Skip to content

Model catalog

One key. Every kind of intelligence.

Filter by provider, capability, context window or price. Every model accepts the same request shape — only the model field changes.

Showing 6 of 6 models
ModelProviderCapabilitiesContextMax outputInput / 1MOutput / 1M
Claude Sonnet 5claude-sonnet-5AnthropicReasoningCodingLong Context1M128K$3.00$15.00Details
DeepSeek V4 Prodeepseek-v4-proDeepSeekReasoningCoding256K64K$0.90$3.40Details
DeepSeek V4.1 Flashdeepseek-v4.1-flashDeepSeekFastCoding256K64K$0.20$0.80Details
GLM 5.2glm-5.2Zhipu AIReasoningCoding256K64K$0.60$2.20Details
GLM 5.3 Flashglm-5.3-flashZhipu AIFastCoding256K64K$0.25$1.10Details
GPT 5.6 Lunagpt-5.6-lunaOpenAIReasoningVisionLong Context1M128K$2.50$10.00Details
  • Claude Sonnet 5Anthropicclaude-sonnet-5 · 1M context · $3.00 in / $15.00 outDetails
  • DeepSeek V4 ProDeepSeekdeepseek-v4-pro · 256K context · $0.90 in / $3.40 outDetails
  • DeepSeek V4.1 FlashDeepSeekdeepseek-v4.1-flash · 256K context · $0.20 in / $0.80 outDetails
  • GLM 5.2Zhipu AIglm-5.2 · 256K context · $0.60 in / $2.20 outDetails
  • GLM 5.3 FlashZhipu AIglm-5.3-flash · 256K context · $0.25 in / $1.10 outDetails
  • GPT 5.6 LunaOpenAIgpt-5.6-luna · 1M context · $2.50 in / $10.00 outDetails

Not sure which model to route to?

Configure a default model and an ordered fallback chain, and let the gateway pick a healthy route.

Configure routing