Using LLaVA 1.6 Mistral 7B on Replicate API
Implementation guide · LLaVA 1.6 · Haotian Liu
Replicate API exposes LLaVA 1.6 Mistral 7B through model ID yorickvp/llava-v1.6-mistral-7b. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.
Last refreshed 2026-04-19. Next refresh: weekly.
Quick Start
- 1
- 2Use the Replicate API SDK or REST API to call
yorickvp/llava-v1.6-mistral-7b— see the documentation for request format. - 3
Code Examples
pip install replicateREPLICATE_API_TOKENyorickvp/llava-v1.6-mistral-7bReplicate 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-v1.6-mistral-7b format: "owner/model-name" (latest version) or "owner/model-name:version-hash"
output = replicate.run(
"yorickvp/llava-v1.6-mistral-7b",
input={"prompt": "Hello"}
)
# Output is a list or generator depending on the model
print("".join(output))Pricing on Replicate API
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.05 |
| Output tokens | $0.25 |
Capabilities
No model capability flags are currently sourced.
About LLaVA 1.6 Mistral 7B
LLaVA-v1.6 Mistral-7B is an open-source, multimodal language model capable of processing text and images. Built on the Mistral-7B-Instruct-v0.2 base, it combines a large language model with a vision encoder to enhance reasoning, optical character recognition, and world understanding. Trained on substantial datasets, including image-text pairs from LAION/CC/SBU, GPT-generated data, and VQA data, it was evaluated against 12 benchmarks. The model improves upon LLaVA-1.5 with higher image resolution processing and better reasoning, offering bilingual support and commercial licensing. It finds use in applications like chatbots, image captioning, and visual QA tasks but requires significant computational resources for high-res images.