Anthropic logo

Claude Opus 5 (Fast) API

anthropic/claude-opus-5-fast

Call Claude Opus 5 (Fast) through UberLLM’s OpenAI-compatible API — from $4.27/M input and $21.34/M output, routed automatically to the cheapest healthy seller. Anthropic · 1,000,000 token context. Fee included.

Try it live — no signup
Demo · a few prompts a day, no sign-up

Claude Opus 5 (Fast) pricing

Price now · per 1M tokens
Input
$4.2686
Output
$21.343
Cached input
$0.4269
% off list
61% off
List price · per 1M tokens
Input
$11.00
Output
$55.00
Cached input
$1.10
Providers and their list prices, per 1M tokens
ProviderInputOutputCached input
Venice AI$10.00$50.00$1.00
OpenRouter$10.00$50.00$1.00

UberLLM routes every request to the cheapest healthy seller for this model. The price shown includes UberLLM’s 10% fee.

How to use Claude Opus 5 (Fast) with the OpenAI SDK

Already using the OpenAI SDK? Change one line — the base URL — and call Claude Opus 5 (Fast) with your existing code. Anthropic SDKs work against https://api.uberllm.dev/v1/messages.

python
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="anthropic/claude-opus-5-fast",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)

Claude Opus 5 (Fast) API — FAQ

How much does the Claude Opus 5 (Fast) API cost?

Claude Opus 5 (Fast) is listed from $4.27 per million input tokens and $21.34 per million output tokens through UberLLM, which routes each request to the cheapest healthy seller on a live marketplace and bills the price shown, which includes UberLLM's 10% fee.

How do I call Claude Opus 5 (Fast) via API?

Use any OpenAI-compatible SDK: set the base URL to https://api.uberllm.dev/v1, your UberLLM API key, and model "anthropic/claude-opus-5-fast". Anthropic SDKs work via https://api.uberllm.dev/v1/messages.

Is Claude Opus 5 (Fast) OpenAI-compatible on UberLLM?

Yes. Every model on UberLLM — including Claude Opus 5 (Fast) — is served through one OpenAI-compatible endpoint, so you change only the base URL and key.

More Anthropic models