Listed rates are the highest rates across available channels. Your request is billed at the selected channel’s rate, locked when the request starts, and may cost less.
Claude Opus 5
Availableclaude-opus-5AnthropictextAnthropic’s current flagship for the most demanding reasoning and agentic workloads. 1M context, 128k output.
Input / Output per 1M tokens
$5.00 / $25.00
Context window
1M
Provider routes
2
Capabilities
StreamingToolsVision
Provider routing
Balances price, recent reliability, latency, and output speed. If the preferred provider fails, 202AI automatically tries the next eligible route.
ProviderInput / MTokOutput / MTokLatencyThroughputUptime
Anthropic PreferredDirect route
claude-opus-5Input / MTok
$5.00Output / MTok
$25.00Latency
—Throughput
—Uptime
—Amazon Bedrock
bedrock-claude-opus-5Input / MTok
$5.00Output / MTok
$25.00Latency
—Throughput
—Uptime
—Performance uses active endpoint data and successful requests from the last 14 days. Routes without enough observations remain eligible as fallbacks.
API example
OpenAI-compatible, with automatic provider fallback.
chat.ts
import OpenAI from 'openai';
const client = new OpenAI({
baseURL: 'https://router.202ai.xyz/v1',
apiKey: process.env.MACAW_API_KEY!,
});
const res = await client.chat.completions.create({
model: 'claude-opus-5:balanced',
messages: [
{ role: 'user', content: 'Write me a haiku about gateways.' },
],
});
console.log(res.choices[0].message.content);