The Forecasting Company API

Endpoint:https://api.retrocast.com

Model inference

POST

https://api.retrocast.com

/forecast

Perform inference with foundation models.

Model inference › query Parameters

modelstring · enum · required
The forecasting model to use for inference. Note that only tabpfn-ts, moirai and moirai-moe support exogenous variables.
Enum values:
moirai
chronos
chronos-bolt
timesfm
timesfm-2
moirai-moe
moirai-2
tabpfn-ts
Default: tabpfn-ts
cloudstring · enum
Specify the cloud provider to use for inference. If none is set then any may be used depending on availability.
Enum values:
gcp
aws
oci

Model inference › Headers

Authorizationstring · required
The Authorization header is used to authenticate with the API using your API key. Value is of the format Bearer YOUR_KEY_HERE.

Model inference › Request Body

seriesobject[] · required
Example: {"0":{"future_variables":{"local_attendance_forecast":[125,75,200,122,123,150,100,120,121,119]},"future_variables_index":["2001-01-06","2001-01-07","2001-01-08","2001-01-09","2001-01-10","2001-01-11","2001-01-12","2001-01-13","2001-01-14","2001-01-15"],"hist_variables":{"temperature":[74,72,79,77,75]},"index":["2001-01-06","2001-01-07","2001-01-08","2001-01-09","2001-01-10"],"static_variables":{"Population":100000},"target":[125,120,140,135,133]}}
horizoninteger · min: 1 · max: 10000 · required
Number of steps to forecast given the frequency.
Example: 5
freqstring · enum · required
Frequency of the time series.
Enum values:
5min
15min
30min
H
D
W
M
Q
Example: D

context
The amount of history to use when forecasting. This is the number of steps to look back in the target series. More history can improve the forecast accuracy, but can also increase the computation time. By default this is set to the max of model capability or the length of the provided target series, whichever is shorter.
Example: 20
Default: null
quantiles
Default: [0.1,0.9,0.4,0.5]
covariates
Apply additional co-variates provided by TFC. Only supported by the following models: Navi, Moirai, Moriai-MoE and TabPFN-TS.
Example: {"0":{"config":{"country":"US"},"type":"holidays"}}
Default: null
model_config
Optional model-specific configuration overrides.
Example: {"config":{"season_length":7},"model":"aarima"}
Default: null

Model inference › Responses

Success

series
Default: null
status
Default: completed

POST /forecast

curl --request POST \
  --url 'https://api.retrocast.com/forecast?model=tabpfn-ts' \
  --header 'Authorization: <string>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "series": [
    {
      "index": [
        "2001-01-06",
        "2001-01-07",
        "2001-01-08",
        "2001-01-09",
        "2001-01-10"
      ],
      "target": [
        125,
        120,
        140,
        135,
        133
      ]
    }
  ],
  "horizon": 5,
  "freq": "D",
  "context": null,
  "quantiles": [
    0.1,
    0.9,
    0.4,
    0.5
  ]
}
'

shell

Show example in

Request Body Example

{
  "series": [
    {
      "index": [
        "2001-01-06",
        "2001-01-07",
        "2001-01-08",
        "2001-01-09",
        "2001-01-10"
      ],
      "target": [
        125,
        120,
        140,
        135,
        133
      ]
    }
  ],
  "horizon": 5,
  "freq": "D",
  "context": null,
  "quantiles": [
    0.1,
    0.9,
    0.4,
    0.5
  ]
}

json

application/json

Example Responses

No example

json

application/json

Submit job for forecasting

POST

https://api.retrocast.com

/forecast-jobs

Perform historic inference for a range of forecast creation dates (fcds). These jobs can run longer and need to be retrieved with a separate endpoint and the returned job ID.

Submit job for forecasting › query Parameters

modelstring · enum · required
The forecasting model to use for inference. Note that only tabpfn-ts, moirai, and moirai-moe support exogenous variables.
Enum values:
moirai
chronos
chronos-bolt
timesfm
timesfm-2
moirai-moe
moirai-2
tabpfn-ts
Default: tabpfn-ts

Submit job for forecasting › Headers

Authorizationstring · required
The Authorization header is used to authenticate with the API using your API key. Value is of the format Bearer YOUR_KEY_HERE.

