Tavily Search
tavily/searchAI-optimized web search.. Supports depth control, topic filtering, time range, and optional LLM-generated answer.
- Base price
- $0.08USD / run
- Execution
- sync
- Model type
- api
- Input fields
- 8
Try the model
Playground
Input
The search query.
Depth of search. 'advanced' returns more comprehensive results. Allowed values: basic, advanced.
120
Maximum number of results to return. Range: 1 to 20.
Topic category to focus the search. Allowed values: general, news, finance.
Include an LLM-generated answer summarizing the results.
Include the full raw page content for each result.
Only include results from these domains.
Exclude results from these domains.
OutputReady
Your output will appear here
Complete the inputs, then click Run.
Specifications
Pricing
- Base price
- $0.08 / run
- Billing formula
- 0.08
Context & modalities
- Input
- Schema-defined
- Output
- api
Capabilities
- Chat
- Not supported
- Vision
- Not supported
- Reasoning
- Not supported
- Structured output
- Not supported
- Function calling
- Not supported
- Audio input
- Not supported
Access
- Provider
- Tavily
- Model ID
- tavily/search
- Execution
- sync
- API
- Platform API
- Endpoint
- /v1/api/tavily/search
API README
Tavily Search
AI-optimized web search. Supports depth control, topic filtering, time range, and optional LLM-generated answer. It is suitable for AI-search, research, web-search workflows.
Capability
AI-optimized web search. Supports depth control, topic filtering, time range, and optional LLM-generated answer. It helps applications, agents, and automated workflows turn that capability into repeatable tasks and useful downstream experiences.
Common use cases
- Search and discover relevant records for research, monitoring, and product experiences.
- Create repeatable integrations that pass structured results to downstream business systems.
- Support scheduled jobs, internal tools, and agent workflows with structured results.
Start building
Send your first request
Platform API endpoint with unified authentication and usage tracking.
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
-X POST "https://api.sandbase.ai/v1/api/tavily/search" \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'SANDBASE_JSON'
{
"query": "手性钙钛矿 圆偏振拉曼 手性声子 谱学",
"topic": "general",
"max_results": 8,
"search_depth": "basic",
"include_answer": true,
"include_domains": [
"openai.com"
],
"include_raw_content": false
}
SANDBASE_JSON
)
printf '%s\n' "$result"Choose your model
Compare models
| Model | Context | Input / 1M | Output / 1M | Released |
|---|---|---|---|---|
Tavily SearchThis model Tavily | — | — | — | Jan 1, 2024 |
Tavily | — | — | — | Jan 1, 2024 |
Tavily | — | — | — | Jan 1, 2024 |