Claude Opus 4.6 API pricing and code examples
Claude Opus 4.6 is an Anthropic model you can call through LivRouter's OpenAI-compatible endpoint. There is no separate Anthropic account and no separate invoice: one LivRouter API key reaches Claude Opus 4.6 alongside every other model on the platform, billed per token from prepaid credits.
Claude Opus 4.6 API at a glance
Compare Claude Opus 4.6 API pricing, model ID, and OpenAI-compatible examples through LivRouter.
- Model ID
- claude-opus-4-6
- Provider
- Anthropic
- API format
- OpenAI-compatible
- Billing
- Per token from LivRouter credits
- Common integration focus
- Coding, analysis, and assistant integrations
Claude Opus 4.6 pricing
Rates are in USD per 1M tokens. The reference row is the provider base rate recorded in LivRouter's catalog; the plan rows show the published rates for each eligible plan.
| Plan | Input / 1M | Output / 1M | Cached input / 1M |
|---|---|---|---|
| Reference (Anthropic) | $5.00 | $25.00 | $0.50 |
| Max Claude Kiro−93% | $0.35 | $1.75 | $0.035 |
| Max ClaudeMax−70% | $1.50 | $7.50 | $0.15 |
| Pro Claude Kiro−85% | $0.75 | $3.75 | $0.075 |
| Pro ClaudeMax−62% | $1.90 | $9.50 | $0.19 |
Lowest listed LivRouter rate for Claude Opus 4.6: $0.35 per 1M input tokens on the Max Claude Kiro plan — about 93% below the Anthropic reference rate. See every plan and rate.
Source: LivRouter model catalog. Catalog checked .
What does a Claude Opus 4.6 request cost?
One million uncached input tokens plus 100,000 output tokens at the listed Max Claude Kiro rates cost $0.525. This example excludes subscription fees and assumes the selected plan is active. Actual charges depend on input, output, and cached-token usage.
Compare plan fees and credit allowancesCall Claude Opus 4.6 with the OpenAI SDK
Claude Opus 4.6 follows the OpenAI chat completions format, so existing OpenAI client code keeps working — change the base URL and the model name. The same key also works for the Anthropic SDK and CLI agents such as Claude Code.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.livrouter.com/v1",
apiKey: process.env.LIVROUTER_API_KEY,
});
const completion = await client.chat.completions.create({
model: "claude-opus-4-6",
messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);Prefer plain HTTP? The same request over curl:
curl https://api.livrouter.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $LIVROUTER_API_KEY" \
-d '{
"model": "claude-opus-4-6",
"messages": [{"role": "user", "content": "Hello"}]
}'Frequently asked questions about Claude Opus 4.6
How much does claude-opus-4-6 cost through LivRouter?
claude-opus-4-6 is metered per token. The Anthropic reference rate is $5.00 per 1M input tokens and $25.00 per 1M output tokens. On the Max Claude Kiro plan LivRouter charges $0.35 per 1M input tokens, about 93% below the Anthropic reference rate. Cached input is $0.035 per 1M tokens.
Can I call claude-opus-4-6 with the OpenAI SDK?
Yes. claude-opus-4-6 is reachable through the OpenAI-compatible endpoint at https://api.livrouter.com/v1. Keep your existing OpenAI client code and change the base URL and the model name to "claude-opus-4-6".
Do I need a separate Anthropic account?
No. LivRouter routes the request for you. You only need a LivRouter API key and credits — no separate Anthropic subscription.
Is claude-opus-4-6 available on the Start tier?
claude-opus-4-6 is not part of the Start tier group. It is available on the paid plans listed above.
Other Anthropic models on LivRouter
- Claude Fable 5$0.35/1M in
- Claude Fable 5 1$0.35/1M in
- Claude Fable 5 2$0.56/1M in
- Claude Haiku 4 5$0.07/1M in
- Claude Haiku 5 5$0.007/1M in
- Claude Opus 4 7$0.35/1M in
- Claude Opus 4 8$0.35/1M in
- Claude Opus 5$0.35/1M in
- Claude Opus 5 5$0.28/1M in
- Claude Sonnet 4 5$0.21/1M in
- Claude Sonnet 4 6$0.21/1M in
- Claude Sonnet 5$0.14/1M in
- Claude Sonnet 5 5$0.14/1M in