Testing

Integration testing without surprises

Test with the same settings as production. Free playground testing so you can ship with confidence.

Testing mode mirrors prod Free playground runs Structured output samples Provider billing applies

Visual

Testing flow at a glance

From test request to production-configured playground output.

01

Test request

From staging, CLI, or playground

02

Production config applied

Same routing, limits as prod

03

Free playground execution

No charges, provider usage applies

04

Validate structured output

Test schemas before production

05

Ship with confidence

Same config, now for real users

Live testing config
workflow: "testing_review"
mode: "testing"
playground_cost: "free_on_modelriver"
logging: "not_logged"
provider_usage: "billed_by_provider"
schema: "book_review_schema"
              
1

Match production behavior

Same routing, limits, and structured outputs as live traffic.

2

Test for free in playground

ModelRiver covers playground requests; provider billing still applies.

3

Validate structured outputs

Use schemas and samples to verify shape, tool calls, and safety gates.

Playground cost

Free on us

We cover playground requests; provider usage remains billable.

Config parity

Matches prod

Testing mode runs the exact production configuration and limits.

Output confidence

Schema-first

Validate against provided schemas before releasing to customers.

Scroll the playbook

01 · Prepare

Mirror production configs in testing mode with the same providers.

02 · Exercise

Run test requests through the production-configured playground for free.

03 · Validate

Check structured outputs, schemas, and tool calls before rollout.

04 · Promote

Flip to production users with the same config you tested.

When to use

  • Before promoting new workflows or tools to production traffic.
  • Validating structured outputs and tool calls against schemas.
  • Teams wanting parity with production limits without touching user quota.

What you get

  • Testing mode that mirrors production routing, limits, and retries.
  • Free, not-logged playground runs; provider usage still applies.
  • Schema-first validation to ensure outputs land exactly as expected.

Test Mode workflows

Switch workflows to Testing mode in the console

POST https://api.modelriver.com/v1/ai
Authorization: Bearer mr_live_your_key

{
  "workflow": "product-extractor-test",
  "messages": [...]
}

// Test mode returns sample data from your structured output:
{
  "data": { /* sample data */ },
  "meta": {
    "test_mode": true,
    "provider": "Testing"
  }
}

No AI providers are called. Sample data from structured outputs is returned instantly. Perfect for integration testing and CI/CD.

Ship tested workflows with confidence

Use testing mode plus the production-configured playground to validate outputs, then roll forward knowing nothing changes for real users.