All nodes/Integrations/HTTP & Web

Web Search

Searches the web and returns both the model's answer and the sources themselves with text excerpts. Works as a regular scenario step (the Query port) and as an AI agent tool on the 'Agent extensions' input. The search engine is the model's built-in one, or Exa/Parallel/Perplexity.

Web SearchT▶

QuerySearch results

Agent extension

Type in the graph: websearch

ToolExec

An error output can be enabled to handle failures on their own path.

Ports can be split into separate execution and data handles.

Try it

Minimal working scenario

Entry

Web SearchT▶

Exit▶

Execute + Data

Press “Copy nodes”, open the editor and hit Ctrl+V on the canvas.

Pick your own connection or knowledge base first — the graph carries REPLACE_ME.

When to use it

The one web-search node: it returns both an answer and the sources with their text excerpts — to cite them, to show them to the user, or to feed them into the next prompt. The neighbour Fetch Webpage solves a different problem: it reads a URL you already know. “Find it, then read it” is those two nodes on one agent.

The node plays both roles at once: a normal graph step (the Query port) and an agent tool (tool_out → the agent’s extensions port). When a model calls it, what comes back is the sources — not an answer written by another model.

How it works

A search always rides along with a model request. That is where the Model field comes from, and why there are two independent charges — the tokens at the model’s normal tariff, plus a separate search fee. On a key of your own the platform charges for neither.

Search mode “Single search” performs exactly one request per run: predictable cost, works with every model. “Agentic” hands the decision to the model, which then needs tool calling, and the volume is bounded by Max searches, with a spend ceiling set by the platform on top.

Turning Write an answer off returns the sources only and costs less: answer comes back empty while results and context are filled. context is a ready markdown digest, handy to drop straight into the next node’s prompt.

Search engine “Auto” uses the provider’s own search when the model has one and Exa otherwise. “Built into the model” requires a model marked native search in the dropdown.

Common mistakes

Picking “Built into the model” for a model without its own search. The node stops before the call and explains why — that is configuration, not a search outage.
Expecting content to always be filled. Native provider search and perplexity/sonar cite title and URL only; excerpts come from Exa, Parallel and Perplexity as the engine.
Filling the Query field while the Query port is connected. The port wins, the field is ignored.
Using both domain filters. Parallel and Perplexity accept either Only these domains or Exclude domains; native OpenAI search ignores exclusions and native Google search does not support them.
Treating excerpt size as a cost control. In “Single search” mode it trims text that has already arrived: it bounds the output, not the token bill. Depth is set by Search depth, the only control that reaches the model’s built-in search.

Inputs

Port Wire Payload Notes

Port	Wire	Payload	Notes
Query`query`	Execute + Data`execute_data`	—	Search text; replaces the Query field when connected shown when operation_mode ≠ "as_tool"

Queryquery

Execute + Dataexecute_data

—

Search text; replaces the Query field when connected

shown when operation_mode ≠ "as_tool"

Outputs

Port	Wire	Payload	Notes
Search results`output`	Execute + Data`execute_data`	`object`	shown when operation_mode ≠ "as_tool"
Agent extension`tool_out`	Extension`link_extension`	—	shown when operation_mode ≠ "executable"

