Anthropic
Claude Opus 5.5
Anthropic's latest Opus model for long-running coding agents and knowledge work, with always-on adaptive thinking
Context Length1M tokens; standard rates across the full window
Max Output128K tokens
MultimodalText and image input; text output
Pricing & Specs
๐ฐ Pricing
Input$4 / M tokens
Output$20 / M tokens
Cache Write$8 / M tokens
Cache Hit$0.20 / M tokens
โ๏ธ Specs
Context Length1M tokens; standard rates across the full window
Max Output128K tokens
MultimodalText and image input; text output
Adaptive ThinkingAlways on; omit thinking and control depth with output_config.effort (default: medium)
Tool CallingUse tool_choice=auto; forced any/tool choices are unsupported
Cache Write BillingThis service uses the 1h cache-write rate ($8 / MTok) for both 5m and 1h cache writes
Fast Mode2x token rates; upstream research preview
API CompatibilityClaude Messages API; Claude Code
Release DateSeptember 22, 2026
Knowledge CutoffJune 2026
API Examples
Python
import anthropic
client = anthropic.Anthropic(api_key="YOUR_API_KEY", base_url="https://api.xairouter.com")
message = client.messages.create(
model="claude-opus-5-5",
max_tokens=4096,
messages=[{"role": "user", "content": "Hello, Claude!"}],
)
for block in message.content:
if block.type == "text":
print(block.text)
cURL
curl https://api.xairouter.com/v1/messages \
-H "x-api-key: YOUR_API_KEY" \
-H "anthropic-version: 2023-06-01" \
-H "Content-Type: application/json" \
-d '{"model":"claude-opus-5-5","max_tokens":4096,"messages":[{"role":"user","content":"Hello, Claude!"}]}'
Developer Assist
export ANTHROPIC_AUTH_TOKEN=YOUR_API_KEY
export ANTHROPIC_BASE_URL=https://api.xairouter.com
claude --model claude-opus-5-5
Official references (verified September 23, 2026): Claude Opus 5.5 ยท Anthropic Pricing.