Text to speech | Respan Docs

You could use Respan’s unified LLM API to call Text-to-speech model to turn text into lifelike spoken audio.

Respan now supports tts-1 and tts-1-hd models from OpenAI.

Model	Description
`tts-1`	OpenAI latest text to speech model, optimized for speed.
`tts-1-hd`	OpenAI latest text to speech model, optimized for quality.

Integration steps:

Go to OpenAI API plaform to get your OpenAI API key.

You should add your OpenAI’s API key on Respan credentials page.

OpenAI Python

1 from openai import OpenAI
2 
3 client = OpenAI(
4     base_url="https://api.respan.ai/api/",
5     api_key="YOUR_RESPAN_API_KEY",
6 )
7 
8 response = client.audio.speech.create(
9     model="tts-1", # or "tts-1-hd"
10     voice="alloy",
11     input="Today is a wonderful day to build something people love!",
12     extra_body={"customer_identifier": "customer_11"}  # All Respan parameters are supported
13 )

OpenAI TypeScript

1 const speechFile = path.resolve("./speech.mp3");
2 
3 const openai = new OpenAI({
4   baseURL: "https://api.respan.ai/api/",
5   apiKey: "YOUR_RESPAN_API_KEY",
6 });
7 
8 const mp3 = await openai.audio.speech.create({
9   model: "tts-1", // or "tts-1-hd"
10   voice: "alloy",
11   input: "Today is a wonderful day to build something people love!",
12   extra_body: { customer_identifier: "customer_11" } // All Respan parameters are supported
13 });

Python

1 def demo_call(input, 
2               model="tts-1",
3               voice="alloy",
4               token="YOUR_RESPAN_API_KEY",
5               ):
6     headers = {
7         'Content-Type': 'application/json',
8         'Authorization': f'Bearer {token}',
9     }
10 
11     data = {
12         'model': model,
13         'input': input,
14         'voice': voice,
15         'customer_identifier': "customer_11"
16     }
17 
18     response = requests.post('https://api.respan.ai/api/audio/speech', headers=headers, json=data)
19     return response
20 
21 messages = "Today is a wonderful day to build something people love!"
22 print(demo_call(messages).json())

TypeScript

1 // Define the function with TypeScript
2 fetch('https://api.respan.ai/api/audio/speech', {
3   method: 'POST',
4   headers: {
5     'Content-Type': 'application/json',
6     'Authorization': 'Bearer YOUR_RESPAN_API_KEY'
7   },
8     body: JSON.stringify({
9         model: 'tts-1',
10         input: "Today is a wonderful day to build something people love!"
11         voice: "alloy",
12         customer_identifier: "customer_11"
13     })
14 })
15 .then(response => response.json())
16 .then(data => console.log(data));

OpenAI parameters

model string required: The model to use. It should be one of tts-1 or tts-1-hd.
input string required: The text to generate audio for. The maximum length is 4096 characters.
voice string required: The voice to use when generating the audio. Supported voices are alloy, echo, fable, onyx, nova, and shimmer. Previews of the voices are available in the OpenAI’s Text to speech guide.
response_format string: The format to audio in. Supported formats are mp3, opus, aac, flac, wav, and pcm.
speed Number: The speed of the generated audio. Select a value from 0.25 to 4.0. 1.0 is the default.

Respan parameters

See how to make a standard Respan API call in the Quick Start guide.

Generation parameters

customer_credentials object: You can pass in your customer’s credentials for supported providers and use their credits when our proxy is calling models from those providers.
See details here

Example

1 "customer_credentials": {
2 
3   "openai": {
4     "api_key": "YOUR_OPENAI_API_KEY",
5   }
6 }

disable_log boolean: When set to true, only the request and performance metrics will be recorded, input and output messages will be omitted from the log.

Observability parameters

metadata dict: You can add any key-value pair to this metadata field for your reference. Check the details of metadata here.

Contact team@respan.ai if you need extra parameter support for your use case.

