OpenRouter Vision API Docs | fal

Run any Vision Language Model with fal. Analyze and understand images using Claude (Anthropic), GPT-5 / GPT-4o (OpenAI), Gemini (Google), Grok (xAI), Llama (Meta), Qwen, Pixtral (Mistral), and more. Send one or multiple images for captioning, analysis, OCR, or visual Q&A. Powered by OpenRouter.

openrouter/router/vision

Inference

Commercial use

Streaming

Partner

Schema

LLMs

Playground API Examples

1. Calling the API

2. Authentication

API Key

3. Queue

4. Files

5. Schema

About

Run any VLM (Vision Language Model) with fal, powered by OpenRouter.

1. Calling the API#

Install the client#

The client provides a convenient way to interact with the model API.

npm install --save @fal-ai/client

Migrate to @fal-ai/client

The @fal-ai/serverless-client package has been deprecated in favor of @fal-ai/client. Install the new package and update your imports — see client setup.

Setup your API Key#

Set FAL_KEY as an environment variable in your runtime.

export FAL_KEY="YOUR_API_KEY"

Submit a request#

The client API handles the API submit protocol. It will handle the request status updates and return the result when the request is completed.

import { fal } from "@fal-ai/client";

const result = await fal.subscribe("openrouter/router/vision", {
  input: {
    prompt: "Caption this image for a text-to-image model with as much detail as possible.",
    model: "openai/gpt-6-sol"
  },
  logs: true,
  onQueueUpdate: (update) => {
    if (update.status === "IN_PROGRESS") {
      update.logs.map((log) => log.message).forEach(console.log);
    }
  },
});
console.log(result.data);
console.log(result.requestId);

Streaming#

This model supports streaming requests. You can stream data directly to the model and get the result in real-time.

import { fal } from "@fal-ai/client";

const stream = await fal.stream("openrouter/router/vision", {
  input: {
    prompt: "Caption this image for a text-to-image model with as much detail as possible.",
    model: "openai/gpt-6-sol"
  }
});

for await (const event of stream) {
  console.log(event);
}

const result = await stream.done();

2. Authentication#

The API uses an API Key for authentication. It is recommended you set the FAL_KEY environment variable in your runtime when possible.

API Key#

In an environment where you cannot set environment variables, you can configure the API key manually on the client.

import { fal } from "@fal-ai/client";

fal.config({
  credentials: "YOUR_FAL_KEY"
});

Protect your API Key

When running code on the client-side (e.g. in a browser, mobile app or GUI applications), make sure to not expose your FAL_KEY. Instead, use a server-side proxy to make requests to the API. For more information, check out our server-side integration guide.

3. Queue#

Long-running requests

For long-running requests, such as training jobs or models with slower inference times, it is recommended to check the Queue status and rely on Webhooks instead of blocking while waiting for the result.

Submit a request#

The client API provides a convenient way to submit requests to the model.

import { fal } from "@fal-ai/client";

const { request_id } = await fal.queue.submit("openrouter/router/vision", {
  input: {
    prompt: "Caption this image for a text-to-image model with as much detail as possible.",
    model: "openai/gpt-6-sol"
  },
  webhookUrl: "https://optional.webhook.url/for/results",
});

Fetch request status#

You can fetch the status of a request to check if it is completed or still in progress.

import { fal } from "@fal-ai/client";

const status = await fal.queue.status("openrouter/router/vision", {
  requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b",
  logs: true,
});

Get the result#

Once the request is completed, you can fetch the result. See the Output Schema for the expected result format.

import { fal } from "@fal-ai/client";

const result = await fal.queue.result("openrouter/router/vision", {
  requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b"
});
console.log(result.data);
console.log(result.requestId);

4. Files#

Some attributes in the API accept file URLs as input. Whenever that's the case you can pass your own URL or a Base64 data URI.

Data URI (base64)#

You can pass a Base64 data URI as a file input. The API will handle the file decoding for you. Keep in mind that for large files, this alternative although convenient can impact the request performance.

Hosted files (URL)#

You can also pass your own URLs as long as they are publicly accessible. Be aware that some hosts might block cross-site requests, rate-limit, or consider the request as a bot.

