Telnyx AI Assistants Python

Telnyx AI Assistants - Python

Installation

pip install telnyx

Setup

import os
from telnyx import Telnyx

client = Telnyx(
    api_key=os.environ.get("TELNYX_API_KEY"),  # This is the default and can be omitted
)

All examples below assume client is already initialized as shown above.

Error Handling

All API calls can fail with network errors, rate limits (429), validation errors (422), or authentication errors (401). Always handle errors in production code:

import telnyx

try:
    assistant = client.ai.assistants.create(
        instructions="You are a helpful assistant.",
        name="my-resource",
        model="openai/gpt-4o",
    )
except telnyx.APIConnectionError:
    print("Network error — check connectivity and retry")
except telnyx.RateLimitError:
    import time
    time.sleep(1)  # Check Retry-After header for actual delay
except telnyx.APIStatusError as e:
    print(f"API error {e.status_code}: {e.message}")
    if e.status_code == 422:
        print("Validation error — check required fields and formats")

Common error codes: 401 invalid API key, 403 insufficient permissions, 404 resource not found, 422 validation error (check field formats), 429 rate limited (retry with exponential backoff).

Important Notes

• Phone numbers must be in E.164 format (e.g., +13125550001). Include the + prefix and country code. No spaces, dashes, or parentheses.
• Pagination: List methods return an auto-paginating iterator. Use for item in page_result: to iterate through all pages automatically.
• Model availability varies by account. If a model returns 422 "not available for inference", use client.ai.assistants.list() to discover working models. Commonly available: openai/gpt-4o, Qwen/Qwen3-235B-A22B.

Reference Use Rules

Do not invent Telnyx parameters, enums, response fields, or webhook fields.

• If the parameter, enum, or response field you need is not shown inline in this skill, read references/api-details.md before writing code.
• Before using any operation in ## Additional Operations, read the optional-parameters section and the response-schemas section.

Core Tasks

Create an assistant

Assistant creation is the entrypoint for any AI assistant integration. Agents need the exact creation method and the top-level fields returned by the SDK.

client.ai.assistants.create() — POST /ai/assistants

assistant = client.ai.assistants.create(
    instructions="You are a helpful assistant.",
    name="my-resource",
    model="openai/gpt-4o",
)
print(assistant.id)

Primary response fields:

• assistant.id
• assistant.name
• assistant.model
• assistant.instructions
• assistant.created_at
• assistant.conversation_flow

Chat with an assistant

Chat is the primary runtime path. Agents need the exact assistant method and the response content field.

client.ai.assistants.chat() — POST /ai/assistants/{assistant_id}/chat

response = client.ai.assistants.chat(
    assistant_id="550e8400-e29b-41d4-a716-446655440000",
    content="Tell me a joke about cats",
    conversation_id="42b20469-1215-4a9a-8964-c36f66b406f4",
)
print(response.content)

Primary response fields:

• response.content

Create an assistant test

Test creation is the main validation path for production assistant behavior before deployment.

client.ai.assistants.tests.create() — POST /ai/assistants/tests

assistant_test = client.ai.assistants.tests.create(
    destination="+15551234567",
    instructions="Act as a frustrated customer who received a damaged product. Ask for a refund and escalate if not satisfied with the initial response.",
    name="Customer Support Bot Test",
    rubric=[{
        "criteria": "Assistant responds within 30 seconds",
        "name": "Response Time",
    }, {
        "criteria": "Provides correct product information",
        "name": "Accuracy",
    }],
)
print(assistant_test.test_id)

Primary response fields:

• assistant_test.test_id
• assistant_test.name
• assistant_test.destination
• assistant_test.created_at
• assistant_test.instructions
• assistant_test.description

Important Supporting Operations

Use these when the core tasks above are close to your flow, but you need a common variation or follow-up step.

Get an assistant

Fetch the current state before updating, deleting, or making control-flow decisions.

client.ai.assistants.retrieve() — GET /ai/assistants/{assistant_id}

assistant = client.ai.assistants.retrieve(
    assistant_id="550e8400-e29b-41d4-a716-446655440000",
)
print(assistant.id)

Primary response fields:

• assistant.id
• assistant.name
• assistant.created_at
• assistant.conversation_flow
• assistant.description
• assistant.dynamic_variables

Update an assistant

Create or provision an additional resource when the core tasks do not cover this flow.

client.ai.assistants.update() — POST /ai/assistants/{assistant_id}

assistant = client.ai.assistants.update(
    assistant_id="550e8400-e29b-41d4-a716-446655440000",
)
print(assistant.id)

Primary response fields:

• assistant.id
• assistant.name
• assistant.created_at
• assistant.conversation_flow
• assistant.description
• assistant.dynamic_variables

List assistants

Inspect available resources or choose an existing resource before mutating it.

client.ai.assistants.list() — GET /ai/assistants

assistants_list = client.ai.assistants.list()
print(assistants_list.data)

Response wrapper:

• items: assistants_list.data

Primary item fields:

• id
• name
• created_at
• conversation_flow
• description
• dynamic_variables

Import assistants from external provider

Import existing assistants from an external provider instead of creating from scratch.

client.ai.assistants.imports() — POST /ai/assistants/import

assistants_list = client.ai.assistants.imports(
    api_key_ref="my-openai-key",
    provider="elevenlabs",
)
print(assistants_list.data)

Response wrapper:

• items: assistants_list.data

Primary item fields:

• id
• name
• created_at
• conversation_flow
• description
• dynamic_variables

Get All Tags

Inspect available resources or choose an existing resource before mutating it.

client.ai.assistants.tags.list() — GET /ai/assistants/tags

tags = client.ai.assistants.tags.list()
print(tags.tags)

Primary response fields:

• tags.tags

List assistant tests with pagination

Inspect available resources or choose an existing resource before mutating it.

client.ai.assistants.tests.list() — GET /ai/assistants/tests

page = client.ai.assistants.tests.list()
page = page.data[0]
print(page.test_id)

Response wrapper:

• items: page.data
• pagination: page.meta

Primary item fields:

• name
• created_at
• description
• destination
• instructions
• max_duration_seconds

Get all test suite names

Inspect available resources or choose an existing resource before mutating it.

client.ai.assistants.tests.test_suites.list() — GET /ai/assistants/tests/test-suites

test_suites = client.ai.assistants.tests.test_suites.list()
print(test_suites.data)

Response wrapper:

• items: test_suites.data

Primary item fields:

• data

Get test suite run history

Fetch the current state before updating, deleting, or making control-flow decisions.

client.ai.assistants.tests.test_suites.runs.list() — GET /ai/assistants/tests/test-suites/{suite_name}/runs

page = client.ai.assistants.tests.test_suites.runs.list(
    suite_name="my-test-suite",
)
page = page.data[0]
print(page.run_id)

Response wrapper:

• items: page.data
• pagination: page.meta

Primary item fields:

• status
• created_at
• updated_at
• completed_at
• conversation_id
• conversation_insights_id

Additional Operations

Use the core tasks above first. The operations below are indexed here with exact SDK methods and required params; use references/api-details.md for full optional params, response schemas, and lower-frequency webhook payloads. Before using any operation below, read the optional-parameters section and the response-schemas section so you do not guess missing fields.

For exhaustive optional parameters, full response schemas, and complete webhook payloads, see references/api-details.md.