Configuration

Field	Type	Default	Description
Node mode`operation_mode`	`string`	`executable`	Executable — a step in the scenario, with Run and Success ports. As Tool — an extension an AI Agent calls itself: only the Agent extension port is shown and the agent decides when to run it. Options: `executable` — Executable, `as_tool` — As Tool
Query`query`	`string`	`""`	What to search for. Ignored when the Query port is connected. supports templatesoverridden by port: query shown when «Node mode» = Executable
Model`model`	`string`	`openai/gpt-4o-mini`	The model that runs the search and writes the answer. Any model can search; models marked 'native search' can additionally use their own built-in own engine. Options: `openai/gpt-6-luna` — OpenAI: GPT-6 Luna · native search, `openai/gpt-oss-20b` — OpenAI: gpt-oss-20b, `anthropic/claude-opus-5.5` — Anthropic: Claude Opus 5.5 · native search, `anthropic/claude-haiku-5.5` — Anthropic: Claude Haiku 5.5 · native search, `google/gemini-3.8-flash` — Google: Gemini 3.8 Flash · native search, `google/gemini-2.5-flash-lite` — Google: Gemini 2.5 Flash Lite · native search, `deepseek/deepseek-v4-pro` — DeepSeek: DeepSeek V4 Pro 0423, `deepseek/deepseek-v4.1-flash` — DeepSeek: DeepSeek V4.1 Flash, `x-ai/grok-4.6` — SpaceXAI: Grok 4.6 · native search, `qwen/qwen3.8-max-0902` — Qwen: Qwen3.8 Max (0902), `qwen/qwen3.7-flash` — Qwen: Qwen3.7 Flash, `meta/muse-glimmer-30b` — Meta: Muse Glimmer 30B show all (406) `mistralai/mistral-large-2512` — Mistral: Mistral Large 3 2512, `mistralai/mistral-nemo` — Mistral: Mistral Nemo, `moonshotai/kimi-k3` — MoonshotAI: Kimi K3, `moonshotai/kimi-k2.5` — MoonshotAI: Kimi K2.5, `minimax/minimax-m3` — MiniMax: MiniMax M3, `minimax/minimax-m2.7` — MiniMax: MiniMax M2.7, `z-ai/glm-5.3` — Z.ai: GLM 5.3, `z-ai/glm-5.3-flash` — Z.ai: GLM 5.3 Flash, `nvidia/nemotron-3-ultra-550b-a55b` — NVIDIA: Nemotron 3 Ultra, `openai/gpt-5.6-luna` — OpenAI: GPT-5.6 Luna · native search, `openai/gpt-5.6-sol` — OpenAI: GPT-5.6 Sol · native search, `openai/gpt-6.1-sol` — OpenAI: GPT-6.1 Sol · native search, `openai/gpt-6-astra` — OpenAI: GPT-6 Astra · native search, `openai/gpt-6-sol` — OpenAI: GPT-6 Sol · native search, `openai/gpt-6-luna-pro` — OpenAI: GPT-6 Luna Pro · native search, `openai/gpt-oss-120b` — OpenAI: gpt-oss-120b, `openai/gpt-5.6-terra` — OpenAI: GPT-5.6 Terra · native search, `openai/gpt-4o-mini` — OpenAI: GPT-4o-mini, `openai/gpt-5-nano` — OpenAI: GPT-5 Nano · native search, `openai/gpt-5.4-mini` — OpenAI: GPT-5.4 Mini · native search, `openai/gpt-5.3-codex` — OpenAI: GPT-5.3-Codex · native search, `openai/gpt-5.6-luna-pro` — OpenAI: GPT-5.6 Luna Pro · native search, `openai/gpt-5-mini` — OpenAI: GPT-5 Mini · native search, `openai/gpt-5.4-nano` — OpenAI: GPT-5.4 Nano · native search, `openai/gpt-4.1-mini` — OpenAI: GPT-4.1 Mini · native search, `openai/gpt-5.4` — OpenAI: GPT-5.4 · native search, `openai/gpt-4.1` — OpenAI: GPT-4.1 · native search, `openai/gpt-5.5` — OpenAI: GPT-5.5 · native search, `openai/gpt-5.2` — OpenAI: GPT-5.2 · native search, `openai/gpt-6.1-sol-pro` — OpenAI: GPT-6.1 Sol Pro · native search, `openai/gpt-5.1` — OpenAI: GPT-5.1 · native search, `openai/gpt-6-luna:batch` — OpenAI: GPT-6 Luna (batch) · native search, `openai/gpt-6-astra-pro` — OpenAI: GPT-6 Astra Pro · native search, `openai/gpt-4.1-nano` — OpenAI: GPT-4.1 Nano · native search, `openai/gpt-5.6-sol-pro` — OpenAI: GPT-5.6 Sol Pro · native search, `openai/gpt-4o` — OpenAI: GPT-4o, `openai/gpt-4o-mini-2024-07-18` — OpenAI: GPT-4o-mini (2024-07-18), `openai/gpt-5` — OpenAI: GPT-5 · native search, `openai/gpt-5.6-luna:batch` — OpenAI: GPT-5.6 Luna (batch) · native search, `openai/gpt-6-sol-pro` — OpenAI: GPT-6 Sol Pro · native search, `openai/gpt-5.6-terra-pro` — OpenAI: GPT-5.6 Terra Pro · native search, `openai/o4-mini` — OpenAI: o4 Mini · native search, `openai/gpt-6-luna-pro:batch` — OpenAI: GPT-6 Luna Pro (batch) · native search, `openai/gpt-oss-safeguard-20b` — OpenAI: gpt-oss-safeguard-20b, `openai/gpt-chat-latest` — OpenAI: GPT Chat Latest · native