Get Requests

POST

request

query-clickhouse

curl --request POST \
  --url https://api.helicone.ai/v1/request/query-clickhouse \
  --header 'Content-Type: application/json' \
  --header 'authorization: <api-key>' \
  --data '{
  "filter": "all",
  "isCached": false,
  "limit": 100,
  "offset": 0,
  "sort": {
    "created_at": "desc"
  },
  "includeInputs": false,
  "isScored": false,
  "isPartOfExperiment": false
}'

{
  "filter": "all",
  "isCached": false,
  "limit": 10,
  "offset": 0,
  "sort": {
    "created_at": "desc"
  },
  "isScored": false,
  "isPartOfExperiment": false
}

For users in the European Union: Please use eu.api.helicone.ai instead of api.helicone.ai to ensure compliance with data residency requirements and optimal performance.

Python Example

See how to query requests using our Python SDK.

TypeScript Example

Learn to fetch requests with TypeScript/JavaScript.

The following API is the same as the Get Requests API, but it is optimized for speed when querying large amount of data. This endpoint will timeout for point queries and is really slow when querying just a few requests.

The following API lets you get all of the requests that would be visible in the request table at helicone.ai/requests.

Premade examples 👇

Filter	Description
Get Request by User	Get all the requests made by a user

Filter

A filter is either a FilterLeaf or a FilterBranch, and can be composed of multiple filters generating an AST of ANDs/ORs.

Here is how it is represented in typescript:

export interface FilterBranch {
  left: FilterNode;
  operator: "or" | "and"; // Can add more later
  right: FilterNode;
}

export type FilterNode = FilterLeaf | FilterBranch | "all";

This allows us to build complex filters like this:

{
  "filter": {
    "operator": "and",
    "right": {
      "request_response_rmt": {
        "model": {
          "contains": "gpt-4"
        }
      }
    },
    "left": {
      "request_response_rmt": {
        "user_id": {
          "equals": "abc@email.com"
        }
      }
    }
  }
}

