Using LLaVA 13B on Replicate API

Implementation guide · LLaVA · Haotian Liu

ServerlessOpen Weights

Replicate API exposes LLaVA 13B through model ID yorickvp/llava-13b. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-09-30. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at Replicate API and generate an API key.
  2. 2
    Use the Replicate API SDK or REST API to call yorickvp/llava-13b — see the documentation for request format.
API PortalDocumentationPricingModel Card

Code Examples

Install
pip install replicate
API key
REPLICATE_API_TOKEN
Model ID
yorickvp/llava-13b

Replicate uses "owner/model-name" format (e.g. "meta/meta-llama-3-8b-instruct") for the latest version, or "owner/model-name:version-sha" to pin to a specific version. The REST endpoint splits owner and model-name into the path: /v1/models/{owner}/{model-name}/predictions.

import replicate

# reads REPLICATE_API_TOKEN from env
# yorickvp/llava-13b format: "owner/model-name" (latest version) or "owner/model-name:version-hash"
output = replicate.run(
    "yorickvp/llava-13b",
    input={"prompt": "Hello"}
)
# Output is a list or generator depending on the model
print("".join(output))

Pricing on Replicate API

Capabilities

VisionMultimodal

About LLaVA 13B

Original LLaVA (Large Language-and-Vision Assistant) 13B model. Multimodal vision+language model combining a vision encoder with a language model for visual understanding tasks.

Full model details →

Model Specs

Released2023-04-17
Parameters13B
Context4k
ArchitectureDecoder Only

Provider

Replicate API

Replicate

San Francisco, California, United States