search, `openai/gpt-4o-2024-08-06` — OpenAI: GPT-4o (2024-08-06), `openai/gpt-6-sol:batch` — OpenAI: GPT-6 Sol (batch) · native search, `openai/gpt-4o-2024-11-20` — OpenAI: GPT-4o (2024-11-20), `openai/gpt-5.1-codex-mini` — OpenAI: GPT-5.1-Codex-Mini · native search, `openai/o3-mini` — OpenAI: o3 Mini · native search, `openai/gpt-5.2-codex` — OpenAI: GPT-5.2-Codex · native search, `openai/gpt-5.1-codex` — OpenAI: GPT-5.1-Codex · native search, `openai/gpt-oss-120b:batch` — OpenAI: gpt-oss-120b (batch), `openai/gpt-3.5-turbo` — OpenAI: GPT-3.5 Turbo, `openai/o3` — OpenAI: o3 · native search, `openai/gpt-5.6-sol:batch` — OpenAI: GPT-5.6 Sol (batch) · native search, `openai/gpt-5.6-luna-pro:batch` — OpenAI: GPT-5.6 Luna Pro (batch) · native search, `openai/gpt-5-nano:batch` — OpenAI: GPT-5 Nano (batch) · native search, `openai/gpt-5.6-terra:batch` — OpenAI: GPT-5.6 Terra (batch) · native search, `openai/gpt-6-astra:batch` — OpenAI: GPT-6 Astra (batch) · native search, `openai/gpt-5.5-pro` — OpenAI: GPT-5.5 Pro · native search, `openai/gpt-4o-2024-05-13` — OpenAI: GPT-4o (2024-05-13), `openai/gpt-5.1-codex-max` — OpenAI: GPT-5.1-Codex-Max · native search, `openai/o4-mini-high` — OpenAI: o4 Mini High · native search, `openai/gpt-4` — OpenAI: GPT-4, `openai/gpt-4-turbo` — OpenAI: GPT-4 Turbo, `openai/gpt-oss-20b:batch` — OpenAI: gpt-oss-20b (batch), `openai/gpt-6-sol-pro:batch` — OpenAI: GPT-6 Sol Pro (batch) · native search, `openai/gpt-6-astra-pro:batch` — OpenAI: GPT-6 Astra Pro (batch) · native search, `openai/gpt-3.5-turbo-0613` — OpenAI: GPT-3.5 Turbo (older v0613), `openai/gpt-5.2-pro` — OpenAI: GPT-5.2 Pro · native search, `openai/gpt-5.4-pro` — OpenAI: GPT-5.4 Pro · native search, `openai/gpt-3.5-turbo-16k` — OpenAI: GPT-3.5 Turbo 16k, `openai/o1` — OpenAI: o1 · native search, `openai/o3-mini-high` — OpenAI: o3 Mini High · native search, `openai/gpt-5-pro` — OpenAI: GPT-5 Pro · native search, `openai/o3-pro` — OpenAI: o3 Pro · native search, `openai/o1-pro` — OpenAI: o1-pro · native search, `openai/gpt-5.6-sol-pro:batch` — OpenAI: GPT-5.6 Sol Pro (batch) · native search, `openai/gpt-5.6-terra-pro:batch` — OpenAI: GPT-5.6 Terra Pro (batch) · native search, `openai/gpt-5-pro:batch` — OpenAI: GPT-5 Pro (batch) · native search, `openai/o3-mini:batch` — OpenAI: o3 Mini (batch) · native search, `openai/o4-mini:batch` — OpenAI: o4 Mini (batch) · native search, `openai/gpt-5:batch` — OpenAI: GPT-5 (batch) · native search, `openai/gpt-5-mini:batch` — OpenAI: GPT-5 Mini (batch) · native search, `openai/o3:batch` — OpenAI: o3 (batch) · native search, `openai/gpt-5.5-pro:batch` — OpenAI: GPT-5.5 Pro (batch) · native search, `openai/gpt-5.4-pro:batch` — OpenAI: GPT-5.4 Pro (batch) · native search, `openai/gpt-5.2:batch` — OpenAI: GPT-5.2 (batch) · native search, `openai/gpt-5.5:batch` — OpenAI: GPT-5.5 (batch) · native search, `openai/gpt-5.1:batch` — OpenAI: GPT-5.1 (batch) · native search, `openai/gpt-5.2-pro:batch` — OpenAI: GPT-5.2 Pro (batch) · native search, `openai/gpt-4.1-nano:batch` — OpenAI: GPT-4.1 Nano (batch) · native search, `openai/gpt-5.4-nano:batch` — OpenAI: GPT-5.4 Nano (batch) · native search, `openai/gpt-4.1-mini:batch` — OpenAI: GPT-4.1 Mini (batch) · native search, `openai/gpt-4o:batch` — OpenAI: GPT-4o (batch) · native search, `openai/gpt-4.1:batch` — OpenAI: GPT-4.1 (batch) · native search, `openai/gpt-5.4-mini:batch` — OpenAI: GPT-5.4 Mini (batch) · native search, `openai/gpt-4o-mini:batch` — OpenAI: GPT-4o-mini (batch) · native search, `openai/gpt-4-turbo:batch` — OpenAI: GPT-4 Turbo (batch) · native search, `openai/gpt-5.4:batch` — OpenAI: GPT-5.4 (batch) · native search, `openai/gpt-3.5-turbo:batch` — OpenAI: GPT-3.5 Turbo (batch) · native search, `openai/gpt-3.5-turbo-instruct` — OpenAI: GPT-3.5 Turbo Instruct, `openai/gpt-5.2-chat` — OpenAI: GPT-5.2 Chat · native search, `anthropic/claude-sonnet-5.5` — Anthropic: Claude Sonnet 5.5 · native search, `anthropic/claude-opus-5` — Anthropic: Claude Opus 5 · native search, `anthropic/claude-sonnet-5` — Anthropic: Claude Sonnet 5 · native