Authorizations

authorization

string

header

required

Body

application/json

Request query filters

filter

required

From T, pick a set of properties whose keys are in the union K

filter.request_response_rmt

object

Make all properties in T optional

filter.request_response_rmt.latency

object

Make all properties in T optional

filter.request_response_rmt.status

object

Make all properties in T optional

filter.request_response_rmt.request_created_at

object

Make all properties in T optional

filter.request_response_rmt.response_created_at

object

Make all properties in T optional

filter.request_response_rmt.model

object

Make all properties in T optional

filter.request_response_rmt.user_id

object

Make all properties in T optional

filter.request_response_rmt.organization_id

object

Make all properties in T optional

filter.request_response_rmt.node_id

object

Make all properties in T optional

filter.request_response_rmt.job_id

object

Make all properties in T optional

filter.request_response_rmt.threat

object

Make all properties in T optional

filter.request_response_rmt.request_id

object

Make all properties in T optional

filter.request_response_rmt.prompt_tokens

object

Make all properties in T optional

filter.request_response_rmt.completion_tokens

object

Make all properties in T optional

filter.request_response_rmt.total_tokens

object

Make all properties in T optional

filter.request_response_rmt.target_url

object

Make all properties in T optional

filter.request_response_rmt.properties

object

filter.request_response_rmt.search_properties

object

filter.request_response_rmt.scores

object

filter.request_response_rmt.scores_column

object

Make all properties in T optional

filter.request_response_rmt.request_body

object

Make all properties in T optional

filter.request_response_rmt.response_body

object

Make all properties in T optional

filter.response

object

Make all properties in T optional

filter.request

object

Make all properties in T optional

filter.request.prompt

object

Make all properties in T optional

filter.request.created_at

object

Make all properties in T optional

filter.request.user_id

object

Make all properties in T optional

filter.request.auth_hash

object

Make all properties in T optional

filter.request.org_id

object

Make all properties in T optional

filter.request.id

object

Make all properties in T optional

filter.request.node_id

object

Make all properties in T optional

filter.request.model

object

Make all properties in T optional

filter.request.modelOverride

object

Make all properties in T optional

filter.request.path

object

Make all properties in T optional

filter.request.prompt_id

object

Make all properties in T optional

filter.feedback

object

Make all properties in T optional

filter.sessions_request_response_rmt

object

Make all properties in T optional

filter.sessions_request_response_rmt.session_session_id

object

Make all properties in T optional

filter.sessions_request_response_rmt.session_session_name

object

Make all properties in T optional

filter.sessions_request_response_rmt.session_total_cost

object

Make all properties in T optional

filter.sessions_request_response_rmt.session_total_tokens

object

Make all properties in T optional

filter.sessions_request_response_rmt.session_prompt_tokens

object

Make all properties in T optional

filter.sessions_request_response_rmt.session_completion_tokens

object

Make all properties in T optional

filter.sessions_request_response_rmt.session_total_requests

object

Make all properties in T optional

filter.sessions_request_response_rmt.session_created_at

object

Make all properties in T optional

filter.sessions_request_response_rmt.session_latest_request_created_at

object

Make all properties in T optional

filter.cache_hits

object

Make all properties in T optional

filter.cache_hits.organization_id

object

Make all properties in T optional

filter.cache_hits.request_id

object

Make all properties in T optional

filter.cache_hits.latency

object

Make all properties in T optional

filter.cache_hits.completion_tokens

object

Make all properties in T optional

filter.cache_hits.prompt_tokens

object

Make all properties in T optional

filter.cache_hits.created_at

object

Make all properties in T optional

filter.properties

object

filter.values

object

offset

number

limit

number

sort

object

isCached

boolean

includeInputs

boolean

isPartOfExperiment

boolean

isScored

boolean

Response

200 - application/json

data

object[]

required

data.response_id

string | null

required

data.response_created_at

string | null

required

data.response_status

number

required

data.response_model

string | null

required

data.request_id

string

required

data.request_created_at

string

required

data.request_body

any

required

data.request_path

string

required

data.request_user_id

string | null

required

data.request_properties

object

required

Construct a type with a set of properties K of type T

data.request_model

string | null

required

data.model_override

string | null

required

data.helicone_user

string | null

required

data.provider

required

Available options:

OPENAI,

ANTHROPIC,

AZURE,

LOCAL,

HELICONE,

AMDBARTEK,

ANYSCALE,

CLOUDFLARE,

2YFV,

TOGETHER,

LEMONFOX,

FIREWORKS,

PERPLEXITY,

GOOGLE,

OPENROUTER,

WISDOMINANUTSHELL,

GROQ,

COHERE,

MISTRAL,

DEEPINFRA,

QSTASH,

FIRECRAWL,

AWS,

DEEPSEEK,

X,

AVIAN,

NEBIUS,

NOVITA

data.delay_ms

number | null

required

data.time_to_first_token

number | null

required

data.total_tokens

number | null

required

data.prompt_tokens

number | null

required

data.prompt_cache_write_tokens

number | null

required

data.prompt_cache_read_tokens

number | null

required

data.completion_tokens

number | null

required

data.prompt_audio_tokens

number | null

required

data.completion_audio_tokens

number | null

required

data.prompt_id

string | null

required

data.llmSchema

object

required

data.llmSchema.request

object

required

data.llmSchema.request.llm_type

enum<string>

Available options:

chat,

completion

data.llmSchema.request.provider

string

data.llmSchema.request.model

string

data.llmSchema.request.messages

object[] | null

data.llmSchema.request.prompt

string | null

data.llmSchema.request.instructions

string | null

data.llmSchema.request.max_tokens

number | null

data.llmSchema.request.temperature

number | null

data.llmSchema.request.top_p

number | null

data.llmSchema.request.seed

number | null

data.llmSchema.request.stream

boolean | null

data.llmSchema.request.presence_penalty

number | null

data.llmSchema.request.frequency_penalty

number | null

data.llmSchema.request.stop

data.llmSchema.request.reasoning_effort

enum<string> | null

Available options:

low,

medium,

high

data.llmSchema.request.tools

object[]

data.llmSchema.request.parallel_tool_calls

boolean | null

data.llmSchema.request.tool_choice

object

data.llmSchema.request.response_format

object

data.llmSchema.request.toolDetails

object

data.llmSchema.request.vectorDBDetails

object

data.llmSchema.request.input

data.llmSchema.request.n

number | null

data.llmSchema.request.size

string

data.llmSchema.request.quality

string

data.llmSchema.response

object

data.llmSchema.response.vectorDBDetailsResponse

object

data.llmSchema.response.toolDetailsResponse

object

data.llmSchema.response.error

object

data.llmSchema.response.model

string | null

data.llmSchema.response.instructions

string | null

data.llmSchema.response.responses

object[] | null

data.llmSchema.response.messages

object[] | null

data.country_code

string | null

required

data.asset_ids

string[] | null

required

data.asset_urls

object

required

Construct a type with a set of properties K of type T

data.scores

object

required

Construct a type with a set of properties K of type T

data.properties

object

required

Construct a type with a set of properties K of type T

data.assets

string[]

required

data.target_url

string

required

data.model

string

required

data.response_body

any

data.feedback_created_at

string | null

data.feedback_id

string | null

data.feedback_rating

boolean | null

data.signed_body_url

string | null

data.costUSD

number | null

error

enum<number> | null

required

data

object[]

required

data.response_id

string | null

required

data.response_created_at

string | null

required

data.response_status

number

required

data.response_model

string | null

required

data.request_id

string

required

data.request_created_at

string

required

data.request_body

any

required

data.request_path

string

required

data.request_user_id

string | null

required

data.request_properties

object

required

Construct a type with a set of properties K of type T

data.request_model

string | null

required

data.model_override

string | null

required

data.helicone_user

string | null

required

data.provider

required

Available options:

