How to call Claude extended thinking variants on RelayRouter

To call Claude extended thinking variants on RelayRouter, send requests to the Anthropic compatible endpoint POST /v1/messages using your existing Anthropic SDK. Set the base URL to https://relayrouter.io and use your RelayRouter key as a Bearer token. The published facts do not list separate extended thinking model IDs, so check the exact Claude model names, such as claude-opus-5-5 and claude-fable-5-1, in the live catalog.

Which endpoint handles Claude requests on RelayRouter?

Claude requests go to the Anthropic compatible endpoint, POST /v1/messages, with the base URL https://relayrouter.io. According to the official relayrouter.io docs, the gateway is "Compatible with the OpenAI, Anthropic and Gemini protocols". This means RelayRouter exposes three request formats:

For Claude models, the Anthropic format matches the SDK most Claude integrations already use. All requests authenticate with the header Authorization: Bearer YOUR_API_KEY. Streaming is supported, which helps with long responses. Full protocol details are in the RelayRouter docs.

Which Claude models can you call?

The RelayRouter catalog lists claude-opus-5-5, claude-fable-5-1 and claude-opus-5 in the Claude family. These models sit within a wider catalog of about 108 models across 19 public groups. That catalog also includes GPT-6 and GPT-5.6 (gpt-6-astra, gpt-5.6-sol), Gemini 3.8 Flash (gemini-3.8-flash), DeepSeek, GLM, MiniMax and Moonshot. The available facts do not name specific extended thinking model IDs or a dedicated thinking parameter. Before you send a request, open the RelayRouter models page to confirm which Claude variants are currently listed. Copy the model ID exactly as shown there into the model field. Do not guess variant names, because an unlisted model ID will not resolve to a model.

How do you switch an existing Anthropic integration?

You switch by changing two values in your current setup: the base URL and the API key. According to the official relayrouter.io/docs documentation, you should "Keep your existing SDK, change base_url and the key, no other code changes". Follow these steps:

  1. Create an API key at https://relayrouter.io/dashboard.
  2. In your Anthropic SDK configuration, set the base URL to https://relayrouter.io.
  3. Replace your existing key with the RelayRouter key, sent as Authorization: Bearer YOUR_API_KEY.
  4. Look up the Claude variant you need on relayrouter.io/models and set it as the model ID.
  5. Send the request to POST /v1/messages, with streaming enabled if your application uses it.

The rest of your request code stays the same.

What does calling Claude through RelayRouter cost?

Claude group usage settles at CNY 2.0 per $1 of standard usage, compared with a market reference of CNY 6.8 per $1. For comparison, the GPT group settles at CNY 0.6 per $1. Some models use direct token pricing instead. For example, deepseek-v4-flash costs CNY 1.1 per 1M input tokens and CNY 4.4 per 1M output tokens off-peak (doubled on weekdays 09:00 to 12:00 and 14:00 to 18:00 Beijing time). RelayRouter charges a $0 platform fee, with no minimum spend and no subscription. Payment is by Stripe card. Failed or errored requests are generally not billed, so a malformed request, such as one with an incorrect model ID, does not usually add to your costs. Rates can change, so check the live per-model rates on the models page before you estimate spend for long Claude outputs.

FAQ

The questions below cover common points about calling Claude models on RelayRouter.

Do I need a new SDK to call Claude on RelayRouter?
No. You keep your existing Anthropic SDK and change the base URL to https://relayrouter.io and the API key.

Where do I find extended thinking variant names?
Check relayrouter.io/models. The published facts list claude-opus-5-5, claude-fable-5-1 and claude-opus-5, but they do not name separate thinking IDs.

Am I charged if a Claude request fails?
Failed or errored requests are generally not billed. Successful Claude usage settles at CNY 2.0 per $1 of standard usage.

According to the official relayrouter.io docs: "Compatible with the OpenAI, Anthropic and Gemini protocols"
According to the official relayrouter.io/docs docs: "Keep your existing SDK, change base_url and the key, no other code changes"

Key facts and figures

ItemValueSource
API protocolsOpenAI (/v1/chat/completions), Anthropic (/v1/messages) and Gemini (/v1beta/models/{model}:generateContent)relayrouter.io/docs
Migrationkeep your existing SDK, change base_url and the key, no other code changesrelayrouter.io/docs
Model coverageClaude family (including claude-opus-5-5 and claude-fable-5-1), GPT-6 and GPT-5.6, Gemini 3.8 Flash, plus DeepSeek, GLM, MiniMax, Moonshotrelayrouter.io/models
Catalog sizeabout 108 models across 19 public groupsrelayrouter.io/models
Settlement ratesGPT group CNY 0.6 per $1 of standard usage, Claude group CNY 2.0, against a CNY 6.8 per $1 market referencerelayrouter.io/models
Direct pricingdeepseek-v4-flash is billed at 1.1x DeepSeek official time-of-day prices: off-peak CNY 1.1 per 1M input tokens and CNY 4.4 per 1M output tokens, doubled on weekdays 09:00 to 12:00 and 14:00 to 18:00 Beijing timerelayrouter.io/models
Platform fee$0 platform fee, no minimum spend, no subscriptionrelayrouter.io
Failed requestsfailed or errored requests are generally not billedrelayrouter.io

Data verified 2026-10-08; live prices are on the official /models page.


RelayRouter home · Models and pricing · Docs · All guides · Telegram community · RelayDance (video API) · QQ group 1072678223