Example

1 {
2   "my_value_key": "my_value"
3 }

customer_identifier string: Use this as a tag to identify the user associated with the API call. See the details of customer identifier here.

Example

1 {
2     //...other_params,
3     "customer_identifier": "user_123"
4 }

customer_email string: This is the email address of the user associated with the API call. You can add your corresponding user’s email address to the request.

You could also edit customer’s emails on the platform. Check the details of user editing here.

Example

1 {
2     //...other_params,
3     "customer_email": "hendrix@respan.ai"
4 }

thread_identifier string: See spans as a conversation thread. Pass all spans with the same thread_identifier to see them in the same thread.

Example

1 {
2     //...other_params,
3     "thread_identifier": "test_thread"
4 }

request_breakdown boolean: Adding this returns the summarization of the response in the response body. If streaming is on, the metrics will be streamed as the last chunk.

Properties

Regular Response

1 {
2   "id": "chatcmpl-7476cf3f-fcc9-4902-a548-a12489856d8a",
3   //... main part of the response body ...
4   "request_breakdown": {
5     "prompt_tokens": 6,
6     "completion_tokens": 9,
7     "cost": 4.8e-5,
8     "prompt_messages": [
9       {
10         "role": "user",
11         "content": "How are you doing today?"
12       }
13     ],
14     "completion_message": {
15       "content": " I'm doing well, thanks for asking!",
16       "role": "assistant"
17     },
18     "model": "claude-2",
19     "cached": false,
20     "timestamp": "2024-02-20T01:23:39.329729Z",
21     "status_code": 200,
22     "stream": false,
23     "latency": 1.8415491580963135,
24     "scores": {},
25     "category": "Questions",
26     "metadata": {},
27     "routing_time": 0.18612787732854486,
28     "full_request": {
29       "messages": [
30         {
31           "role": "user",
32           "content": "How are you doing today?"
33         }
34       ],
35       "model": "claude-2",
36       "logprobs": true
37     },
38     "sentiment_score": 0
39   }
40 }

Streaming Response

1 //... other chunks ...
2 // The following is the last chunk
3 {
4   "id": "request_breakdown",
5   "choices": [
6     {
7       "delta": { "content": null, "role": "assistant" },
8       "finish_reason": "stop",
9       "request_breakdown": {
10         "prompt_tokens": 6,
11         "completion_tokens": 9,
12         "cost": 4.8e-5, //  In usd
13         "prompt_messages": [
14           {
15             "role": "user",
16             "content": "How are you doing today?"
17           }
18         ],
19         "completion_message": {
20           "content": " I'm doing well, thanks for asking!",
21           "role": "assistant"
22         },
23         "model": "claude-2",
24         "cached": false,
25         "timestamp": "2024-02-20T01:23:39.329729Z",
26         "status_code": 200,
27         "stream": false,
28         "latency": 1.8415491580963135, // in seconds
29         "scores": {},
30         "category": "Questions",
31         "metadata": {},
32         "routing_time": 0.18612787732854486, // in seconds
33         "full_request": {
34           "messages": [
35             {
36               "role": "user",
37               "content": "How are you doing today?"
38             }
39           ],
40           "model": "claude-2",
41           "logprobs": true
42         },
43         "sentiment_score": 0
44       },
45       "index": 0,
46       "message": { "content": null, "role": "assistant" }
47     }
48   ],
49   "created": 1706100589,
50   "model": "extra_parameter",
51   "object": "chat.completion.chunk",
52   "system_fingerprint": null,
53   "usage": {}
54 }