OPENAI,

ANTHROPIC,

AZURE,

LOCAL,

HELICONE,

AMDBARTEK,

ANYSCALE,

CLOUDFLARE,

2YFV,

TOGETHER,

LEMONFOX,

FIREWORKS,

PERPLEXITY,

GOOGLE,

OPENROUTER,

WISDOMINANUTSHELL,

GROQ,

COHERE,

MISTRAL,

DEEPINFRA,

QSTASH,

FIRECRAWL,

AWS,

DEEPSEEK,

X,

AVIAN,

NEBIUS,

NOVITA

data.delay_ms

number | null

required

data.time_to_first_token

number | null

required

data.total_tokens

number | null

required

data.prompt_tokens

number | null

required

data.prompt_cache_write_tokens

number | null

required

data.prompt_cache_read_tokens

number | null

required

data.completion_tokens

number | null

required

data.prompt_audio_tokens

number | null

required

data.completion_audio_tokens

number | null

required

data.prompt_id

string | null

required

data.llmSchema

object

required

data.llmSchema.request

object

required

data.llmSchema.request.llm_type

enum<string>

Available options:

chat,

completion

data.llmSchema.request.provider

string

data.llmSchema.request.model

string

data.llmSchema.request.messages

object[] | null

data.llmSchema.request.prompt

string | null

data.llmSchema.request.instructions

string | null

data.llmSchema.request.max_tokens

number | null

data.llmSchema.request.temperature

number | null

data.llmSchema.request.top_p

number | null

data.llmSchema.request.seed

number | null

data.llmSchema.request.stream

boolean | null

data.llmSchema.request.presence_penalty

number | null

data.llmSchema.request.frequency_penalty

number | null

data.llmSchema.request.stop

data.llmSchema.request.reasoning_effort

enum<string> | null

Available options:

low,

medium,

high

data.llmSchema.request.tools

object[]

data.llmSchema.request.parallel_tool_calls

boolean | null

data.llmSchema.request.tool_choice

object

data.llmSchema.request.response_format

object

data.llmSchema.request.toolDetails

object

data.llmSchema.request.vectorDBDetails

object

data.llmSchema.request.input

data.llmSchema.request.n

number | null

data.llmSchema.request.size

string

data.llmSchema.request.quality

string

data.llmSchema.response

object

data.llmSchema.response.vectorDBDetailsResponse

object

data.llmSchema.response.toolDetailsResponse

object

data.llmSchema.response.error

object

data.llmSchema.response.model

string | null

data.llmSchema.response.instructions

string | null

data.llmSchema.response.responses

object[] | null

data.llmSchema.response.messages

object[] | null

data.country_code

string | null

required

data.asset_ids

string[] | null

required

data.asset_urls

object

required

Construct a type with a set of properties K of type T

data.scores

object

required

Construct a type with a set of properties K of type T

data.properties

object

required

Construct a type with a set of properties K of type T

data.assets

string[]

required

data.target_url

string

required

data.model

string

required

data.response_body

any

data.feedback_created_at

string | null

data.feedback_id

string | null

data.feedback_rating

boolean | null

data.signed_body_url

string | null

data.costUSD

number | null

error

enum<number> | null

required

data

enum<number> | null

required

error

string

required

Get Requests (Point Queries)

curl --request POST \
  --url https://api.helicone.ai/v1/request/query-clickhouse \
  --header 'Content-Type: application/json' \
  --header 'authorization: <api-key>' \
  --data '{
  "filter": "all",
  "isCached": false,
  "limit": 100,
  "offset": 0,
  "sort": {
    "created_at": "desc"
  },
  "includeInputs": false,
  "isScored": false,
  "isPartOfExperiment": false
}'

{
  "filter": "all",
  "isCached": false,
  "limit": 10,
  "offset": 0,
  "sort": {
    "created_at": "desc"
  },
  "isScored": false,
  "isPartOfExperiment": false
}

Request

Prompt

User

Evals

Webhooks

Evaluator

Experiment

Trace

Log

Property

Dataset

Customer

Dashboard

Settings

Session

Python Example

TypeScript Example

Premade examples 👇

Filter

Authorizations

Body

Response

Request

Prompt

User

Evals

Webhooks

Evaluator

Experiment

Trace

Log

Property

Dataset

Customer

Dashboard

Settings

Session

Python Example

TypeScript Example

​Premade examples 👇

​Filter

Authorizations

Body

Response

Premade examples 👇

Filter