LLaVA 1.6 Vicuna 7B on Replicate API

Name: LLaVA 1.6 Vicuna 7B on Replicate API
Brand: Haotian Liu
SKU: llava-1.6-vicuna-7b-replicate
Price: 0.05 USD

LLaVA 1.6 · Haotian Liu

ServerlessOpen Source

Last refreshed 2026-05-19. Next refresh: weekly.

Why use LLaVA 1.6 Vicuna 7B on Replicate API?

Replicate API offers LLaVA 1.6 Vicuna 7B with pay-as-you-go pricing at $0.05/1M input tokens. Replicate is a cloud-based platform that enables users to run machine learning models easily and efficiently.

Input / 1M

$0.050

Output / 1M

$0.25

Cache

Not sourced

Batch

Not sourced

Setup recipe

Python + curl

Install

pip install replicate

Auth

export REPLICATE_API_TOKEN=...

Call

import replicate
output = replicate.run(
    "llava-1.6-vicuna-7b",
    input={"prompt": "Hello"}

Model ID

llava-1.6-vicuna-7b

Request example

import replicate

# reads REPLICATE_API_TOKEN from env
# llava-1.6-vicuna-7b format: "owner/model-name" (latest version) or "owner/model-name:version-hash"
output = replicate.run(
    "llava-1.6-vicuna-7b",
    input={"prompt": "Hello"}
)
# Output is a list or generator depending on the model
print("".join(output))

Gotchas

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.
The examples expect REPLICATE_API_TOKEN; rename it only if your application config maps the new variable.

Pricing

Type	Price (per 1M)
Input tokens	$0.05
Output tokens	$0.25

Capabilities

No model capability flags are currently sourced.

About LLaVA 1.6 Vicuna 7B

LLaVA 1.6 Vicuna 7B is a sophisticated multimodal large language model that integrates a Vicuna-7B language model with a high-performing vision encoder, such as CLIP's ViT-L/14. This innovative combination enables it to process and understand both text and image inputs, making it ideal for tasks like image captioning, visual question answering, and multimodal chatbot interactions. It features enhanced image resolution capabilities, improved OCR, and logical reasoning skills, all while maintaining data efficiency. Despite these advancements, users should be aware of its performance variability and computational demands when handling high-resolution images. Being open-source, it invites community collaboration for further enhancements.