Exa Python SDK

The official Python SDK for Exa, the web search API for AI.

Install

pip install exa-py

Requires Python 3.9+

Quick Start

from exa_py import Exa

exa = Exa(api_key="your-api-key")

# Search the web
results = exa.search(
    "blog post about artificial intelligence",
    type="auto",
    contents={"highlights": True}
)

# Ask a question
response = exa.answer("What is the capital of France?")

Search

results = exa.search(
    "machine learning startups",
    contents={"highlights": True}
)

results = exa.search(
    "climate tech news",
    num_results=20,
    start_published_date="2024-01-01",
    include_domains=["techcrunch.com", "wired.com"],
    contents={"highlights": True}
)

results = exa.search(
    "What are the latest battery breakthroughs?",
    type="auto",
    system_prompt="Prefer official sources and avoid duplicate results",
    output_schema={
        "type": "object",
        "properties": {
            "summary": {"type": "string"},
            "key_companies": {"type": "array", "items": {"type": "string"}},
        },
        "required": ["summary", "key_companies"],
    },
)
print(results.output.content if results.output else None)

for chunk in exa.stream_search(
    "What are the latest battery breakthroughs?",
    type="auto",
):
    if chunk.content:
        print(chunk.content, end="", flush=True)

Search output_schema modes:

{"type": "text", "description": "..."}: return plain text in output.content
{"type": "object", ...}: return structured JSON in output.content

system_prompt and output_schema are supported on every search type. Search streaming is available via stream_search(...), which yields OpenAI-style chat completion chunks.

For type: "object", search currently enforces:

max nesting depth: 2
max total properties: 10

Deep search variants that also support additional_queries:

deep-lite
deep
deep-reasoning

results = exa.get_contents(
    ["https://docs.exa.ai"],
    text=True
)

results = exa.get_contents(
    ["https://arxiv.org/abs/2303.08774"],
    highlights=True
)

Answer

response = exa.answer("What caused the 2008 financial crisis?")
print(response.answer)

for chunk in exa.stream_answer("Explain quantum computing"):
    print(chunk, end="", flush=True)

Web Search and Contents tools

Use Exa as a web_search tool in an OpenAI or Anthropic loop. Call web_search() with no arguments to get Exa's recommended settings for agentic search (type="auto" and contents={"highlights": True}).

from exa_py import Exa
from openai import OpenAI

exa = Exa()
openai_client = OpenAI()

messages = [{"role": "user", "content": "What's the latest on AI chips?"}]

completion = openai_client.chat.completions.create(
    model="gpt-5.6",
    messages=messages,
    tools=[exa.openai.web_search()],
)

message = completion.choices[0].message
messages.append(message)
messages += exa.openai.handle_tool_calls(message)

import anthropic

client = anthropic.Anthropic()
response = client.messages.create(
    model="claude-sonnet-4-5",
    max_tokens=1024,
    messages=messages,
    tools=[exa.anthropic.web_search()],
)

Pass name (and optionally description) to rename the tool. Anthropic requires tool names to be unique, so a custom name lets the Exa tool run alongside Anthropic's built-in web_search_20250305 tool:

response = client.messages.create(
    model="claude-sonnet-4-5",
    max_tokens=1024,
    messages=messages,
    tools=[
        exa.anthropic.web_search(name="exa_web_search"),
        {"type": "web_search_20250305", "name": "web_search", "max_uses": 5},
    ],
)

get_contents is available in the same namespaces and lets the model read pages it already has URLs for. It takes a list of URLs and accepts every Exa.get_contents option:

completion = openai_client.chat.completions.create(
    model="gpt-5.6",
    messages=messages,
    tools=[
        exa.openai.web_search(),
        exa.openai.get_contents(summary=True, livecrawl="preferred"),
    ],
)

For the OpenAI Responses API, use exa.openai.responses.web_search() and the same handle_tool_calls helper. The handlers answer every tool call: calls naming a tool they can't resolve get an Error: unknown tool "<name>" output instead of being dropped, so follow-up requests stay valid. If you run other tools alongside Exa's, replace those error outputs with your own results before the next request.

