs

Reducto, LlamaParse, Extend

$1K - $6K

Frontier VLMs

Gemini, Claude, GPT

$938 - $7.3K

$10$100$1K$10K

Estimates vs typical OCR, Document AI, and frontier VLM pricing.

A vision-only gateway, built for builders.

LLM routers and gateways route to 100s of LLMs, yet only a handful of VLMs, and often no OCR or classical CV models. Visual AI deserves its own stack.

Multimodal, Multitask
One catalog spanning multi-modal inputs and multi-task outputs: OCR, detection, segmentation, pose, keypoints, and more.
Chat Completions Native
OCR, captioning, and multimodal chat run through the same OpenAI-compatible chat completions API you already use.
Orchestration Built-In
Send a 500-page PDF or a 2-hour video in a single call. The gateway chunks, batches, and reassembles for you. No pipelines to build.
Structured Outputs, Out of the Box
JSON-schema enforcement on every call. CV wrappers emit fixed schemas; VLMs honor response_format.
Open Models, No Lock-In
Every model is open-weight, served through the OpenAI-compatible API you already use. Swap models or providers freely, your client code never changes.
Agent-native vision, via MCP
Give any MCP client instant access to the full visual model catalog. Agents see, read, and reason over images out of the box.

Built for production visual AI.

Optimized for production workloads and cost-efficiency. Every model deployed gets its own performance tune-up.

Models Supported
29
p50 Latency
<100ms
Uptime SLA
99.9%
Type II · HIPAA · BAA
SOC 2

12345678910111213141516171819

from openai import OpenAI

client = OpenAI(base_url="https://gateway.vlm.run/openai/",
                api_key="<VLM_RUN_API_KEY>")

resp = client.chat.completions.create(
    model="rednote-hilab/dots.mocr",
    messages=[{"role": "user", "content": [
        {"type": "document_url", "document_url": {"url": "invoice.pdf"}},
    ]}],
    extra_body={"method": "markdown"},
)
print(resp.choices[0].message.content)

# <document page="1">
# ## Invoice #1042
# | Item      | Qty | Amount |
# | API seats |  12 | $1,200 |
# </document>

Vision-native Chat Completions.

Point the OpenAI SDK at the gateway and swap the model, or hand the same catalog to an agent over MCP. Same signature, exhaustive visual model catalog.

Read the Docs Document OCR

Use cases

What you can build with the Gateway.

Compose vision models like building blocks. One SDK. One key. One bill.

Document ingestion pipelines

Layout, OCR, and markdown extraction across contracts, statements, and forms, at sub-cent per-page economics.

Multi-modal chatbots and agents

Build powerful multi-modal chatbots and agents with VLMs that pack native support for multi-modal inputs such as images, PDFs, or videos in a single chat completion.

Media and asset tagging

Auto-caption, tag, and index large image and video libraries for search, dedup, and recommendations.

Private and regulated deployments

Stand up the whole visual stack inside your own VPC or on-prem, with SSO, RBAC, and audit log export. Regulated data stays inside your boundary, under a BAA, on dedicated capacity you control.

Get an API key. Ship vision today.

Get an API Key Read the Docs

One unified API, Any Visual Model.

29 visual models. One endpoint.

Dirt-cheap Document OCR.

Cost comparison (log scale)

Cost comparison (log scale)

A vision-only gateway, built for builders.

Multimodal, Multitask

Chat Completions Native

Orchestration Built-In

Structured Outputs, Out of the Box

Open Models, No Lock-In

Agent-native vision, via MCP

Built for production visual AI.

Vision-native Chat Completions.

What you can build with the Gateway.

Document ingestion pipelines

Multi-modal chatbots and agents

Media and asset tagging

Private and regulated deployments

Get an API key. Ship vision today.