claude-opus-4-6 API

Claude Opus 4.6 is the 4.6-generation Opus model from Anthropic, built for work where answer quality matters more than raw speed: multi-step reasoning, agentic coding across large repositories, and tool-driven workflows that run for many turns. It pairs the full 1,000,000-token context window with a 128,000-token output ceiling, so a single request can hold an entire codebase, a stack of contracts, or months of conversation history and still return a long, structured answer. Its model ID is a dateless pinned snapshot — claude-opus-4-6 always resolves to the same weights, which makes it a safe choice for production pipelines that must not drift. On CaMeL Hub the model bills strictly per token: $5 per 1M input tokens and $25 per 1M output tokens, the same headline rate as the newer Opus 4.7 and 4.8. Two documented details make it economical in practice. First, Anthropic's pricing page states the 1M-token window carries no long-context price tier — a 900K-token prompt is billed at the same per-token rate as a 9K one. Second, Opus 4.6 keeps the pre-4.7 tokenizer; Anthropic notes the tokenizer introduced with Opus 4.7 produces roughly 30% more tokens for the same text, so identical documents generally tokenize more compactly on Opus 4.6. Latency sits in the moderate band — slower than Sonnet- or Haiku-class models — which suits quality-first agent and batch workloads rather than latency-critical chat. CaMeL Hub exposes Opus 4.6 in two endpoint flavors: the OpenAI-compatible /v1/chat/completions route, where any OpenAI SDK works after switching base_url to https://api.camel-hub.com/v1, and an Anthropic-native Messages route for code already written against that API. Streaming, function calling, and image input are all supported. Accounts can be funded by one-off top-ups or subscription plans, with Alipay, WeChat Pay, and international cards accepted — and one API key covers this model alongside every other model on the platform, so A/B-testing it against GPT or Gemini needs no code changes beyond the model name.

curl https://api.camel-hub.com/v1/chat/completions \
  -H "Authorization: Bearer $CAMEL_HUB_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-opus-4-6",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from openai import OpenAI

client = OpenAI(
    api_key="$CAMEL_HUB_KEY",
    base_url="https://api.camel-hub.com/v1",  # <-- the only change vs. the OpenAI default
)

resp = client.chat.completions.create(
    model="claude-opus-4-6",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.CAMEL_HUB_KEY,
  baseURL: "https://api.camel-hub.com/v1", // <-- the only change vs. the OpenAI default
});

const resp = await client.chat.completions.create({
  model: "claude-opus-4-6",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(resp.choices[0].message.content);