Uploading files#

We provide a convenient file storage that allows you to upload files and use them in your requests. You can upload files using the client API and use the returned URL in your requests.

import { fal } from "@fal-ai/client";

const file = new File(["Hello, World!"], "hello.txt", { type: "text/plain" });
const url = await fal.storage.upload(file);

Auto uploads

The client will auto-upload the file for you if you pass a binary object (e.g. File, Data).

Read more about file handling in our file upload guide.

5. Schema#

Input#

image_urls list<string>

List of image URLs to be processed.

pdf_urls list<string>

List of PDF document URLs to be processed. Only PDF files are accepted: http(s) URLs must point to a .pdf file and data URIs must be data:application/pdf;base64,... Models without native PDF support fall back to OpenRouter's document parsing.

prompt string* required

Prompt to be used for the image

system_prompt string

System prompt to provide context or instructions to the model

model string* required

Name of the model to use. Charged based on actual token usage.

reasoning boolean

Should reasoning be the part of the final answer.

temperature float

This setting influences the variety in the model's responses. Lower values lead to more predictable and typical responses, while higher values encourage more diverse and less common responses. At 0, the model always gives the same response for a given input. Default value: 1

max_tokens integer

This sets the upper limit for the number of tokens the model can generate in response. It won't produce more than this limit. The maximum value is the context length minus the prompt length.

enable_web_search boolean

Give the model access to real-time web information via OpenRouter's web search server tool. When enabled, the model decides when to search and may search multiple times per request. Search costs are charged in addition to token usage.

web_search_options WebSearchOptions

Options for web search (engine, result limits, domain filters, ...). Ignored unless enable_web_search is true.

{
  "image_urls": [
    "https://fal.media/files/tiger/4Ew1xYW6oZCs6STQVC7V8_86440216d0fe42e4b826d03a2121468e.jpg"
  ],
  "pdf_urls": [
    "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf"
  ],
  "prompt": "Caption this image for a text-to-image model with as much detail as possible.",
  "system_prompt": "Only answer the question, do not provide any additional information or add any prefix/suffix other than the answer of the original question. Don't use markdown.",
  "model": "openai/gpt-6-sol",
  "temperature": 1
}

Output#

output string* required

Generated output

usage UsageInfo* required

Token usage information

{
  "output": "A close-up of a tiger's face focusing on its bright orange iris and the area around its eye, with white fur eyebrows and a contrasting black and rich orange striped fur pattern. The word \"FLUX\" is overlaid in bold, white, brush-stroke styled text across the tiger's face.",
  "usage": {
    "total_tokens": 1403,
    "cost": 0.0005595,
    "completion_tokens": 63,
    "prompt_tokens": 1340
  }
}

Other types#

WebSearchOptions#

engine EngineEnum

Search engine to use. 'auto' uses native provider search when available and falls back to Exa. 'native' prefers the provider's built-in web search (OpenAI, Anthropic, Google, xAI, Perplexity), falling back to Exa for models without native support. 'exa' always uses Exa's search API. Default value: "auto"

Possible enum values: auto, native, exa

max_results integer

Maximum results per search call (1-25). Applies to the Exa engine; ignored with native provider search. Defaults to 5.

max_uses integer

Maximum number of searches the model may perform in a single request. Once reached, further search calls return an error result instead of executing. With native provider search, forwarded only to Anthropic; other native providers ignore it.

max_total_results integer

Maximum total results across all search calls in a single request. Useful for controlling cost and context size in agentic loops.

search_context_size Enum

How much content to retrieve per result. For Exa: low=5K, medium=15K, high=30K characters per result; when omitted, Exa picks adaptively (~2-4K per result). Ignored with native provider search. Overridden by max_characters when both are set.

Possible enum values: low, medium, high

max_characters integer

Exact maximum characters of content per result (1-100,000). Applies to the Exa engine; ignored with native provider search. Takes precedence over search_context_size when both are set.

allowed_domains list<string>

Limit results to these domains. Supported by Exa and most native providers (not Google native search).

excluded_domains list<string>

Exclude results from these domains. Supported by Exa and some native providers (not OpenAI or Google native search).

user_location WebSearchUserLocation

Approximate user location for location-biased results. Only supported by native provider search; ignored by Exa.