Agent API

The Agent API is available without a beta header.

run = exa.agent.runs.create(
    query="Find engineering leaders at AI infrastructure companies that raised a Series A or B in the last 6 months.",
    output_schema={
        "type": "object",
        "properties": {
            "people": {
                "type": "array",
                "maxItems": 10,
                "items": {
                    "type": "object",
                    "properties": {
                        "name": {"type": "string"},
                        "contact_email": {"type": "string", "format": "email"},
                        "linkedin_url": {"type": "string", "format": "uri"},
                    },
                    "required": ["name", "linkedin_url"],
                },
            }
        },
        "required": ["people"],
    },
    effort="auto",
)

run = exa.agent.runs.poll_until_finished(run.id)
print(run.output.structured if run.output else None)

For Agent Max, use the beta namespace and pass the beta token explicitly:

from exa_py import Exa
from exa_py.agent import AGENT_MAX_EFFORT_BETA

exa = Exa()
run = exa.beta.agent.runs.create(
    query="Find all companies building browser automation tools in the United States.",
    effort="max",
    budget={"maxCostDollars": 10},
    betas=[AGENT_MAX_EFFORT_BETA],
)

Agent Monitors (Beta)

Agent Monitors use the beta namespace and require the AGENT_MONITORS_BETA_HEADER beta identifier (agent-monitors-2026-08-04).

An Agent Monitor keeps a table of entities × fields fresh on a cadence: static fields are answered once per entity over the live web, dynamic fields are tracked from news on every refresh.

from exa_py.agent import AGENT_MONITORS_BETA_HEADER

betas = [AGENT_MONITORS_BETA_HEADER]

# Create a monitor. Creation is async: it returns with status "creating"
# and becomes "active" once the first refresh completes.
monitor = exa.beta.agent.monitors.create(
    betas=betas,
    cadence="7d",
    entities=[
        {"name": "Acme Corp", "domain": "acme.com"},
        {"name": "Globex", "domain": "globex.com"},
    ],
    fields=[
        {"name": "funding", "description": "New funding rounds"},  # dynamic by default
        {"name": "ceo", "description": "The company's current CEO", "mode": "static"},
    ],
    idempotency_key="my-monitor-1",  # safe retries: same key returns the same monitor
)

# Page the monitor's current entities and their contents.
for view in exa.beta.agent.monitors.entities.list_all(monitor.id, betas=betas):
    print(view.entity.name, view.contents)

# Follow the content change feed (resume later from the page's next_cursor).
changes = exa.beta.agent.monitors.changes.list(
    monitor.id,
    betas=betas,
    since="2026-01-01T00:00:00Z",
)

# One-shot stateless snapshot of a past news window — no monitor created.
snapshot = exa.beta.agent.monitors.snapshots.create_and_wait(
    betas=betas,
    entities=[{"name": "Acme Corp", "domain": "acme.com"}],
    fields=[{"name": "funding", "description": "New funding rounds"}],  # dynamic by default
    start_date="2026-01-01",
    end_date="2026-01-08",
)
print(snapshot.data)

# Add entities, inspect refresh progress, clean up.
exa.beta.agent.monitors.entities.add(
    monitor.id,
    betas=betas,
    entities=[{"name": "Initech", "domain": "initech.com"}],
)
current = exa.beta.agent.monitors.get(monitor.id, betas=betas)
print(current.status, current.refresh, current.usage)
exa.beta.agent.monitors.delete(monitor.id, betas=betas)

Async

from exa_py import AsyncExa

exa = AsyncExa(api_key="your-api-key")

results = await exa.search("async search example", contents={"highlights": True})

See the full documentation for all features including websets, filters, and advanced options.

Release files for exa-py 2.20.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for exa-py 2.20.0
File	Size	Uploaded
exa_py-2.20.0.tar.gz	80.0 kB	Sep 1, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for exa-py 2.20.0
File	Interpreter	ABI	Platform	Reset
exa_py-2.20.0-py3-none-any.whl 109.6 kB Sep 1, 2026	Python 3	none	any	Details

Total release size: 189.6 kB

Release files / exa_py-2.20.0.tar.gz

Download URL	exa_py-2.20.0.tar.gz
Size	80.0 kB
Tags	Source
SHA-256 checksum How to use checksums	`e7c6d80c91fcb192a53e4615f032f15fd50352fec1825535222e5c9b4f1fda78`
BLAKE2b-256 checksum How to use checksums	`d93d112afb07944b357c3b6e37e63639a2d6d7178edaf486e87f7f0f70d92694`
Upload date	Sep 1, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/6.1.0 CPython/3.12.9`

Release files / exa_py-2.20.0-py3-none-any.whl

Download URL	exa_py-2.20.0-py3-none-any.whl
Size	109.6 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`5a61decaa2d8d6124938c9f86b89ff53b6f4d8b11bf24ddf83fcca76c11c26b2`
BLAKE2b-256 checksum How to use checksums	`15e10de5407121dcef075567d2f352dd0f268c7c21eedd402a75bf2b747b19f6`
Upload date	Sep 1, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/6.1.0 CPython/3.12.9`