{"ok":true,"service":"ai-relay","version":53,"build":"v3.4.17","mode":"passthrough-first (the model you pick is the model used) + cpu-safe","upstream":"https://integrate.api.nvidia.com","has_server_key":true,"has_alt_key":true,"token_required":true,"default_model":"openai/gpt-oss-20b","race_models":["openai/gpt-oss-20b","nvidia/nemotron-3-ultra-550b-a55b","z-ai/glm-5.3-flash","z-ai/glm-5.3","moonshotai/kimi-k3","deepseek-ai/deepseek-v4.1-flash"],"race_max":4,"race_stagger_ms":250,"race":"off","fallback":"off","key_failover":"on","key_failover_ready":true,"think_mode":"","total_budget_ms":600000,"passthrough_default":true,"stats":"on","usage_inject":"on","rate_limit":{"token_binding":true,"ip_binding":true},"tokens_configured":1,"race_wait_ms":9000,"race_grace_ms":800,"race_head_ms":16000,"race_data_guard_ms":45000,"max_tokens":4096,"max_tokens_tools":8192,"default_effort":"","upstream_timeout_ms":600000}