search, `anthropic/claude-sonnet-4.6` — Anthropic: Claude Sonnet 4.6 · native search, `anthropic/claude-fable-5.1` — Anthropic: Claude Fable 5.1 · native search, `anthropic/claude-haiku-4.5` — Anthropic: Claude Haiku 4.5 · native search, `anthropic/claude-opus-4.8` — Anthropic: Claude Opus 4.8 · native search, `anthropic/claude-sonnet-4.5` — Anthropic: Claude Sonnet 4.5 · native search, `anthropic/claude-opus-4.6` — Anthropic: Claude Opus 4.6 · native search, `anthropic/claude-fable-5` — Anthropic: Claude Fable 5 · native search, `anthropic/claude-opus-4.7` — Anthropic: Claude Opus 4.7 · native search, `anthropic/claude-opus-4.5` — Anthropic: Claude Opus 4.5 · native search, `anthropic/claude-sonnet-4` — Anthropic: Claude Sonnet 4 · native search, `anthropic/claude-opus-5.5:batch` — Anthropic: Claude Opus 5.5 (batch) · native search, `anthropic/claude-sonnet-5.5:batch` — Anthropic: Claude Sonnet 5.5 (batch) · native search, `anthropic/claude-opus-4.1` — Anthropic: Claude Opus 4.1 · native search, `anthropic/claude-haiku-5.5:batch` — Anthropic: Claude Haiku 5.5 (batch) · native search, `anthropic/claude-fable-5.1:batch` — Anthropic: Claude Fable 5.1 (batch) · native search, `anthropic/claude-opus-5:batch` — Anthropic: Claude Opus 5 (batch) · native search, `anthropic/claude-sonnet-5:batch` — Anthropic: Claude Sonnet 5 (batch) · native search, `anthropic/claude-opus-4.1:batch` — Anthropic: Claude Opus 4.1 (batch) · native search, `anthropic/claude-haiku-4.5:batch` — Anthropic: Claude Haiku 4.5 (batch) · native search, `anthropic/claude-opus-4.5:batch` — Anthropic: Claude Opus 4.5 (batch) · native search, `anthropic/claude-sonnet-4.5:batch` — Anthropic: Claude Sonnet 4.5 (batch) · native search, `anthropic/claude-opus-4.6:batch` — Anthropic: Claude Opus 4.6 (batch) · native search, `anthropic/claude-sonnet-4.6:batch` — Anthropic: Claude Sonnet 4.6 (batch) · native search, `anthropic/claude-opus-4.7:batch` — Anthropic: Claude Opus 4.7 (batch) · native search, `anthropic/claude-opus-4.8:batch` — Anthropic: Claude Opus 4.8 (batch) · native search, `anthropic/claude-fable-5:batch` — Anthropic: Claude Fable 5 (batch) · native search, `google/gemini-3-flash-preview` — Google: Gemini 3 Flash Preview · native search, `google/gemini-3.1-flash-lite` — Google: Gemini 3.1 Flash Lite · native search, `google/gemini-2.5-flash` — Google: Gemini 2.5 Flash · native search, `google/gemma-4-31b-it` — Google: Gemma 4 31B, `google/gemini-3.7-flash` — Google: Gemini 3.7 Flash · native search, `google/gemma-4-26b-a4b-it` — Google: Gemma 4 26B A4B , `google/gemini-3.5-flash-lite` — Google: Gemini 3.5 Flash Lite · native search, `google/gemini-3.1-pro-preview` — Google: Gemini 3.1 Pro Preview · native search, `google/gemini-3.1-flash-lite-preview` — Google: Gemini 3.1 Flash Lite Preview · native search, `google/gemini-3.6-flash` — Google: Gemini 3.6 Flash · native search, `google/gemini-3.5-flash` — Google: Gemini 3.5 Flash · native search, `google/gemini-2.5-pro` — Google: Gemini 2.5 Pro · native search, `google/gemma-3-27b-it` — Google: Gemma 3 27B, `google/gemma-3-12b-it` — Google: Gemma 3 12B, `google/gemini-2.5-flash-lite:batch` — Google: Gemini 2.5 Flash Lite (batch) · native search, `google/gemini-3.6-flash:batch` — Google: Gemini 3.6 Flash (batch) · native search, `google/gemini-3.7-flash:batch` — Google: Gemini 3.7 Flash (batch) · native search, `google/gemini-3.1-flash-lite:batch` — Google: Gemini 3.1 Flash Lite (batch) · native search, `google/gemini-3.8-flash:batch` — Google: Gemini 3.8 Flash (batch) · native search, `google/gemma-3-4b-it` — Google: Gemma 3 4B, `google/gemini-3.1-pro-preview-customtools` — Google: Gemini 3.1 Pro Preview Custom Tools · native search, `google/gemini-2.5-flash:batch` — Google: Gemini 2.5 Flash (batch) · native search, `google/gemini-3.5-flash-lite:batch` — Google: Gemini 3.5 Flash Lite (batch) · native search, `google/gemma-2-27b-it` — Google: Gemma 2 27B, `google/gemini-3.1-pro-preview:batch` — Google: Gemini 3.1 Pro Preview (batch) · native search, `google/gemini-3-flash-preview:batch` — Google: