Live from gateway /v1/models
Catalog reflects the 10 models the gateway is routing right now.

Models

한 API로 라우팅되는 모델 카탈로그

OpenToken 게이트웨이가 라우팅하는 모델과 100만 토큰당 정가입니다. 모델 ID만 바꿔 호출하세요. 가격은 공급자 정가이며 마크업이 없습니다.

전체 10개 중 10개 표시

ModelModalityInput / 1MOutput / 1MCache read / 1MCache write / 1MContextCaching
Claude Haiku 4.5anthropic/claude-haiku-4-5Fast, low-cost Claude model for high-volume and latency-sensitive tasks.text · vision$1.00$5.00$0.10$1.25200Kexplicit
Claude Opus 4.6anthropic/claude-opus-4-6High-capability Claude Opus generation for demanding reasoning workloads.text · vision$5.00$25.00$0.50$6.25200Kexplicit
Claude Opus 4.7anthropic/claude-opus-4-7Anthropic's most capable model for complex reasoning, coding, and agents.text · vision$5.00$25.00$0.50$6.25200Kexplicit
Claude Sonnet 4.5anthropic/claude-sonnet-4-5Prior Claude Sonnet generation, cost-balanced for general use.text · vision$3.00$15.00$0.30$3.75200Kexplicit
Claude Sonnet 4.6anthropic/claude-sonnet-4-6Balanced Claude Sonnet model for everyday production traffic.text · vision$3.00$15.00$0.30$3.75200Kexplicit
Gemini 2.5 Progoogle/gemini-2.5-proGoogle long-context model with a 1M-token window and strong reasoning.text · vision$1.25$10.00$0.125$1.251,000Kexplicit
Gemini 3 Flashgoogle/gemini-3-flashFast, low-cost Gemini 3 model for high-volume, latency-sensitive agent traffic.text · vision$0.50$3.00$0.05$0.501,000Kexplicit
Gemini 3.1 Flash-Litegoogle/gemini-3.1-flash-liteMost cost-efficient Gemini model for high-volume agentic tasks and simple processing.text · vision$0.25$1.50$0.025$0.251,000Kexplicit
Gemini 3.1 Progoogle/gemini-3.1-proHighest-capability Gemini 3.1 model with a 2M-token context window.text · vision$2.00$12.00$0.20$2.002,000Kexplicit
Text Embedding 004google/text-embedding-004768-dim text embeddings via the gateway /v1/embeddings endpoint.embeddings$0.025$0.00——2.048Kimplicit