The rivano.providers resource manages the LLM backends that the gateway routes traffic to. You can configure multiple providers, test connectivity, and control failover behavior.

List providers

import Rivano from '@rivano/sdk';

const rivano = new Rivano({ apiKey: 'rv_...' });

const { data } = await rivano.providers.list();
for (const provider of data) {
  console.log(`${provider.name} [${provider.isPrimary ? 'primary' : ''}${provider.isFallback ? 'fallback' : ''}]`);
}

import requests

response = requests.get(
    'https://api.rivano.ai/api/providers',
    headers={'Authorization': 'Bearer rv_...'},
)
for p in response.json()['data']:
    print(p['name'], 'primary:', p.get('isPrimary'), 'fallback:', p.get('isFallback'))

curl https://api.rivano.ai/api/providers \
  -H "Authorization: Bearer rv_..."

Create a provider

import Rivano from '@rivano/sdk';

const rivano = new Rivano({ apiKey: 'rv_...' });

const provider = await rivano.providers.create({
  name: 'openai-primary',
  apiKey: 'sk-...',
  isPrimary: true,
  isFallback: false,
  timeoutMs: 30000,
});

console.log('Provider created:', provider.id);

import requests

response = requests.post(
    'https://api.rivano.ai/api/providers',
    headers={
        'Authorization': 'Bearer rv_...',
        'Content-Type': 'application/json',
    },
    json={
        'name': 'openai-primary',
        'apiKey': 'sk-...',
        'isPrimary': True,
        'isFallback': False,
        'timeoutMs': 30000,
    },
)
print(response.json()['id'])

curl https://api.rivano.ai/api/providers \
  -X POST \
  -H "Authorization: Bearer rv_..." \
  -H "Content-Type: application/json" \
  -d '{
    "name": "openai-primary",
    "apiKey": "sk-...",
    "isPrimary": true,
    "timeoutMs": 30000
  }'

Create parameters

Parameter	Type	Required	Description
`name`	`string`	Yes	Provider identifier, used in gateway routing
`apiKey`	`string`	Yes	API key for this provider
`baseUrl`	`string`	No	Override the provider’s base URL (useful for Azure, Ollama)
`isPrimary`	`boolean`	No	Receive traffic when no provider hint is given
`isFallback`	`boolean`	No	Receive traffic when the primary provider fails
`timeoutMs`	`number`	No	Per-request timeout in milliseconds (default: 30000)

💡

Mark one provider as isPrimary: true and another as isFallback: true to get automatic failover with no application code changes.

Test a provider

providers.test() verifies connectivity and returns the list of models the provider exposes:

import Rivano from '@rivano/sdk';

const rivano = new Rivano({ apiKey: 'rv_...' });

const result = await rivano.providers.test('provider_abc123');

if (result.success) {
  console.log('Connected. Available models:');
  for (const model of result.models ?? []) {
    console.log(' ', model);
  }
} else {
  console.error('Provider test failed');
}

import requests

response = requests.post(
    'https://api.rivano.ai/api/providers/provider_abc123/test',
    headers={'Authorization': 'Bearer rv_...'},
)
result = response.json()
if result['success']:
    print('Connected:', result.get('models'))
else:
    print('Failed')

curl https://api.rivano.ai/api/providers/provider_abc123/test \
  -X POST \
  -H "Authorization: Bearer rv_..."

Delete a provider

import Rivano from '@rivano/sdk';

const rivano = new Rivano({ apiKey: 'rv_...' });

await rivano.providers.delete('provider_abc123');

Supported providers

Provider	Name key	Notes
OpenAI	`openai`	GPT-4o, GPT-4-turbo, o1, o3
Anthropic	`anthropic`	Claude 3.x, Claude 4.x
Google	`google`	Gemini 1.5 Pro, Flash, Ultra
Azure OpenAI	`azure`	Requires `baseUrl` with your deployment URL
Amazon Bedrock	`bedrock`	Requires AWS credentials via `baseUrl`
Mistral	`mistral`	Mistral Large, Small
Cohere	`cohere`	Command R, Command R+
Ollama	`ollama`	Local models — set `baseUrl` to your Ollama instance

Error handling

Error	When it occurs
`SdkAuthError`	Invalid Rivano API key
`SdkForbiddenError`	Insufficient permissions
`SdkNotFoundError`	Provider ID does not exist
`SdkError`	Invalid provider config or duplicate name

Gateway Providers — Configure providers in rivano.yaml
Core Concepts — Providers — Provider routing logic
Gateway Configuration — Full gateway config reference

SDK — Providers