Claude Sonnet 5 API

Put Claude Sonnet 5 behind the same control plane as your stack

Use Claude Sonnet 5 for coding, analysis and instruction-heavy workflows while keeping credentials, quotas, logs and routing in the same gateway as GPT, Gemini and other model families.

Create an account AI model pricing

ProviderAnthropic-compatible

Model IDclaude-sonnet-5

BillingToken-based input, output and prompt-cache billing by selected group

Endpoints/v1/messages, /v1/chat/completions

Recharge value

Recharge $15. Get $100-equivalent official API usage.

A $15 recharge adds gateway usage value benchmarked to $100 at official API list prices.

Recharge$15

Official API list-price equivalent$100

Equivalent usage depends on the model, tokens, resolution and selected group. This is SuperAI API balance, not an official provider account or transferable provider credit.

Recharge calculator

See the official list-price usage value

Enter a recharge amount to estimate the API usage value benchmarked against official provider list prices.

Recharge amount (USD)

Official list-price equivalent$100.00

Difference in purchase cost$85.00

Effective purchase rate15% of official list-price value

This estimates SuperAI API gateway usage value, not transferable credit in an official provider account. Actual consumption depends on the model, tokens, resolution and selected group.

API request example

curl -X POST https://superaiapi.com/v1/messages \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "claude-sonnet-5",
  "max_tokens": 1024,
  "messages": [{"role": "user", "content": "Review this implementation"}]
}'

Use the protocol your application already understands

Send native Claude Messages requests when you need Anthropic-oriented semantics, or use the OpenAI-compatible endpoint when Claude is one option inside an existing multi-model application.

Native /v1/messages endpoint
OpenAI-compatible Chat Completions path
Streaming on supported channels
Prompt-cache usage visibility

Route around temporary upstream incidents

Claude capacity can vary across suppliers. Channel health scoring and automatic failover let the gateway prefer stable routes, temporarily reduce traffic to failing routes and probe them again after recovery.

Control access without distributing provider keys

Issue gateway tokens to users or services, assign groups and quotas, and keep upstream credentials inside the administrative channel layer.

Frequently asked questions

Can I use the Anthropic SDK?

Yes. Point supported Messages API clients at the gateway Base URL and use a SuperAI API token with the claude-sonnet-5 model ID.

Can Claude Sonnet 5 share a token with GPT models?

Yes, when the token group is permitted to use both model families.

How is prompt caching billed?

Cache reads and writes follow the configured model and group ratios. The usage log exposes cache-token details when the upstream reports them.