claude-opus-4-8 API

Claude Opus 4.8 is the Opus-class workhorse Anthropic recommends as the starting point for complex agentic coding and enterprise workloads. It uses adaptive thinking — the model decides how much reasoning depth each request needs, with the effort parameter defaulting to high — which makes it dependable in long tool-use loops: multi-file refactors, iterative test-and-fix cycles, and agent runs that span dozens of sequential steps without losing the plot. Latency is moderate: slower than Sonnet-class models, but substantially cheaper and faster than Anthropic's top-tier Fable 5 while covering most of the same territory. The specs are built for large jobs. The context window is 1M tokens with up to 128K output tokens per request, and Anthropic documents no long-context surcharge — a 900K-token prompt bills at the same per-token rate as a 9K one. It also accepts image input, so screenshots, charts, and scanned documents can flow through the same pipeline as text. One migration note worth budgeting for: Opus 4.7 and later use a newer tokenizer that produces roughly 30% more tokens for the same text than pre-4.7 models, so token counts (and therefore costs) will read higher than a like-for-like run on older Claude versions. On CaMeL Hub, claude-opus-4-8 is billed per token at $5 per 1M input and $25 per 1M output in the public default group, with streaming, function calling, and vision all enabled. The same API key works against both the OpenAI-compatible endpoint (point any OpenAI SDK at https://api.camel-hub.com/v1) and the Anthropic-native format, so tools like Claude Code connect without code changes. One account also covers GPT, Gemini, DeepSeek, and hundreds of other models behind the same base URL, and you can pay by Alipay, WeChat Pay, or international cards — with both top-up and subscription options.

curl https://api.camel-hub.com/v1/chat/completions \
  -H "Authorization: Bearer $CAMEL_HUB_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-opus-4-8",
    "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-4-8",
    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-4-8",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(resp.choices[0].message.content);