You could use Respan's unified LLM API to call Text-to-speech model to turn text into lifelike spoken audio. Respan now supports `tts-1` and `tts-1-hd` models from OpenAI. | Model | Description | | -------- | ------------------------------------- | |`tts-1` | OpenAI latest text to speech model, optimized for speed. | |`tts-1-hd` |OpenAI latest text to speech model, optimized for quality. | ## Integration steps: Go to [OpenAI API plaform](https://platform.openai.com/api-keys) to get your OpenAI API key. You should add your OpenAI's API key on [Respan credentials page](https://platform.respan.ai/platform/api/providers). <img height="200" width="500" src="https://keywordsai-static.s3.us-east-1.amazonaws.com/docs/settings/providers.jpg"/> ```Python OpenAI Python from openai import OpenAI client = OpenAI( base_url="https://api.respan.ai/api/", api_key="YOUR_RESPAN_API_KEY", ) response = client.audio.speech.create( model="tts-1", # or "tts-1-hd" voice="alloy", input="Today is a wonderful day to build something people love!", extra_body={"customer_identifier": "customer_11"} # All Respan parameters are supported ) ``` ```TypeScript OpenAI TypeScript const speechFile = path.resolve("./speech.mp3"); const openai = new OpenAI({ baseURL: "https://api.respan.ai/api/", apiKey: "YOUR_RESPAN_API_KEY", }); const mp3 = await openai.audio.speech.create({ model: "tts-1", // or "tts-1-hd" voice: "alloy", input: "Today is a wonderful day to build something people love!", extra_body: { customer_identifier: "customer_11" } // All Respan parameters are supported }); ``` ```python Python def demo_call(input, model="tts-1", voice="alloy", token="YOUR_RESPAN_API_KEY", ): headers = { 'Content-Type': 'application/json', 'Authorization': f'Bearer {token}', } data = { 'model': model, 'input': input, 'voice': voice, 'customer_identifier': "customer_11" } response = requests.post('https://api.respan.ai/api/audio/speech', headers=headers, json=data) return response messages = "Today is a wonderful day to build something people love!" print(demo_call(messages).json()) ``` ```TypeScript TypeScript // Define the function with TypeScript fetch('https://api.respan.ai/api/audio/speech', { method: 'POST', headers: { 'Content-Type': 'application/json', 'Authorization': 'Bearer YOUR_RESPAN_API_KEY' }, body: JSON.stringify({ model: 'tts-1', input: "Today is a wonderful day to build something people love!" voice: "alloy", customer_identifier: "customer_11" }) }) .then(response => response.json()) .then(data => console.log(data)); ``` ## OpenAI parameters - `model` *string* **required**: The model to use. It should be one of `tts-1` or `tts-1-hd`. - `input` *string* **required**: The text to generate audio for. The maximum length is 4096 characters. - `voice` *string* **required**: The voice to use when generating the audio. Supported voices are `alloy`, `echo`, `fable`, `onyx`, `nova`, and `shimmer`. Previews of the voices are available in the OpenAI's [Text to speech guide.](https://platform.openai.com/docs/guides/text-to-speech/voice-options) - `response_format` *string*: The format to audio in. Supported formats are `mp3`, `opus`, `aac`, `flac`, `wav`, and `pcm`. - `speed` *Number*: The speed of the generated audio. Select a value from 0.25 to 4.0. 