Gemini 3 Flash Preview (batch) · native search, `google/gemini-3.5-flash:batch` — Google: Gemini 3.5 Flash (batch) · native search, `google/gemini-2.5-pro:batch` — Google: Gemini 2.5 Pro (batch) · native search, `google/gemini-2.5-pro-preview` — Google: Gemini 2.5 Pro Preview 06-05 · native search, `deepseek/deepseek-v4-flash-0731` — DeepSeek: DeepSeek V4 Flash 0731, `deepseek/deepseek-v4-flash` — DeepSeek: DeepSeek V4 Flash 0423, `deepseek/deepseek-v4-pro-0813` — DeepSeek: DeepSeek V4 Pro 0813, `deepseek/deepseek-v3.2` — DeepSeek: DeepSeek V3.2, `deepseek/deepseek-v4-flash-vision-exp` — DeepSeek: DeepSeek V4 Flash Vision Exp, `deepseek/deepseek-chat-v3.1` — DeepSeek: DeepSeek V3.1, `deepseek/deepseek-chat-v3-0324` — DeepSeek: DeepSeek V3 0324, `deepseek/deepseek-chat` — DeepSeek: DeepSeek V3, `deepseek/deepseek-v3.2-exp` — DeepSeek: DeepSeek V3.2 Exp, `deepseek/deepseek-r1-0528` — DeepSeek: R1 0528, `deepseek/deepseek-v3.1-terminus` — DeepSeek: DeepSeek V3.1 Terminus, `deepseek/deepseek-v4.1-flash:batch` — DeepSeek: DeepSeek V4.1 Flash (batch), `deepseek/deepseek-r1` — DeepSeek: R1, `x-ai/grok-4.7` — SpaceXAI: Grok 4.7 · native search, `x-ai/grok-4.5` — SpaceXAI: Grok 4.5 · native search, `x-ai/grok-4.3` — SpaceXAI: Grok 4.3 · native search, `x-ai/grok-4.20` — SpaceXAI: Grok 4.20 · native search, `x-ai/grok-build-0.1` — SpaceXAI: Grok Build 0.1 · native search, `x-ai/grok-4.20-multi-agent` — SpaceXAI: Grok 4.20 Multi-Agent · native search, `x-ai/grok-4.3:batch` — SpaceXAI: Grok 4.3 (batch) · native search, `qwen/qwen3.8-27b` — Qwen: Qwen3.8 27B, `qwen/qwen3.8-flash` — Qwen: Qwen3.8 Flash, `qwen/qwen3.7-plus` — Qwen: Qwen3.7 Plus, `qwen/qwen3-235b-a22b-2507` — Qwen: Qwen3 235B A22B Instruct 2507, `qwen/qwen3.8-2.4t-a95b` — Qwen: Qwen3.8 2.4T A95B, `qwen/qwen3.5-flash-02-23` — Qwen: Qwen3.5-Flash, `qwen/qwen3.6-35b-a3b` — Qwen: Qwen3.6 35B A3B, `qwen/qwen3.5-397b-a17b` — Qwen: Qwen3.5 397B A17B, `qwen/qwen3-30b-a3b-instruct-2507` — Qwen: Qwen3 30B A3B Instruct 2507, `qwen/qwen3.5-9b` — Qwen: Qwen3.5-9B, `qwen/qwen3.8-omni-flash` — Qwen: Qwen3.8 Omni Flash, `qwen/qwen3-next-80b-a3b-instruct` — Qwen: Qwen3 Next 80B A3B Instruct, `qwen/qwen3-coder-next` — Qwen: Qwen3 Coder Next, `qwen/qwen3-vl-32b-instruct` — Qwen: Qwen3 VL 32B Instruct, `qwen/qwen3-vl-235b-a22b-instruct` — Qwen: Qwen3 VL 235B A22B Instruct, `qwen/qwen3.8-max-prime` — Qwen: Qwen3.8 Max Prime, `qwen/qwen3.6-plus` — Qwen: Qwen3.6 Plus, `qwen/qwen3.5-35b-a3b` — Qwen: Qwen3.5-35B-A3B, `qwen/qwen3-32b` — Qwen: Qwen3 32B, `qwen/qwen3-coder` — Qwen: Qwen3 Coder 480B A35B, `qwen/qwen3.6-27b` — Qwen: Qwen3.6 27B, `qwen/qwen3.5-27b` — Qwen: Qwen3.5-27B, `qwen/qwen3.7-max` — Qwen: Qwen3.7 Max, `qwen/qwen3.6-flash` — Qwen: Qwen3.6 Flash, `qwen/qwen3.5-122b-a10b` — Qwen: Qwen3.5-122B-A10B, `qwen/qwen3-vl-8b-instruct` — Qwen: Qwen3 VL 8B Instruct, `qwen/qwen3-vl-30b-a3b-instruct` — Qwen: Qwen3 VL 30B A3B Instruct, `qwen/qwen3-14b` — Qwen: Qwen3 14B, `qwen/qwen3-coder-30b-a3b-instruct` — Qwen: Qwen3 Coder 30B A3B Instruct, `qwen/qwen3-8b` — Qwen: Qwen3 8B, `qwen/qwen3.5-plus-02-15` — Qwen: Qwen3.5 Plus 2026-02-15, `qwen/qwen-2.5-7b-instruct` — Qwen: Qwen2.5 7B Instruct, `qwen/qwen-2.5-72b-instruct` — Qwen2.5 72B Instruct, `qwen/qwen3-coder-plus` — Qwen: Qwen3 Coder Plus, `qwen/qwen3-30b-a3b` — Qwen: Qwen3 30B A3B, `qwen/qwen3-235b-a22b` — Qwen: Qwen3 235B A22B, `qwen/qwen2.5-vl-72b-instruct` — Qwen: Qwen2.5 VL 72B Instruct, `qwen/qwen3-coder-flash` — Qwen: Qwen3 Coder Flash, `qwen/qwen3-235b-a22b-thinking-2507` — Qwen: Qwen3 235B A22B Thinking 2507, `qwen/qwen3-max` — Qwen: Qwen3 Max, `qwen/qwen3.5-plus-20260420` — Qwen: Qwen3.5 Plus 2026-04-20, `qwen/qwen-plus` — Qwen: Qwen-Plus, `qwen/qwen3-30b-a3b-thinking-2507` — Qwen: Qwen3 30B A3B Thinking 2507, `qwen/qwen-plus-2025-07-28` — Qwen: Qwen Plus 0728, `qwen/qwen3-max-thinking` — Qwen: Qwen3 Max Thinking, `qwen/qwen3-vl-235b-a22b-thinking` — Qwen: Qwen3 VL 235B A22B Thinking, `qwen/qwen3-next-80b-a3b-thinking` — Qwen: Qwen3 Next 80B A3B Thinking, `qwen/qwen3.6-max-preview` — Qwen: Qwen3.6 Max