GetVibe API gives you GPT-5.6, Claude Opus 4.8, Gemini and dozens of other models behind a single OpenAI-compatible endpoint. You keep your existing OpenAI client code and only change the base URL and the model name — the rest works as-is.
Base URL and authentication
Create a key in the dashboard, then point any OpenAI-compatible client at https://getvibeapi.com/v1:
# Set your key once
export GETVIBE_API_KEY="sk-pv-..."
# Chat completion
curl https://getvibeapi.com/v1/chat/completions \
-H "Authorization: Bearer $GETVIBE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-6.1-sol",
"messages": [{"role": "user", "content": "Explain API gateways in one paragraph"}]
}'Use your existing OpenAI SDK
Swap the base URL and you are done. No new dependencies, no provider-specific wrappers.
from openai import OpenAI
client = OpenAI(
base_url="https://getvibeapi.com/v1",
api_key="sk-pv-...",
)
resp = client.chat.completions.create(
model="gpt-6.1-sol",
messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://getvibeapi.com/v1",
apiKey: "sk-pv-...",
});
const resp = await client.chat.completions.create({
model: "claude-opus-4.8",
messages: [{ role: "user", content: "Hello!" }],
});Which model should you pick?
- GPT-5.6 Luna — the balanced default for coding, agents and everyday tasks.
- Claude Opus 4.8 — strongest long-context reasoning and writing.
- Gemini 3.1 Pro — reasoning with multimodal input, including video.
- DeepSeek V4 Pro — a high-quality, low-cost option for high-volume work.
Pricing
You pay per 1M tokens of input and output, in USD. Check live per-model pricing on the Models page. Top up your balance with a card or crypto, then spend as you go — no monthly commitment.
Next steps
Read the documentation for streaming, embeddings, vision and the full model catalog, or open the dashboard and create your first key.