UsageInfo#

prompt_tokens integer

completion_tokens integer

total_tokens integer

cost float* required

prompt_tokens_details PromptTokensDetails

WebSearchUserLocation#

type string

Location type. Only 'approximate' is supported. Default value: "approximate"

city string

City name, e.g. 'San Francisco'.

region string

Region or state, e.g. 'California'.

country string

Two-letter country code, e.g. 'US'.

timezone string

IANA timezone, e.g. 'America/Los_Angeles'.

PromptTokensDetails#

cached_tokens integer

cache_write_tokens integer

Related Models

1. Calling the API

2. Authentication

API Key

3. Queue

4. Files

5. Schema

About

Run any VLM (Vision Language Model) with fal, powered by OpenRouter.

1. Calling the API#

Install the client#

The client provides a convenient way to interact with the model API.

npm install --save @fal-ai/client

Migrate to @fal-ai/client

The @fal-ai/serverless-client package has been deprecated in favor of @fal-ai/client. Install the new package and update your imports — see client setup.

Setup your API Key#

Set FAL_KEY as an environment variable in your runtime.

export FAL_KEY="YOUR_API_KEY"

Submit a request#

The client API handles the API submit protocol. It will handle the request status updates and return the result when the request is completed.

import { fal } from "@fal-ai/client";

const result = await fal.subscribe("openrouter/router/vision", {
  input: {
    prompt: "Caption this image for a text-to-image model with as much detail as possible.",
    model: "openai/gpt-6-sol"
  },
  logs: true,
  onQueueUpdate: (update) => {
    if (update.status === "IN_PROGRESS") {
      update.logs.map((log) => log.message).forEach(console.log);
    }
  },
});
console.log(result.data);
console.log(result.requestId);

Streaming#

This model supports streaming requests. You can stream data directly to the model and get the result in real-time.

import { fal } from "@fal-ai/client";

const stream = await fal.stream("openrouter/router/vision", {
  input: {
    prompt: "Caption this image for a text-to-image model with as much detail as possible.",
    model: "openai/gpt-6-sol"
  }
});

for await (const event of stream) {
  console.log(event);
}

const result = await stream.done();

2. Authentication#

The API uses an API Key for authentication. It is recommended you set the FAL_KEY environment variable in your runtime when possible.

API Key#

In an environment where you cannot set environment variables, you can configure the API key manually on the client.

import { fal } from "@fal-ai/client";

fal.config({
  credentials: "YOUR_FAL_KEY"
});

Protect your API Key

3. Queue#

Long-running requests

Submit a request#

The client API provides a convenient way to submit requests to the model.

import { fal } from "@fal-ai/client";

const { request_id } = await fal.queue.submit("openrouter/router/vision", {
  input: {
    prompt: "Caption this image for a text-to-image model with as much detail as possible.",
    model: "openai/gpt-6-sol"
  },
  webhookUrl: "https://optional.webhook.url/for/results",
});

Fetch request status#

You can fetch the status of a request to check if it is completed or still in progress.

import { fal } from "@fal-ai/client";

const status = await fal.queue.status("openrouter/router/vision", {
  requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b",
  logs: true,
});

Get the result#

Once the request is completed, you can fetch the result. See the Output Schema for the expected result format.

import { fal } from "@fal-ai/client";

const result = await fal.queue.result("openrouter/router/vision", {
  requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b"
});
console.log(result.data);
console.log(result.requestId);

4. Files#

Some attributes in the API accept file URLs as input. Whenever that's the case you can pass your own URL or a Base64 data URI.

Data URI (base64)#

Hosted files (URL)#

You can also pass your own URLs as long as they are publicly accessible. Be aware that some hosts might block cross-site requests, rate-limit, or consider the request as a bot.

Uploading files#

We provide a convenient file storage that allows you to upload files and use them in your requests. You can upload files using the client API and use the returned URL in your requests.

import { fal } from "@fal-ai/client";

const file = new File(["Hello, World!"], "hello.txt", { type: "text/plain" });
const url = await fal.storage.upload(file);

Auto uploads

The client will auto-upload the file for you if you pass a binary object (e.g. File, Data).

Read more about file handling in our file upload guide.