Preview, `qwen/qwen-2.5-coder-32b-instruct` — Qwen2.5 Coder 32B Instruct, `qwen/qwen3-vl-30b-a3b-thinking` — Qwen: Qwen3 VL 30B A3B Thinking, `qwen/qwen3-vl-8b-thinking` — Qwen: Qwen3 VL 8B Thinking, `mistralai/mistral-large-4-0` — Mistral: Mistral Large 4, `mistralai/mistral-small-3.2-24b-instruct` — Mistral: Mistral Small 3.2 24B, `mistralai/mistral-small-24b-instruct-2501` — Mistral: Mistral Small 3, `mistralai/mistral-small-2603` — Mistral: Mistral Small 4, `mistralai/mistral-medium-3-5` — Mistral: Mistral Medium 3.5, `mistralai/ministral-8b-2512` — Mistral: Ministral 3 8B 2512, `mistralai/mistral-medium-3.1` — Mistral: Mistral Medium 3.1, `mistralai/devstral-2512` — Mistral: Devstral 2 2512, `mistralai/ministral-3b-2512` — Mistral: Ministral 3 3B 2512, `mistralai/ministral-14b-2512` — Mistral: Ministral 3 14B 2512, `mistralai/mistral-medium-3` — Mistral: Mistral Medium 3, `mistralai/mistral-small-3.1-24b-instruct` — Mistral: Mistral Small 3.1 24B, `mistralai/codestral-2508` — Mistral: Codestral 2508, `mistralai/ministral-8b-2512:batch` — Mistral: Ministral 3 8B 2512 (batch), `mistralai/mistral-large` — Mistral Large, `mistralai/voxtral-small-24b-2507` — Mistral: Voxtral Small 24B 2507, `mistralai/mistral-large-2407` — Mistral Large 2407, `mistralai/mixtral-8x22b-instruct` — Mistral: Mixtral 8x22B Instruct, `mistralai/mistral-small-2603:batch` — Mistral: Mistral Small 4 (batch), `mistralai/mistral-saba` — Mistral: Saba, `mistralai/mistral-medium-3-5:batch` — Mistral: Mistral Medium 3.5 (batch), `mistralai/mistral-large-2512:batch` — Mistral: Mistral Large 3 2512 (batch), `mistralai/codestral-2508:batch` — Mistral: Codestral 2508 (batch), `mistralai/mistral-medium-3.1:batch` — Mistral: Mistral Medium 3.1 (batch), `moonshotai/kimi-k2.6` — MoonshotAI: Kimi K2.6, `moonshotai/kimi-k2.7-code` — MoonshotAI: Kimi K2.7 Code, `moonshotai/kimi-k2-0905` — MoonshotAI: Kimi K2 0905, `moonshotai/kimi-k2` — MoonshotAI: Kimi K2 0711, `moonshotai/kimi-k2-thinking` — MoonshotAI: Kimi K2 Thinking, `moonshotai/kimi-k3:batch` — MoonshotAI: Kimi K3 (batch), `minimax/minimax-m2.5` — MiniMax: MiniMax M2.5, `minimax/minimax-m2.1` — MiniMax: MiniMax M2.1, `minimax/minimax-m2` — MiniMax: MiniMax M2, `minimax/minimax-m2-her` — MiniMax: MiniMax M2-her, `minimax/minimax-m1` — MiniMax: MiniMax M1, `minimax/minimax-01` — MiniMax: MiniMax-01, `z-ai/glm-5.2` — Z.ai: GLM 5.2, `z-ai/glm-5.3-flashx` — Z.ai: GLM 5.3 FlashX, `z-ai/glm-5.3-prime` — Z.ai: GLM 5.3 Prime, `z-ai/glm-4.7` — Z.ai: GLM 4.7, `z-ai/glm-5` — Z.ai: GLM 5, `z-ai/glm-5.1` — Z.ai: GLM 5.1, `z-ai/glm-4.6` — Z.ai: GLM 4.6, `z-ai/glm-4.7-flash` — Z.ai: GLM 4.7 Flash, `z-ai/glm-4.5-air` — Z.ai: GLM 4.5 Air, `z-ai/glm-5-turbo` — Z.ai: GLM 5 Turbo, `z-ai/glm-5.3-flash:batch` — Z.ai: GLM 5.3 Flash (batch), `z-ai/glm-4.5` — Z.ai: GLM 4.5, `z-ai/glm-5v-turbo` — Z.ai: GLM 5V Turbo, `z-ai/glm-4.6v` — Z.ai: GLM 4.6V, `z-ai/glm-4.5v` — Z.ai: GLM 4.5V, `z-ai/glm-5.3:batch` — Z.ai: GLM 5.3 (batch), `nvidia/nemotron-3.5-lightning` — NVIDIA: Nemotron 3.5 Lightning, `nvidia/nemotron-3-super-120b-a12b` — NVIDIA: Nemotron 3 Super, `nvidia/nemotron-3-nano-30b-a3b` — NVIDIA: Nemotron 3 Nano 30B A3B, `nvidia/nemotron-3.5-content-safety` — NVIDIA: Nemotron 3.5 Content Safety, `xiaomi/mimo-v2.6-flash` — Xiaomi: MiMo-V2.6-Flash, `xiaomi/mimo-v2.6-pro` — Xiaomi: MiMo-V2.6-Pro, `xiaomi/mimo-v2.5` — Xiaomi: MiMo-V2.5, `xiaomi/mimo-v2.5-pro` — Xiaomi: MiMo-V2.5-Pro, `xiaomi/mimo-v2.6-pro-ultraspeed` — Xiaomi: MiMo-V2.6-Pro-UltraSpeed, `tencent/hy4-preview` — Tencent: Hy4 preview, `tencent/hy3` — Tencent: Hy3, `tencent/hy3-preview` — Tencent: Hy3 preview, `tencent/hy-mt2-30b-a3b` — Tencent: Hy-MT2-30B-A3B, `tencent/hy-mt2-7b` — Tencent: Hy-MT2-7B, `tencent/hy-mt2-1.8b` — Tencent: Hy-MT2-1.8B, `tencent/hunyuan-a13b-instruct` — Tencent: Hunyuan A13B Instruct, `upstage/solar-mini4` — Upstage: Solar Mini 4, `upstage/solar-pro4` — Upstage: Solar Pro 4, `upstage/solar-pro-3` — Upstage: Solar Pro 3, `inclusionai/ling-3.1-flash` — inclusionAI: Ling 3.1 Flash, `inclusionai/ling-3.0-flash` — inclusionAI: Ling 3.0 