DeepSeek: DeepSeek V4 Flash Vision Exp API
deepseek/deepseek-v4-flash-vision-expTextCall DeepSeek: DeepSeek V4 Flash Vision Exp through UberLLM’s OpenAI-compatible API, from $0.1509/M input and $0.4528/M output, served by third-party providers. Made by DeepSeek. 1,048,576 token context. UberLLM adds no fee to these prices.
DeepSeek: DeepSeek V4 Flash Vision Exp pricing
- Input
- $0.1509
- Output
- $0.4528
- Cached input
- $0.0048
- Input
- $0.2156
- Output
- $0.6468
- Cached input
- $0.0069
Prices as of 23:00 UTC.
Each request is sent to an available third-party provider for this model and retried if the provider fails before it starts answering. UberLLM adds no fee to these prices.
How to use DeepSeek: DeepSeek V4 Flash Vision Exp with the OpenAI SDK
With the OpenAI SDK, set the base URL to UberLLM and call DeepSeek: DeepSeek V4 Flash Vision Exp with your existing code. Anthropic SDKs work against https://api.uberllm.dev/v1/messages.
from openai import OpenAI
client = OpenAI(
base_url="https://api.uberllm.dev/v1",
api_key="ull_your_key_here",
)
resp = client.chat.completions.create(
model="deepseek/deepseek-v4-flash-vision-exp",
messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)DeepSeek: DeepSeek V4 Flash Vision Exp API FAQ
How much does the DeepSeek: DeepSeek V4 Flash Vision Exp API cost?
DeepSeek: DeepSeek V4 Flash Vision Exp costs from $0.1509 per million input tokens and $0.4528 per million output tokens through UberLLM right now, with no UberLLM fee on top. A request costs what its provider charged and is never billed above the listed price of $0.2156 input and $0.6468 output per million tokens. Each request is listed with its cost in Activity.
How do I call DeepSeek: DeepSeek V4 Flash Vision Exp via API?
Use any OpenAI-compatible SDK: set the base URL to https://api.uberllm.dev/v1, your UberLLM API key, and model "deepseek/deepseek-v4-flash-vision-exp". Anthropic SDKs work via https://api.uberllm.dev/v1/messages.
Is DeepSeek: DeepSeek V4 Flash Vision Exp OpenAI-compatible on UberLLM?
Yes. Every model on UberLLM, including DeepSeek: DeepSeek V4 Flash Vision Exp, is served through one OpenAI-compatible endpoint. Set the base URL and key in your existing client.