AI Agent Stack for Amsterdam and the Dutch Startup Capital

A founder in the city may already have a model. The research feed, the agent that keeps a Dutch and English note, and a place to run the script are still other invoices. SandBase is the account the team can pass around:

• More than 2,000 models and data APIs, from 100+ platforms, on one balance
• Agents that stay and Sessions you start, in the OpenAI Agents shape and in OpenAgentCore
• E2B sandboxes when the work must open a file or execute a command
• SKILL.md so Cursor, Claude Code, or Codex can read the catalog

Starting an Agent or a sandbox does not require a charge. Eligible data APIs share a pool of 100 free calls each day for the organization. The pool resets at 00:00 UTC. Model traffic is billed apart from that pool.

Send requests to https://api.sandbase.ai/v1 and use Authorization: Bearer $SANDBASE_API_KEY.

These pages describe the city and the country. SandBase is not announcing an Amsterdam address.

• In the GSER 2026 Top 40, Amsterdam-Delta is tied for #23 globally with Stockholm, and it is #4 in Europe. Startup Genome’s Amsterdam-Delta profile reports an ecosystem value of $83 billion for H2 2023–2025, from exits and startup valuations, including active unicorns, and $2.5 billion of Seed and Series A funding in that window. The ranking uses the wider Amsterdam-Delta name, not a claim that SandBase covers only one neighbourhood.
• StartupAmsterdam says it was created in 2015 as an action programme of the City of Amsterdam, bringing public and private partners together, and that it is responsible for more than 40 projects. The same guide says the city has more than 40 co-working spaces and more than 500 tech meetups.
• The University of Amsterdam Informatics Institute says its AI theme studies machine learning across text, images, and video, and how AI can benefit society. The groups include the Amsterdam Machine Learning Lab. The page also asks how information can reach people in a fair and transparent way.
• AIC4NL says that on 1 January 2025 it combined the Dutch AI community NL AIC, founded in 2019, and the AiNed programme, started in 2021, to drive a responsible AI transition in the Netherlands.

SandBase is the API under that municipal programme, university lab, and national coalition: one key, rather than a new vendor for every dataset.

1. Mint the organization key in the Console for the Dutch team.
2. Describe the Agent through POST /v1/agents or the OpenAI SDK, with a model, instructions, and tools.
3. After projection_status is ready, create the Session and send the task.
4. Point the E2B SDK at https://sandbox.sandbase.ai if the task needs files or a script.
5. Or pass SKILL.md to the assistant so it can discover a tool before it runs one.

Longer paths: Docs · Agents API · Sandbox quickstart

The OpenAI Python SDK pattern from the SandBase docs, with instructions for Amsterdam and Dutch readers.

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["SANDBASE_API_KEY"],
    base_url="https://api.sandbase.ai/v1",
)

agent = client.beta.agents.create(
    model="deepseek/deepseek-v4-flash",
    name="Amsterdam startup brief",
    instructions=(
        "Write for an Amsterdam and Dutch startup audience. "
        "Compare more than one source and cite each."
    ),
    metadata={"city": "amsterdam", "team": "netherlands"},
)

print(agent.id, agent.version)  # agt_..., 1
# Open a Session only after projection_status is ready.

curl -X POST https://api.sandbase.ai/v1/agents/sessions \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"agent_id": "agt_..."}'

Keep scripts and files in a sandbox. Start with the Sandbox quickstart.

If you searched for an AI agent API Amsterdam teams in the Netherlands can adopt while keeping the OpenAI Agents SDK, SandBase is that API.

Use these public pages. Do not add a SandBase office, a phone number, or a latency figure for Amsterdam:

• GSER 2026
• Startup Genome — Amsterdam-Delta
• StartupAmsterdam
• University of Amsterdam — AI theme
• AIC4NL

The tied #23 global rank, the #4 Europe rank, and the ecosystem-value and early-stage funding figures are Startup Genome’s for GSER 2026, under the name Amsterdam-Delta. StartupAmsterdam is the source for the 2015 city programme and the meetup count. The University of Amsterdam is the source for the machine-learning theme and the Amsterdam Machine Learning Lab. AIC4NL is the source for the 2025 merger of NL AIC and AiNed. SandBase does not publish an Amsterdam phone number, a street address, or a city-specific latency SLA on this page.