1.0 is the default. ## Respan parameters See how to make a standard Respan API call in the [Quick Start](/documentation/features/gateway/gateway-quickstart) guide. ### Generation parameters - `customer_credentials` *object*: You can pass in your customer's credentials for [supported providers](/integrations/overview/overview) and use their credits when our proxy is calling models from those providers. <br/>See details [here](/documentation/admin/llm-provider-keys) **Example** ```json "customer_credentials": { "openai": { "api_key": "YOUR_OPENAI_API_KEY", } } ``` - `disable_log` *boolean*: When set to true, only the request and [performance metrics](/documentation/features/monitoring/metrics) will be recorded, input and output messages will be omitted from the log. ### Observability parameters - `metadata` *dict*: You can add any key-value pair to this metadata field for your reference. Check the [details of metadata here.](/documentation/features/tracing/spans/span-fields-parameters#custom-properties) Contact team@respan.ai if you need extra parameter support for your use case. **Example** ```json { "my_value_key": "my_value" } ``` - `customer_identifier` *string*: Use this as a tag to identify the user associated with the API call. See the [details of customer identifier here.](/documentation/features/user-analytics/customer-identifier) **Example** ```json { //...other_params, "customer_identifier": "user_123" } ``` - `customer_email` *string*: This is the email address of the user associated with the API call. You can add your corresponding user's email address to the request. You could also edit customer's emails on the platform. Check the [details of user editing here.](/api-reference/observe/users/update-user) **Example** ```json { //...other_params, "customer_email": "hendrix@respan.ai" } ``` - `thread_identifier` *string*: See spans as a conversation thread. Pass all spans with the same `thread_identifier` to see them in the same thread. **Example** ```json { //...other_params, "thread_identifier": "test_thread" } ``` - `request_breakdown` *boolean*: Adding this returns the summarization of the response in the response body. If streaming is on, the metrics will be streamed as the last chunk. **Properties** ```json Regular Response { "id": "chatcmpl-7476cf3f-fcc9-4902-a548-a12489856d8a", //... main part of the response body ... "request_breakdown": { "prompt_tokens": 6, "completion_tokens": 9, "cost": 4.8e-5, "prompt_messages": [ { "role": "user", "content": "How are you doing today?" } ], "completion_message": { "content": " I'm doing well, thanks for asking!", "role": "assistant" }, "model": "claude-2", "cached": false, "timestamp": "2024-02-20T01:23:39.329729Z", "status_code": 200, "stream": false, "latency": 1.8415491580963135, "scores": {}, "category": "Questions", "metadata": {}, "routing_time": 0.18612787732854486, "full_request": { "messages": [ { "role": "user", "content": "How are you doing today?" } ], "model": "claude-2", "logprobs": true }, "sentiment_score": 0 } } ``` ```json Streaming Response //... other chunks ... // The following is the last chunk { "id": "request_breakdown", "choices": [ { "delta": { "content": null, "role": "assistant" }, "finish_reason": "stop", "request_breakdown": { "prompt_tokens": 6, "completion_tokens": 9, "cost": 4.8e-5, // In usd "prompt_messages": [ { "role": "user", "content": "How are you doing today?" } ], "completion_message": { "content": " I'm doing well, thanks for asking!", "role": "assistant" }, "model": "claude-2", "cached": false, "timestamp": "2024-02-20T01:23:39.329729Z", "status_code": 200, "stream": false, "latency": 1.8415491580963135, // in seconds "scores": {}, "category": "Questions", "metadata": {}, "routing_time": 0.18612787732854486, // in seconds "full_request": { "messages": [ { "role": "user", "content": "How are you doing today?" } ], "model": "claude-2", "logprobs": true }, "sentiment_score": 0 }, "index": 0, "message": { "content": null, "role": "assistant" } } ], "created": 1706100589, "model": "extra_parameter", "object": "chat.completion.chunk", "system_fingerprint": null, "usage": {} } ```

