Overview
Qianfan VL V1 is a text model from Baidu's Qianfan family. It accepts text input and returns text output, so each request and each response is plain text.
On RealRelay the model is reached through a single OpenAI-compatible endpoint using the official model ID baidu/Qianfan-VL-V1. You send a request containing your text prompt and receive the generated text in the response.
Capabilities
Qianfan VL V1 takes text as input and returns text as output, which makes every call a text-to-text exchange.
You call it with the official model ID baidu/Qianfan-VL-V1 on RealRelay's OpenAI-compatible endpoint, keeping the same request format you use for other models there.
Pricing
Usage is metered at $3.00 per 1M input tokens and $15.00 per 1M output tokens.
Cached input reads are priced at $0.30 per 1M tokens.
Use Cases
Because the model works in text only, it fits tasks where a text prompt should produce a text answer.
Typical patterns include drafting and rewriting written content, summarizing text you supply, and answering questions about a text prompt.
What is Qianfan VL V1?
Qianfan VL V1 is a text model from Baidu's Qianfan family. It accepts text input and returns text output, and it is available on RealRelay under the model ID baidu/Qianfan-VL-V1.
How much does Qianfan VL V1 cost?
Input is $3.00 per 1M tokens and output is $15.00 per 1M tokens. Cached input reads are $0.30 per 1M tokens.
What input and output types does Qianfan VL V1 support?
Input is text and output is text. Each request carries a text prompt and each response returns generated text.
What does cached input cost for Qianfan VL V1?
Cached input reads are priced at $0.30 per 1M tokens, alongside $3.00 per 1M input tokens and $15.00 per 1M output tokens.
How do I call Qianfan VL V1 through the OpenAI-compatible API?
Send a request to RealRelay's OpenAI-compatible endpoint with the model ID baidu/Qianfan-VL-V1 and your text prompt as the input. The generated text comes back in the response.