Cosmos Predict (image-to-video) API
surplus/cosmos-predict-image-to-video
Call Cosmos Predict (image-to-video) through UberLLM’s OpenAI-compatible API — from $0.0000/M input and $0.0000/M output, routed automatically to the cheapest healthy provider. NVIDIA · 8,192 token context. No inference markup.
Cosmos Predict (image-to-video) pricing & providers
| Provider | Input / 1M | Output / 1M |
|---|---|---|
| Surplus Intelligencebest | $0.0000 | $0.0000 |
How to use Cosmos Predict (image-to-video) with the OpenAI SDK
Already using OpenAI or OpenRouter? Change one line — the base URL — and call Cosmos Predict (image-to-video) 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="surplus/cosmos-predict-image-to-video",
messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)Cosmos Predict (image-to-video) API — FAQ
How much does the Cosmos Predict (image-to-video) API cost?
Cosmos Predict (image-to-video) costs from $0.0000 per million input tokens and $0.0000 per million output tokens through UberLLM, which routes to the cheapest healthy provider. There is no inference markup.
How do I call Cosmos Predict (image-to-video) via API?
Use any OpenAI-compatible SDK: set the base URL to https://api.uberllm.dev/v1, your UberLLM API key, and model "surplus/cosmos-predict-image-to-video". Anthropic SDKs work via https://api.uberllm.dev/v1/messages.
Is Cosmos Predict (image-to-video) OpenAI-compatible on UberLLM?
Yes. Every model on UberLLM — including Cosmos Predict (image-to-video) — is served through one OpenAI-compatible endpoint, so you change only the base URL and key.