The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
Python ai-gatewayanthropicazure-openaibedrockgatewaylangchainlitellmllmllm-gatewayllmopsmcp-gatewayopenaiopenai-proxyrustrust-aivertex-ai
{"type": "system", "subtype": "init", "cwd": "/workspace", "session_id": "53af83ee-c3e1-4b96-a70a-f15b6cb6c794", "tools": ["Task", "Bash", "CronCreate", "CronDelete", "CronList", "Edit", "EnterWorktree", "ExitWorktree", "ListAgents", "NotebookEdit", "Read", "ReportFindings", "ScheduleWakeup", "SendMessage", "Skill", "TaskStop", "WebFetch", "WebSearch", "Workflow", "Write"], "mcp_servers": [], "model": "does-not-exist-model-xyz", "permissionMode": "bypassPermissions", "slash_commands": ["deep-research", "dataviz", "update-config", "verify", "debug", "code-review", "simplify", "batch", "fewer-permission-prompts", "doctor", "loop", "claude-api", "workflow-authoring", "run", "run-skill-generator", "agents", "auto-mode-setup", "autocompact", "clear", "color", "compact", "config", "output-style", "context", "effort", "fast", "focus", "heapdump", "init", "mcp", "model", "__remote-workflow", "workflow-launch-exec", "reload-plugins", "reload-skills", "rename", "security-review", "usage", "insights", "recap", "goal", "list-agents", "team-onboarding"], "terminal_slash_commands": ["doctor", "color", "focus", "reload-plugins"], "apiKeySource": "none", "claude_code_version": "2.1.285", "output_style": "default", "agents": ["claude", "Explore", "general-purpose", "Plan", "statusline-setup"], "skills": ["deep-research", "dataviz", "update-config", "verify", "debug", "code-review", "simplify", "batch", "fewer-permission-prompts", "doctor", "loop", "claude-api", "workflow-authoring", "run", "run-skill-generator"], "plugins": [{"name": "cc-plugin-agents-md", "path": "builtin", "source": "cc-plugin-agents-md@builtin"}], "capabilities": ["interrupt_receipt_v1", "interrupt_cancel_queued_v1", "msg_lifecycle_v1", "mcp_read_resource_v1", "mcp_tool_ui_meta_v1"], "analytics_disabled": true, "product_feedback_disabled": true, "uuid": "a5308e12-af9c-41a0-97dc-91fc574b03dc", "fast_mode_state": "off", "fast_mode_disabled_reason": "sdk_opt_in_required", "per_turn_effort_active": false, "view_mode": "default"}
{"type": "assistant", "message": {"diagnostics": null, "id": "4a8ebe84-f673-472b-9f28-b38722e84b33", "container": null, "model": "<synthetic>", "role": "assistant", "stop_details": null, "stop_reason": "stop_sequence", "stop_sequence": "", "type": "message", "usage": {"output_tokens_details": null, "input_tokens": 0, "output_tokens": 0, "cache_creation_input_tokens": 0, "cache_read_input_tokens": 0, "server_tool_use": {"web_search_requests": 0, "web_fetch_requests": 0}, "service_tier": null, "cache_creation": {"ephemeral_1h_input_tokens": 0, "ephemeral_5m_input_tokens": 0}, "inference_geo": null, "iterations": null, "speed": null, "fallback_credit": null}, "content": [{"type": "text", "text": "API Error: 400 litellm.BadRequestError: You passed in model=does-not-exist-model-xyz. There are no healthy deployments for this model\n\nLiteLLM: model group 'does-not-exist-model-xyz' failed with the error above and no fallback model group was found for it, so the request was not retried on another model. Fallbacks are configured for: anthropic/*, anthropic/claude-opus-4-8, claude-mixed-router, anthropic/claude-fable-5, claude-opus-5, claude-sonnet-5, claude-fable-5, claude-fable-5-1, claude-haiku-4-5-20251001. Add a fallbacks entry for that model group (Router fallbacks or proxy router_settings.fallbacks) to retry on another model."}], "context_management": null}, "parent_tool_use_id": null, "session_id": "53af83ee-c3e1-4b96-a70a-f15b6cb6c794", "uuid": "f8c605c9-c1d6-43b0-89f8-aa64015d7895", "timestamp": "2026-09-30T17:00:14.185Z", "error": "unknown", "is_api_error_message": true}
{"duration_api_ms": 0, "stop_reason": "stop_sequence", "session_id": "53af83ee-c3e1-4b96-a70a-f15b6cb6c794", "total_cost_usd": 0, "usage": {"output_tokens_details": {"thinking_tokens": 0}, "input_tokens": 0, "cache_creation_input_tokens": 0, "cache_read_input_tokens": 0, "output_tokens": 0, "server_tool_use": {"web_search_requests": 0, "web_fetch_requests": 0}, "service_tier": "standard", "cache_creation": {"ephemeral_1h_input_tokens": 0, "ephemeral_5m_input_tokens": 0}, "inference_geo": "", "iterations": [], "speed": "standard", "fallback_credit": null}, "modelUsage": {}, "permission_denials": [], "terminal_reason": "api_error", "fast_mode_state": "off", "fast_mode_disabled_reason": "sdk_opt_in_required", "subagent_stats": {"spawned": 0, "requested": {"background": 0, "foreground": 0, "unset": 0}, "started_in_background": 0, "max_depth": 0, "spawned_by_subagents": 0, "completed": 0, "failed": 0, "killed": {"parent": 0, "user": 0, "system": 0}, "refused": {"depth_limit": 0, "concurrency_limit": 0, "budget": 0}, "by_type": {}}, "is_error": true, "num_turns": 1, "subtype": "success", "api_error_status": 400, "result": "API Error: 400 litellm.BadRequestError: You passed in model=does-not-exist-model-xyz. There are no healthy deployments for this model\n\nLiteLLM: model group 'does-not-exist-model-xyz' failed with the error above and no fallback model group was found for it, so the request was not retried on another model. Fallbacks are configured for: anthropic/*, anthropic/claude-opus-4-8, claude-mixed-router, anthropic/claude-fable-5, claude-opus-5, claude-sonnet-5, claude-fable-5, claude-fable-5-1, claude-haiku-4-5-20251001. Add a fallbacks entry for that model group (Router fallbacks or proxy router_settings.fallbacks) to retry on another model.", "type": "result", "duration_ms": 6781, "uuid": "c38e7f6d-8920-44f4-bab5-a599535509a0", "queued_turn_count": 0, "result_index": 0}