Skip to main content
Glama

Analyse / caption an image with a vision model

replicate_vision

Analyze an image with a vision-language model. Describe, caption, or ask questions about the image content.

Instructions

Run a vision-language model to describe, caption, or answer questions about an image.

Args:

  • image (string URL): URL of the image to analyse.

  • prompt (string, optional): Question or instruction (e.g. "describe this image", "count the people"). Default is a generic caption.

  • model (string, default "llava-13b"): Curated key (llava-13b, llava-v1.6-34b, blip-2, qwen-vl) or "owner/name".

  • max_tokens (1-4096, optional): Response length.

  • extra_input (object, optional): Model-specific extras.

Returns: PredictionResult with text_output containing the model's textual answer.

Examples:

  • image="https://example.com/photo.jpg", prompt="What objects are visible?"

  • image="", prompt="Read the values off this chart and list them.", model="llava-v1.6-34b"

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
imageYesURL of the image to analyse / caption.
modelNoVision model. Curated: llava-13b, llava-v1.6-34b, blip-2, qwen-vl. Or "owner/name".llava-13b
promptNoOptional question or instruction (e.g. 'describe this image', 'count the people'). Default is a generic caption.
downloadNo
max_tokensNo
timeout_msNoMax ms to wait for the prediction. If exceeded, returns the prediction ID so you can poll via replicate_get_prediction. Default: 300000 (5min).
extra_inputNo
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations indicate readOnlyHint=false (mutation) and openWorldHint=true (non-standard output). The description adds context: it returns PredictionResult with text_output, explains timeout behavior (default 5 min, polling via replicate_get_prediction), and mentions model-specific extras. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with purpose and uses a clear Args/Returns/Examples structure. Every sentence adds value. Minor wasted space: could combine the two bullet sentences under Args. Overall efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers core functionality, return type, examples, and key parameters. It lacks mention of error handling, auth requirements, or cost information. However, for a 7-param tool with no output schema, it is reasonably complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Despite 57% schema coverage, the description adds significant meaning beyond the schema. It clarifies the model field (curated keys vs 'owner/name'), gives examples, explains the prompt default, specifies max_tokens range, and details timeout with polling fallback. This greatly aids correct invocation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Run a vision-language model to describe, caption, or answer questions about an image.' The title reinforces 'Analyse / caption an image with a vision model.' This distinguishes it from sibling tools like replicate_generate_image (generation) and replicate_remove_background (editing), making the specific verb+resource obvious.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context, including optional prompt, default model, and examples for usage. It implies the tool is for understanding images, not generating them. However, it does not explicitly state when not to use it (e.g., for image editing or audio tasks) or compare with alternatives like replicate_chat for text-only queries.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/sena-labs/replicate-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server