Authentication

AuthorizationBearer

API key authentication. Get your API key from https://platform.respan.ai/platform/api-keys

Request

This endpoint expects an object.

Response

Successful response for Text to speech

my_value_keystring

Errors

401

Unauthorized Error

You could use Respan’s unified LLM API to call Text-to-speech model to turn text into lifelike spoken audio.

Respan now supports tts-1 and tts-1-hd models from OpenAI.

Model	Description
`tts-1`	OpenAI latest text to speech model, optimized for speed.
`tts-1-hd`	OpenAI latest text to speech model, optimized for quality.

Integration steps:

Go to OpenAI API plaform to get your OpenAI API key.

You should add your OpenAI’s API key on Respan credentials page.

OpenAI Python

1 from openai import OpenAI
2 
3 client = OpenAI(
4     base_url="https://api.respan.ai/api/",
5     api_key="YOUR_RESPAN_API_KEY",
6 )
7 
8 response = client.audio.speech.create(
9     model="tts-1", # or "tts-1-hd"
10     voice="alloy",
11     input="Today is a wonderful day to build something people love!",
12     extra_body={"customer_identifier": "customer_11"}  # All Respan parameters are supported
13 )

OpenAI TypeScript

1 const speechFile = path.resolve("./speech.mp3");
2 
3 const openai = new OpenAI({
4   baseURL: "https://api.respan.ai/api/",
5   apiKey: "YOUR_RESPAN_API_KEY",
6 });
7 
8 const mp3 = await openai.audio.speech.create({
9   model: "tts-1", // or "tts-1-hd"
10   voice: "alloy",
11   input: "Today is a wonderful day to build something people love!",
12   extra_body: { customer_identifier: "customer_11" } // All Respan parameters are supported
13 });

Python

1 def demo_call(input, 
2               model="tts-1",
3               voice="alloy",
4               token="YOUR_RESPAN_API_KEY",
5               ):
6     headers = {
7         'Content-Type': 'application/json',
8         'Authorization': f'Bearer {token}',
9     }
10 
11     data = {
12         'model': model,
13         'input': input,
14         'voice': voice,
15         'customer_identifier': "customer_11"
16     }
17 
18     response = requests.post('https://api.respan.ai/api/audio/speech', headers=headers, json=data)
19     return response
20 
21 messages = "Today is a wonderful day to build something people love!"
22 print(demo_call(messages).json())

TypeScript

1 // Define the function with TypeScript
2 fetch('https://api.respan.ai/api/audio/speech', {
3   method: 'POST',
4   headers: {
5     'Content-Type': 'application/json',
6     'Authorization': 'Bearer YOUR_RESPAN_API_KEY'
7   },
8     body: JSON.stringify({
9         model: 'tts-1',
10         input: "Today is a wonderful day to build something people love!"
11         voice: "alloy",
12         customer_identifier: "customer_11"
13     })
14 })
15 .then(response => response.json())
16 .then(data => console.log(data));

OpenAI parameters

model string required: The model to use. It should be one of tts-1 or tts-1-hd.
input string required: The text to generate audio for. The maximum length is 4096 characters.
voice string required: The voice to use when generating the audio. Supported voices are alloy, echo, fable, onyx, nova, and shimmer. Previews of the voices are available in the OpenAI’s Text to speech guide.
response_format string: The format to audio in. Supported formats are mp3, opus, aac, flac, wav, and pcm.
speed Number: The speed of the generated audio. Select a value from 0.25 to 4.0. 1.0 is the default.

Respan parameters

See how to make a standard Respan API call in the Quick Start guide.

Generation parameters

customer_credentials object: You can pass in your customer’s credentials for supported providers and use their credits when our proxy is calling models from those providers.
See details here

Example

1 "customer_credentials": {
2 
3   "openai": {
4     "api_key": "YOUR_OPENAI_API_KEY",
5   }
6 }

disable_log boolean: When set to true, only the request and performance metrics will be recorded, input and output messages will be omitted from the log.

Observability parameters

metadata dict: You can add any key-value pair to this metadata field for your reference. Check the details of metadata here.

Contact team@respan.ai if you need extra parameter support for your use case.

Example

1 {
2   "my_value_key": "my_value"
3 }

customer_identifier string: Use this as a tag to identify the user associated with the API call. See the details of customer identifier here.

Example

1 {
2     //...other_params,
3     "customer_identifier": "user_123"
4 }

customer_email string: This is the email address of the user associated with the API call. You can add your corresponding user’s email address to the request.

You could also edit customer’s emails on the platform. Check the details of user editing here.

Example

1 {
2     //...other_params,
3     "customer_email": "hendrix@respan.ai"
4 }

thread_identifier string: See spans as a conversation thread. Pass all spans with the same thread_identifier to see them in the same thread.

Example

1 {
2     //...other_params,
3     "thread_identifier": "test_thread"
4 }

request_breakdown boolean: Adding this returns the summarization of the response in the response body. If streaming is on, the metrics will be streamed as the last chunk.