5. Schema#

Input#

image_urls list<string>

List of image URLs to be processed.

pdf_urls list<string>

prompt string* required

Prompt to be used for the image

system_prompt string

System prompt to provide context or instructions to the model

model string* required

Name of the model to use. Charged based on actual token usage.

reasoning boolean

Should reasoning be the part of the final answer.

temperature float

max_tokens integer

This sets the upper limit for the number of tokens the model can generate in response. It won't produce more than this limit. The maximum value is the context length minus the prompt length.

enable_web_search boolean

web_search_options WebSearchOptions

Options for web search (engine, result limits, domain filters, ...). Ignored unless enable_web_search is true.

{
  "image_urls": [
    "https://fal.media/files/tiger/4Ew1xYW6oZCs6STQVC7V8_86440216d0fe42e4b826d03a2121468e.jpg"
  ],
  "pdf_urls": [
    "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf"
  ],
  "prompt": "Caption this image for a text-to-image model with as much detail as possible.",
  "system_prompt": "Only answer the question, do not provide any additional information or add any prefix/suffix other than the answer of the original question. Don't use markdown.",
  "model": "openai/gpt-6-sol",
  "temperature": 1
}

Output#

output string* required

Generated output

usage UsageInfo* required

Token usage information

{
  "output": "A close-up of a tiger's face focusing on its bright orange iris and the area around its eye, with white fur eyebrows and a contrasting black and rich orange striped fur pattern. The word \"FLUX\" is overlaid in bold, white, brush-stroke styled text across the tiger's face.",
  "usage": {
    "total_tokens": 1403,
    "cost": 0.0005595,
    "completion_tokens": 63,
    "prompt_tokens": 1340
  }
}

Other types#

WebSearchOptions#

engine EngineEnum

Possible enum values: auto, native, exa

max_results integer

Maximum results per search call (1-25). Applies to the Exa engine; ignored with native provider search. Defaults to 5.

max_uses integer

max_total_results integer

Maximum total results across all search calls in a single request. Useful for controlling cost and context size in agentic loops.

search_context_size Enum

Possible enum values: low, medium, high

max_characters integer

Exact maximum characters of content per result (1-100,000). Applies to the Exa engine; ignored with native provider search. Takes precedence over search_context_size when both are set.

allowed_domains list<string>

Limit results to these domains. Supported by Exa and most native providers (not Google native search).

excluded_domains list<string>

Exclude results from these domains. Supported by Exa and some native providers (not OpenAI or Google native search).

user_location WebSearchUserLocation

Approximate user location for location-biased results. Only supported by native provider search; ignored by Exa.

UsageInfo#

prompt_tokens integer

completion_tokens integer

total_tokens integer

cost float* required

prompt_tokens_details PromptTokensDetails

WebSearchUserLocation#

type string

Location type. Only 'approximate' is supported. Default value: "approximate"

city string

City name, e.g. 'San Francisco'.

region string

Region or state, e.g. 'California'.

country string

Two-letter country code, e.g. 'US'.

timezone string

IANA timezone, e.g. 'America/Los_Angeles'.

PromptTokensDetails#

cached_tokens integer

cache_write_tokens integer

openrouter/router/vision

Table of contents

Table of contents

openrouter/router/vision

Table of contents

1. Calling the API

2. Authentication

3. Queue

4. Files

5. Schema

About

1. Calling the API#

Install the client#

Migrate to @fal-ai/client

Setup your API Key#

Submit a request#

Streaming#

2. Authentication#

API Key#

Protect your API Key

3. Queue#

Long-running requests

Submit a request#

Fetch request status#

Get the result#

4. Files#

Data URI (base64)#

Hosted files (URL)#

Uploading files#

Auto uploads

5. Schema#

Input#

Output#

Other types#

WebSearchOptions#

UsageInfo#

WebSearchUserLocation#

PromptTokensDetails#

Related Models

Table of contents

Table of contents

1. Calling the API

2. Authentication

3. Queue

4. Files

5. Schema

About

1. Calling the API#

Install the client#

Migrate to @fal-ai/client

Setup your API Key#

Submit a request#

Streaming#

2. Authentication#

API Key#

Protect your API Key

3. Queue#

Long-running requests

Submit a request#

Fetch request status#

Get the result#

4. Files#

Data URI (base64)#

Hosted files (URL)#

Uploading files#

Auto uploads

5. Schema#

Input#

Output#

Other types#

WebSearchOptions#

UsageInfo#

WebSearchUserLocation#

PromptTokensDetails#

Related Models