Flash, `inclusionai/ling-3.0-flash-vl` — inclusionAI: Ling 3.0 Flash VL, `inclusionai/ling-3.0-flash-fin` — inclusionAI: Ling 3.0 Flash Fin, `stepfun/step-3.7-flash` — StepFun: Step 3.7 Flash, `stepfun/step-3.5-flash` — StepFun: Step 3.5 Flash, `poolside/laguna-s-2.1` — Poolside: Laguna S 2.1, `poolside/laguna-xs-2.1` — Poolside: Laguna XS 2.1, `meta-llama/llama-3.1-8b-instruct` — Meta: Llama 3.1 8B Instruct, `meta-llama/llama-3.3-70b-instruct` — Meta: Llama 3.3 70B Instruct, `meta-llama/llama-4-maverick` — Meta: Llama 4 Maverick, `meta-llama/llama-4-scout` — Meta: Llama 4 Scout, `meta-llama/llama-guard-4-12b` — Meta: Llama Guard 4 12B, `meta-llama/llama-3.1-70b-instruct` — Meta: Llama 3.1 70B Instruct, `meta-llama/llama-3.2-3b-instruct` — Meta: Llama 3.2 3B Instruct, `meta-llama/llama-3.2-1b-instruct` — Meta: Llama 3.2 1B Instruct, `inception/mercury-2.5` — Inception: Mercury 2.5, `inception/mercury-2` — Inception: Mercury 2, `ibm-granite/granite-4.2-8b` — IBM: Granite 4.2 8B, `ibm-granite/granite-4.0-h-micro` — IBM: Granite 4.0 Micro, `amazon/nova-micro-v1` — Amazon: Nova Micro 1.0, `amazon/nova-lite-v1` — Amazon: Nova Lite 1.0, `amazon/nova-2-lite-v1` — Amazon: Nova 2 Lite, `amazon/nova-pro-v1` — Amazon: Nova Pro 1.0, `amazon/nova-premier-v1` — Amazon: Nova Premier 1.0, `thinkingmachines/inkling` — Thinking Machines: Inkling, `thinkingmachines/inkling-small` — Thinking Machines: Inkling Small, `meituan/longcat-2.0` — Meituan: LongCat 2.0, `unbiased/pareto-26.10-preview` — Pareto 26.10 Preview, `unbiased/pareto` — Pareto, `perceptron/perceptron-mk1` — Perceptron: Perceptron Mk1, `perceptron/perceptron-mk1.5` — Perceptron: Perceptron Mk1.5, `bytedance-seed/seed-2.0-lite` — ByteDance Seed: Seed-2.0-Lite, `bytedance-seed/seed-2.0-mini` — ByteDance Seed: Seed-2.0-Mini, `bytedance-seed/seed-1.6-flash` — ByteDance Seed: Seed 1.6 Flash, `bytedance-seed/seed-2-1-turbo` — ByteDance Seed: Seed 2.1 Turbo, `bytedance-seed/seed-1.6` — ByteDance Seed: Seed 1.6, `bytedance-seed/seed-2.0-code` — ByteDance Seed: Seed-2.0-Code, `sao10k/l3-lunaris-8b` — Sao10K: Llama 3 8B Lunaris, `sao10k/l3.1-euryale-70b` — Sao10K: Llama 3.1 Euryale 70B v2.2, `sao10k/l3.3-euryale-70b` — Sao10K: Llama 3.3 Euryale 70B, `fireworks/ember-1` — Fireworks: Ember-1, `nex-agi/nex-n2.5-mini` — Nex AGI: Nex-N2.5-Mini, `nex-agi/nex-n2.5-pro` — Nex AGI: Nex-N2.5-Pro, `aion-labs/aion-3.5` — AionLabs: Aion 3.5, `aion-labs/aion-3.0` — AionLabs: Aion-3.0, `aion-labs/aion-2.0` — AionLabs: Aion-2.0, `aion-labs/aion-3.5-mini` — AionLabs: Aion 3.5 Mini, `aion-labs/aion-3.0-mini` — AionLabs: Aion-3.0-Mini, `aion-labs/aion-rp-llama-3.1-8b` — AionLabs: Aion-RP 1.0 (8B), `perplexity/sonar` — Perplexity: Sonar · native search, `perplexity/sonar-pro` — Perplexity: Sonar Pro · native search, `perplexity/sonar-pro-search` — Perplexity: Sonar Pro Search · native search, `perplexity/sonar-reasoning-pro` — Perplexity: Sonar Reasoning Pro · native search, `perplexity/sonar-deep-research` — Perplexity: Sonar Deep Research · native search, `sakana/fugu-max` — Sakana: Fugu Max · native search, `sakana/fugu-ultra-v2` — Sakana: Fugu Ultra v2 · native search, `sakana/fugu-ultra` — Sakana: Fugu Ultra · native search, `sakana/sakana-namazu` — Sakana: Sakana Namazu · native search, `microsoft/phi-4` — Microsoft: Phi 4, `microsoft/wizardlm-2-8x22b` — WizardLM-2 8x22B, `thedrummer/cydonia-24b-v4.1` — TheDrummer: Cydonia 24B V4.1, `thedrummer/unslopnemo-12b` — TheDrummer: UnslopNemo 12B, `thedrummer/skyfall-36b-v2` — TheDrummer: Skyfall 36B V2, `cognitivecomputations/dolphin-mistral-24b-venice-edition` — Venice: Uncensored, `nousresearch/hermes-3-llama-3.1-70b` — Nous: Hermes 3 70B Instruct, `nousresearch/hermes-4-405b` — Nous: Hermes 4 405B, `nousresearch/hermes-3-llama-3.1-405b` — Nous: Hermes 3 405B Instruct, `cohere/command-a-plus` — Cohere: Command A+, `cohere/command-r7b-12-2024` — Cohere: Command R7B (12-2024), `cohere/command-r-08-2024` — Cohere: Command R (08-2024), `cohere/command-a` — Cohere: Command A, `cohere/command-r-plus-08-2024` — Cohere: Command R+ (08-2024), `arcee-ai/trinity-large-thinking` — Arcee AI: Trinity Large Thinking, `gryphe/mythomax-l2-13b` — MythoMax 13B, `anthracite-org/magnum-v4-72b` — Magnum v4 72B, `inference-net/schematron-v2-turbo` — Inference.net: Schematron V2 Turbo, `inference-net/schematron-v2-small` — Inference.net: Schematron V2 Small, `bytedance/ui-tars-1.5-7b` — ByteDance: UI-TARS 7B , `baidu/ernie-4.5-vl-424b-a47b` — Baidu: ERNIE 4.5 VL 424B A47B , `undi95/remm-slerp-l2-13b` — ReMM SLERP 13B, `prism-ml/ternary-bonsai-2-27b` — PrismML: Ternary Bonsai 2 27B, `morph/morph-v3-fast` — Morph: Morph V3 Fast, `morph/morph-v3-large` — Morph: Morph V3 Large, `writer/palmyra-x5` — Writer: Palmyra X5, `rekaai/reka-flash-3` — Reka Flash 3, `rekaai/reka-edge` — Reka Edge, `relace/relace-apply-3` — Relace: Relace Apply 3, `relace/relace-search` — Relace: Relace Search, `mancer/weaver` — Mancer: Weaver (alpha)
Search mode`search_mode`	`string`	`once`	'Single search' runs exactly one search per node run — predictable cost, works with every model. 'Agentic' lets the model decide whether and how many times to search; it needs a tool-calling model and a cost ceiling. Options: `once` — Single search (deterministic), `agentic` — Agentic (model decides)
Search engine`engine`	`string`	`auto`	'Auto' uses the model's built-in search when it has one and Exa otherwise. 'Built-in' requires a model marked 'native search'. Parallel is the cheapest but returns short excerpts. Options: `auto` — Auto (native, else Exa), `native` — Built into the model, `exa` — Exa, `parallel` — Parallel (cheapest), `perplexity` — Perplexity
Max results`max_results`	`integer`	`5`	Sources to retrieve per search.
Write an answer`synthesize`	`boolean`	`true`	Off: the model writes nothing and only the sources come back, which is cheaper. The sources are returned either way.
Advanced
Excerpt size per source`max_characters`	`integer`	`0`	Characters of page text kept per source. 0 lets the engine choose (~2000-4000). In 'Single search' mode this trims the excerpts after they arrive, so it bounds the output but not the token cost.
Search depth`search_context_size`	`string`	`""`	How much material the search retrieves. This is the only depth control that reaches a model's built-in search (which ignores the excerpt size, and prices per depth tier). For Exa it is a coarse preset — 5K/15K/30K characters per source — that the excerpt size overrides when both are set. Options: — Provider default, `low` — Low, `medium` — Medium, `high` — High
Only these domains`include_domains`	`array<string>`	—	Wildcards and paths allowed: '*.substack.com', 'openai.com/blog'.
Exclude domains`exclude_domains`	`array<string>`	—	Ignored by native OpenAI search; unsupported by native Google search.
System prompt`system_prompt`	`string`	`""`	Extra instructions for how the answer should be written. supports templates
Search results preamble`search_prompt`	`string`	`""`	Replaces the text placed in front of the search results. Single search mode only. supports templates shown when «Search mode» = Single search (deterministic)
Max answer tokens`max_tokens`	`integer`	`0`	0 uses the platform default. Ignored when 'Write an answer' is off.
Max searches`max_searches`	`integer`	`3`	Hard cap on how many searches the model may run. Agentic mode only. shown when «Search mode» = Agentic (model decides)
Your own key (optional)`connection_id`	`string`	`""`	BYO key. Leave empty to use the platform key. connection: openrouter
Stream search progress in Catch`stream_progress_in_catch`	`boolean`	`true`	Show step-by-step progress in the Catch Tool Call stream. shown when «Node mode» = As Tool

Shared fields

Every node has these three — the platform adds them, not the node author.

expose_error_output — When enabled, show an execution output to connect nodes that run if this step fails.
split_ports_in — Show separate execution and data input handles instead of one combined port.
split_ports_out — Show separate execution and data output handles instead of one combined port.

Ready-made examples using this node

An agent that searches the web