Swarms Logo
Production multi-agent infrastructure

Swarms API

The only API for orchestrating multi-agent systems at production scale.

15+
Multi-agent architectures
1,000+
Models supported
500+
Agents per API request
<1ms
Agent init time

Capabilities

Everything you need to ship agents in production

A complete multi-agent stack — orchestration, memory, tooling, and observability — behind one API.

Multi-agent orchestration

Sequential, concurrent, hierarchical, group-chat and custom topologies — handled by the runtime, not your code.

Shared memory

Persistent, scoped memory across agents so swarms can collaborate, branch, and reason over long horizons.

Pre-built tools

Web search, scraping, finance, document processing, code execution and dozens more — ready out of the box.

1,000+ models

OpenAI, Anthropic, Gemini, Groq, open-weight providers and hundreds more behind a single interface.

MCP protocol

Connect Notion, Supabase, GitHub or any internal system through the Model Context Protocol.

Streaming responses

Token-by-token streaming for low-latency UX and live progress on long-running swarm executions.

Rust runtime

Sub-millisecond initialization and zero-copy message passing built on a Rust-optimized core.

Enterprise infrastructure

Multi-region deployment, fault-tolerant retries, SOC 2 controls and encrypted transport by default.

Telemetry & logs

Per-agent traces, token accounting, latency metrics and structured logs for full observability.

Quickstart

Your first agent in three lines.

Sign up, drop in your API key, and call /v1/agent/completions. No infrastructure to provision.

Generate an API key on the platform

Install the SDK or call the REST endpoint

Run agents — we handle the runtime

agent.py
import os
import requests

response = requests.post(
    "https://api.swarms.world/v1/agent/completions",
    headers={"x-api-key": os.environ["SWARMS_API_KEY"]},
    json={
        "agent_config": {
            "agent_name": "Research Analyst",
            "system_prompt": "You are a senior research analyst.",
            "model_name": "gpt-4o",
            "max_tokens": 8192,
            "temperature": 0.5,
        },
        "task": "Summarize the state of multi-agent AI in 2025.",
    },
)

print(response.json())

Multi-agent

One request. A whole swarm.

Describe the topology and the agents — Swarms handles routing, memory, and aggregation.

swarm.py
import os
from swarms_client import SwarmsClient

client = SwarmsClient(api_key=os.environ["SWARMS_API_KEY"])

response = client.swarms.run(
    name="Medical Analysis Swarm",
    description="Analyzes symptoms and recommends ICD codes",
    swarm_type="ConcurrentWorkflow",
    task="45-year-old female with chest pain. Analyze and provide ICD codes.",
    agents=[
        {
            "agent_name": "Symptom Analyzer",
            "system_prompt": "You analyze patient symptoms and surface key indicators.",
            "model_name": "gpt-4o",
            "temperature": 0.3,
        },
        {
            "agent_name": "ICD Code Specialist",
            "system_prompt": "You map symptoms to ICD codes with rationale.",
            "model_name": "gpt-4o",
            "temperature": 0.2,
        },
    ],
)

print(response)

Available swarm topologies

SequentialWorkflowConcurrentWorkflowHierarchicalSwarmMixtureOfAgentsGroupChatMajorityVotingAgentRearrangeMultiAgentRouterAutoSwarmBuilderHeavySwarmDebateWithJudgeRoundRobinPlannerWorkerSwarmCouncilAsAJudgeBatchedGridWorkflowauto

Pricing

Start free. Scale when you ship.

Generous free tier. Predictable team pricing. On-premise and enterprise when you need them.

Free

Get started with AI. No fees — perfect for prototyping.

$0

Pay only for what you use

  • 100 requests / minute
  • 1,200 requests / day
  • 200K tokens per agent
  • 10 agents per batch
  • Community support
Get API key

Pro

For professionals who need more power and features.

$19.99

per month

  • Higher rate limits than Free
  • Pay-as-you-go usage credits
  • Priority queue access
  • Email support
  • All standard features
Upgrade to Pro
Most popular

Premium

Production workloads with priority access.

$100

per month · or $1,020/yr (save 15%)

  • 2,000 requests / minute
  • 100,000 requests / day
  • 2M tokens per agent
  • 500 agents per batch
  • Priority availability zones
  • 24/7 email & Discord support
Upgrade to Premium

Enterprise

Dedicated infrastructure, on-premise, and SLAs.

Custom

Tailored to your scale

  • Custom rate limits
  • Dedicated capacity
  • On-premise deployment available
  • Custom SLAs & integration support
  • White-label options
Talk to sales

FAQ

Common questions

Swarms is the only API purpose-built for orchestrating many agents in one request. You describe the topology, the agents, and the task — the runtime handles routing, memory, retries, and aggregation. You ship multi-agent workflows in minutes instead of building the plumbing yourself.
1,000+ models including OpenAI (GPT-4o, o-series), Anthropic (Claude), Google (Gemini), Groq, and a long tail of open-weight providers. You pass a model_name per agent — each agent in a swarm can use a different model.
Yes. The Free tier covers 100 req/min and 1,200 req/day with no card required. Upgrade to Pro or Premium any time from your platform subscription page — your existing API key is preserved and the new limits apply immediately with no downtime.
Pick a swarm_type (SequentialWorkflow, ConcurrentWorkflow, HierarchicalSwarm, MixtureOfAgents, GroupChat, and more), pass a list of agent configs and a task. The runtime instantiates each agent on a Rust core, shares memory according to the topology, and returns the aggregated result.
Yes. On-premise is available under our Enterprise tier — full stack as Docker images, source access, unlimited usage, and an enterprise license with priority updates. Ideal for regulated environments and data-sovereignty requirements. Contact sales to scope a deployment.
You'll receive HTTP 429 with retry-after headers. Premium tiers raise the ceiling 20×; Enterprise removes it entirely. The SDKs include automatic retry with exponential backoff.
Encrypted transport, scoped API keys, audit logging, multi-region redundancy, and SOC 2 controls. On-Premise deployments give you full control of keys, data, and the security boundary.

Ready to ship a swarm?

Generate an API key in under a minute. Run your first multi-agent workflow before your coffee gets cold.