All reasoning agents

Self-Consistency

self-consistencyReasoning

Runs the same task num_samples times, independently and in parallel, then hands every answer to an aggregator agent that compares them and returns the answer most of them agree on. Disagreement between samples is a signal that the question is hard or ambiguous; agreement makes the final answer far more reliable than a single run. This is the default reasoning agent type.

Reasoning agents need a Pro or Premium plan. Requests from a free-tier key return 403. See plans

Architecture

How one run moves through the agent

Taskyour promptSample 1independent runSample 2independent runSample Nindependent runAggregator agentmajority voteFinal answerplus every samplenum_samples runs, in parallel
The task fans out to num_samples independent runs in parallel; an aggregator takes a majority vote over their answers.
  1. 1The task is sent to num_samples independent runs of the same model, all at once.
  2. 2Each run reasons through the problem on its own, with no view of the others.
  3. 3An aggregator agent reads every answer and runs a majority vote over them.
  4. 4The response contains the individual samples and the aggregated final answer.

At a glance

swarm_typeself-consistency (alias: consistency-agent)
EndpointPOST /v1/reasoning-agent/completions

Best for

  • Math, logic and word problems with one correct answer
  • Factual questions where a single run might hallucinate
  • Classification and labeling that needs a stable result
  • Decisions where you want a measure of agreement, not one opinion

Parameters

Fields that shape this agent, alongside task, agent_name and description

num_samplesHow many independent answers to generate. 3 to 5 is a good start; each sample is a separate model call.
model_nameModel used for every sample. Defaults to claude-sonnet-5.
system_promptOptional instructions for each sample.
max_loopsLoops per sample. Leave at 1 for most tasks.

Quick start

Get a key, list the reasoning agent types, then run this one. Code examples in cURL, Python, TypeScript, Go and JSON.

1

Get your Swarms API key

Create a key, then export it as SWARMS_API_KEY in your environment.

cloud.swarms.world/api-keys
2

List the reasoning agent types

Returns every supported swarm_type.

List reasoning agent types

curl -X GET 'https://api.swarms.world/v1/reasoning-agent/types' \  -H 'x-api-key: '"$SWARMS_API_KEY"
3

Run the Self-Consistency

Send a task with swarm_type: "self-consistency" to the reasoning agent endpoint.

Run Self-Consistency

curl -X POST 'https://api.swarms.world/v1/reasoning-agent/completions' \  -H 'x-api-key: '"$SWARMS_API_KEY" \  -H 'Content-Type: application/json' \  -d '{  "agent_name": "consistency-solver",  "description": "Answers by majority vote over independent samples.",  "swarm_type": "self-consistency",  "model_name": "gpt-5.5",  "num_samples": 5,  "max_loops": 1,  "task": "If 5 machines take 5 minutes to make 5 widgets, how long would 100 machines take to make 100 widgets? Show your reasoning."}'
4

Read the response

outputs holds the agent's result, and usage reports tokens and the cost of the run.

{  "job_id": "reasoning-agent-…",  "status": "success",  "outputs": "…",  "timestamp": "2026-09-25T12:00:00+00:00",  "agent_name": "consistency-solver",  "agent_type": "self-consistency",  "agent_id": "…",  "usage": {    "input_tokens": 64,    "output_tokens": 1120,    "total_tokens": 1184,    "total_cost": 0.0213  }}

Other reasoning agents

FAQ

What is the Self-Consistency?

Runs the same task num_samples times, independently and in parallel, then hands every answer to an aggregator agent that compares them and returns the answer most of them agree on. Disagreement between samples is a signal that the question is hard or ambiguous; agreement makes the final answer far more reliable than a single run. This is the default reasoning agent type.

How do I run the Self-Consistency with the Swarms API?

POST to https://api.swarms.world/v1/reasoning-agent/completions with "swarm_type" set to "self-consistency" and a task, authenticated with your x-api-key header. "consistency-agent" runs the same agent.

When should I use the Self-Consistency?

It is best for: Math, logic and word problems with one correct answer; Factual questions where a single run might hallucinate; Classification and labeling that needs a stable result; Decisions where you want a measure of agreement, not one opinion.

Which plans can use reasoning agents?

Reasoning agents are a premium endpoint: they need a Pro or Premium plan. A request from a free-tier key returns 403.

How is a reasoning agent run billed?

By tokens, like any other completion. Every sample, loop and evaluation step is a model call, so raising num_samples or max_loops raises the cost. The response reports input, output and total tokens and the total cost.