Properties

Regular Response

1 {
2   "id": "chatcmpl-7476cf3f-fcc9-4902-a548-a12489856d8a",
3   //... main part of the response body ...
4   "request_breakdown": {
5     "prompt_tokens": 6,
6     "completion_tokens": 9,
7     "cost": 4.8e-5,
8     "prompt_messages": [
9       {
10         "role": "user",
11         "content": "How are you doing today?"
12       }
13     ],
14     "completion_message": {
15       "content": " I'm doing well, thanks for asking!",
16       "role": "assistant"
17     },
18     "model": "claude-2",
19     "cached": false,
20     "timestamp": "2024-02-20T01:23:39.329729Z",
21     "status_code": 200,
22     "stream": false,
23     "latency": 1.8415491580963135,
24     "scores": {},
25     "category": "Questions",
26     "metadata": {},
27     "routing_time": 0.18612787732854486,
28     "full_request": {
29       "messages": [
30         {
31           "role": "user",
32           "content": "How are you doing today?"
33         }
34       ],
35       "model": "claude-2",
36       "logprobs": true
37     },
38     "sentiment_score": 0
39   }
40 }

Streaming Response

1 //... other chunks ...
2 // The following is the last chunk
3 {
4   "id": "request_breakdown",
5   "choices": [
6     {
7       "delta": { "content": null, "role": "assistant" },
8       "finish_reason": "stop",
9       "request_breakdown": {
10         "prompt_tokens": 6,
11         "completion_tokens": 9,
12         "cost": 4.8e-5, //  In usd
13         "prompt_messages": [
14           {
15             "role": "user",
16             "content": "How are you doing today?"
17           }
18         ],
19         "completion_message": {
20           "content": " I'm doing well, thanks for asking!",
21           "role": "assistant"
22         },
23         "model": "claude-2",
24         "cached": false,
25         "timestamp": "2024-02-20T01:23:39.329729Z",
26         "status_code": 200,
27         "stream": false,
28         "latency": 1.8415491580963135, // in seconds
29         "scores": {},
30         "category": "Questions",
31         "metadata": {},
32         "routing_time": 0.18612787732854486, // in seconds
33         "full_request": {
34           "messages": [
35             {
36               "role": "user",
37               "content": "How are you doing today?"
38             }
39           ],
40           "model": "claude-2",
41           "logprobs": true
42         },
43         "sentiment_score": 0
44       },
45       "index": 0,
46       "message": { "content": null, "role": "assistant" }
47     }
48   ],
49   "created": 1706100589,
50   "model": "extra_parameter",
51   "object": "chat.completion.chunk",
52   "system_fingerprint": null,
53   "usage": {}
54 }

1	import requests
2
3	url = "https://api.respan.ai/api/audio/speech"
4
5	payload = {}
6	headers = {
7	"Authorization": "Bearer <token>",
8	"Content-Type": "application/json"
9	}
10
11	response = requests.post(url, json=payload, headers=headers)
12
13	print(response.json())

1	from openai import OpenAI
2
3	client = OpenAI(
4	base_url="https://api.respan.ai/api/",
5	api_key="YOUR_RESPAN_API_KEY",
6	)
7
8	response = client.audio.speech.create(
9	model="tts-1", # or "tts-1-hd"
10	voice="alloy",
11	input="Today is a wonderful day to build something people love!",
12	extra_body={"customer_identifier": "customer_11"} # All Respan parameters are supported
13	)

1	const speechFile = path.resolve("./speech.mp3");
2
3	const openai = new OpenAI({
4	baseURL: "https://api.respan.ai/api/",
5	apiKey: "YOUR_RESPAN_API_KEY",
6	});
7
8	const mp3 = await openai.audio.speech.create({
9	model: "tts-1", // or "tts-1-hd"
10	voice: "alloy",
11	input: "Today is a wonderful day to build something people love!",
12	extra_body: { customer_identifier: "customer_11" } // All Respan parameters are supported
13	});

