claude-opus-4-7 API
Claude Opus 4.7 is Anthropic's Opus-class model with a 1M-token context window and 128K max output. On CaMeL Hub you call it through an OpenAI-compatible API (base_url https://api.camel-hub.com/v1) at $5 per 1M input tokens and $25 per 1M output tokens — just swap the base URL in your existing SDK and use the model name claude-opus-4-7.
Pricing
| per 1M input tokens | per 1M output tokens | |
|---|---|---|
| CaMeL Hub | $5.00 | $25.00 |
| Provider list price | $5.00 | $25.00 |
Prices are the public default-group rate in USD per 1M tokens; input and output are billed separately. · Provider list price · verified 2026-07-11
Specifications
- Provider
- Anthropic
- Context window
- 1000000 tokens
- Max output
- 128000 tokens
- Capabilities
- streaming, vision, function-calling
- Endpoints
- anthropic, openai
What it is good for
- Repository-scale code review and refactoring: load hundreds of source files into the 1M-token window and ask for cross-file consistency fixes
- Long-document analysis of contracts, financial filings, or research corpora, with structured extraction into JSON via function calling
- Multi-step agentic pipelines that chain tool calls — planning, executing, and self-correcting over dozens of turns
- Vision workflows: turning screenshots, dashboards, scanned tables, and architecture diagrams into structured data or code
- Drafting and editing high-stakes technical or legal prose where reasoning depth matters more than latency
- Pinned-model production systems: teams that validated on this exact Opus snapshot and want reproducible outputs rather than chasing the latest release
Quickstart
OpenAI-compatible: set base_url to https://api.camel-hub.com/v1 and use your CaMeL Hub API key. No SDK changes needed.
cURL
curl https://api.camel-hub.com/v1/chat/completions \
-H "Authorization: Bearer $CAMEL_HUB_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "claude-opus-4-7",
"messages": [{"role": "user", "content": "Hello!"}]
}'Python
from openai import OpenAI
client = OpenAI(
api_key="$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-4-7",
messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)Node.js
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-4-7",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(resp.choices[0].message.content);Get an API key Browse integration guides
Frequently asked questions
How is Claude Opus 4.7 billed on CaMeL Hub?
Per token, with input and output metered separately: $5 per 1M input tokens and $25 per 1M output tokens. There is no per-request fee — a call that reads 20K tokens and writes 2K tokens costs 20,000 × $5/1M + 2,000 × $25/1M = $0.15. Usage is deducted from your prepaid balance or subscription quota and every request is itemized in the console logs.
Does claude-opus-4-7 support streaming, images, and function calling?
Yes to all three. Set stream: true for token-by-token streaming, pass images (screenshots, diagrams, photos) as input for vision tasks, and define tools/functions for structured tool calls. All of this works through both the OpenAI-compatible endpoint and the native Anthropic Messages endpoint on CaMeL Hub.
What are the context window and output limits?
Anthropic documents a 1M-token context window and a 128K-token maximum output for Claude Opus 4.7. Note that Opus 4.7 uses a newer tokenizer that yields roughly 30% more tokens for the same text than earlier Claude models, so measure long inputs against this model's own token counts when planning around the limit.
How do I start calling claude-opus-4-7?
Register at https://api.camel-hub.com/console, create an API key, then point any OpenAI SDK at base_url https://api.camel-hub.com/v1 with model set to claude-opus-4-7. No code changes beyond the base URL and key — the same key also works against the Anthropic-native Messages route if you prefer that format.
When should I pick Opus 4.7 over a Sonnet or Haiku model?
Pick Opus 4.7 when the task rewards maximum reasoning depth — large-codebase work, long-document synthesis, or agent loops that must recover from their own mistakes. For high-volume, latency-sensitive traffic like chat or classification, a Sonnet- or Haiku-class model on the same endpoint costs a fraction as much; you can A/B both by changing only the model string.