Bonus

Chinese models Kimi-k3, Qwen3.8-max, and GLM-5.3 are now available at 50% off their official prices; GLM-5.3-flash and DeepSeek-V4.1-flash-1017 are available at 40% off their official prices.

Login
Models/Reasoning/Claude Sonnet 4.6

Anthropic: Claude Sonnet 4.6

Strong long-context reasoning model with dependable analytical depth.

Capability support
TText🖼Vision⚙Tools{}JSON⚡Streaming
Context windowN/Atokens

Official pricing

The model's published list prices, used only as the comparison baseline for route pricing and discounts

Input tokens$3.001M
Output tokens$15.001M
Cache read$0.301M
Cache write$6.001M

Available routes

Provider, public group, live pricing, latency, and uptime per active route

Provider / groupInput tokens1M tokensOutput tokens1M tokensCache read1M tokensCache write1M tokensLatencyThroughputUptime
AnthropicGroup: Claude Sonnet 4.690% OFF
Input tokens$0.30$3.00
Output tokens$1.50$15.00
Cache read$0.0300$0.30
Cache write$0.60$6.00
Latency1.5sThroughput—
Uptime