1	def demo_call(input,
2	model="tts-1",
3	voice="alloy",
4	token="YOUR_RESPAN_API_KEY",
5	):
6	headers = {
7	'Content-Type': 'application/json',
8	'Authorization': f'Bearer {token}',
9	}
10
11	data = {
12	'model': model,
13	'input': input,
14	'voice': voice,
15	'customer_identifier': "customer_11"
16	}
17
18	response = requests.post('https://api.respan.ai/api/audio/speech', headers=headers, json=data)
19	return response
20
21	messages = "Today is a wonderful day to build something people love!"
22	print(demo_call(messages).json())

1	// Define the function with TypeScript
2	fetch('https://api.respan.ai/api/audio/speech', {
3	method: 'POST',
4	headers: {
5	'Content-Type': 'application/json',
6	'Authorization': 'Bearer YOUR_RESPAN_API_KEY'
7	},
8	body: JSON.stringify({
9	model: 'tts-1',
10	input: "Today is a wonderful day to build something people love!"
11	voice: "alloy",
12	customer_identifier: "customer_11"
13	})
14	})
15	.then(response => response.json())
16	.then(data => console.log(data));

1	"customer_credentials": {
2
3	"openai": {
4	"api_key": "YOUR_OPENAI_API_KEY",
5	}
6	}

1	{
2	//...other_params,
3	"customer_email": "hendrix@respan.ai"
4	}

1	{
2	"id": "chatcmpl-7476cf3f-fcc9-4902-a548-a12489856d8a",
3	//... main part of the response body ...
4	"request_breakdown": {
5	"prompt_tokens": 6,
6	"completion_tokens": 9,
7	"cost": 4.8e-5,
8	"prompt_messages": [
9	{
10	"role": "user",
11	"content": "How are you doing today?"
12	}
13	],
14	"completion_message": {
15	"content": " I'm doing well, thanks for asking!",
16	"role": "assistant"
17	},
18	"model": "claude-2",
19	"cached": false,
20	"timestamp": "2024-02-20T01:23:39.329729Z",
21	"status_code": 200,
22	"stream": false,
23	"latency": 1.8415491580963135,
24	"scores": {},
25	"category": "Questions",
26	"metadata": {},
27	"routing_time": 0.18612787732854486,
28	"full_request": {
29	"messages": [
30	{
31	"role": "user",
32	"content": "How are you doing today?"
33	}
34	],
35	"model": "claude-2",
36	"logprobs": true
37	},
38	"sentiment_score": 0
39	}
40	}

1	//... other chunks ...
2	// The following is the last chunk
3	{
4	"id": "request_breakdown",
5	"choices": [
6	{
7	"delta": { "content": null, "role": "assistant" },
8	"finish_reason": "stop",
9	"request_breakdown": {
10	"prompt_tokens": 6,
11	"completion_tokens": 9,
12	"cost": 4.8e-5, // In usd
13	"prompt_messages": [
14	{
15	"role": "user",
16	"content": "How are you doing today?"
17	}
18	],
19	"completion_message": {
20	"content": " I'm doing well, thanks for asking!",
21	"role": "assistant"
22	},
23	"model": "claude-2",
24	"cached": false,
25	"timestamp": "2024-02-20T01:23:39.329729Z",
26	"status_code": 200,
27	"stream": false,
28	"latency": 1.8415491580963135, // in seconds
29	"scores": {},
30	"category": "Questions",
31	"metadata": {},
32	"routing_time": 0.18612787732854486, // in seconds
33	"full_request": {
34	"messages": [
35	{
36	"role": "user",
37	"content": "How are you doing today?"
38	}
39	],
40	"model": "claude-2",
41	"logprobs": true
42	},
43	"sentiment_score": 0
44	},
45	"index": 0,
46	"message": { "content": null, "role": "assistant" }
47	}
48	],
49	"created": 1706100589,
50	"model": "extra_parameter",
51	"object": "chat.completion.chunk",
52	"system_fingerprint": null,
53	"usage": {}
54	}