Submit job for forecasting › Request Body

seriesobject[] · required
Example: {"0":{"future_variables":{"local_attendance_forecast":[125,75,200,122,123,150,100,120,121,119]},"future_variables_index":["2001-01-06","2001-01-07","2001-01-08","2001-01-09","2001-01-10","2001-01-11","2001-01-12","2001-01-13","2001-01-14","2001-01-15"],"hist_variables":{"temperature":[74,72,79,77,75]},"index":["2001-01-06","2001-01-07","2001-01-08","2001-01-09","2001-01-10"],"static_variables":{"Population":100000},"target":[125,120,140,135,133]}}
horizoninteger · min: 1 · max: 10000 · required
Number of steps to forecast given the frequency.
Example: 5
freqstring · enum · required
Frequency of the time series.
Enum values:
5min
15min
30min
H
D
W
M
Q
Example: D

context
The amount of history to use when forecasting. This is the number of steps to look back in the target series. More history can improve the forecast accuracy, but can also increase the computation time. By default this is set to the max of model capability or the length of the provided target series, whichever is shorter.
Example: 20
Default: null
quantiles
Default: [0.1,0.9,0.4,0.5]
covariates
Apply additional co-variates provided by TFC. Only supported by the following models: Navi, Moirai, Moriai-MoE and TabPFN-TS.
Example: {"0":{"config":{"country":"US"},"type":"holidays"}}
Default: null
model_config
Optional model-specific configuration overrides.
Example: {"config":{"season_length":7},"model":"aarima"}
Default: null

Submit job for forecasting › Responses

Job submitted successfully

call_idstring
The unique identifier of the submitted job

POST /forecast-jobs

curl --request POST \
  --url 'https://api.retrocast.com/forecast-jobs?model=tabpfn-ts' \
  --header 'Authorization: <string>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "series": [
    {
      "index": [
        "2001-01-06",
        "2001-01-07",
        "2001-01-08",
        "2001-01-09",
        "2001-01-10"
      ],
      "target": [
        125,
        120,
        140,
        135,
        133
      ]
    }
  ],
  "horizon": 5,
  "freq": "D",
  "context": null,
  "quantiles": [
    0.1,
    0.9,
    0.4,
    0.5
  ]
}
'

shell

Show example in

Request Body Example

{
  "series": [
    {
      "index": [
        "2001-01-06",
        "2001-01-07",
        "2001-01-08",
        "2001-01-09",
        "2001-01-10"
      ],
      "target": [
        125,
        120,
        140,
        135,
        133
      ]
    }
  ],
  "horizon": 5,
  "freq": "D",
  "context": null,
  "quantiles": [
    0.1,
    0.9,
    0.4,
    0.5
  ]
}

json

application/json

Example Responses

No example

json

application/json

Retrieve job result

GET

https://api.retrocast.com

/forecast-jobs/{job_id}

Retrieve the forecast result from a forecast job.

Retrieve job result › path Parameters

job_idstring · required

Retrieve job result › Headers

Authorizationstring · required
The Authorization header is used to authenticate with the API using your API key. Value is of the format Bearer YOUR_KEY_HERE.

Retrieve job result › Responses

Success

series
Default: null
status
Default: completed

GET /forecast-jobs/{job_id}

curl --request GET \
  --url https://api.retrocast.com/forecast-jobs/:job_id \
  --header 'Authorization: <string>'

shell

Show example in

Example Responses

No example

json

application/json

OpenAPI spec

GET

https://api.retrocast.com

/openapi

Return the OpenAPI spec for the TFC API.

OpenAPI spec › Responses

Rate Limiting Response

typestring · required
A URI reference that identifies the problem.
titlestring · required
A short, human-readable summary of the problem.
statusnumber · required
The HTTP status code.

instancestring

GET /openapi

curl --request GET \
  --url https://api.retrocast.com/openapi

shell

Show example in

Example Responses

No example

json

application/json

Warmup model

GET

https://api.retrocast.com

/warmup

Warmup a model endpoint for better UX in embedded applications.

Warmup model › query Parameters

modelstring · enum · required
The forecasting model to warmup.
Enum values:
moirai
chronos
chronos-bolt
timesfm
timesfm-2
moirai-moe
moirai-2
tabpfn-ts
Default: tabpfn-ts
cloudstring · enum
Specify the cloud provider to use. If none is set then any may be used depending on availability.
Enum values:
gcp
aws
oci

Warmup model › Headers

Authorizationstring · required
The Authorization header is used to authenticate with the API using your API key. Value is of the format Bearer YOUR_KEY_HERE.

Warmup model › Responses

Rate Limiting Response

typestring · required
A URI reference that identifies the problem.
titlestring · required
A short, human-readable summary of the problem.
statusnumber · required
The HTTP status code.

instancestring

GET /warmup

curl --request GET \
  --url 'https://api.retrocast.com/warmup?model=tabpfn-ts' \
  --header 'Authorization: <string>'

shell

Show example in

Example Responses

No example

json

application/json

Model inference

POST

https://api.retrocast.com

/forecast

Perform inference with foundation models.

Model inference › query Parameters

modelstring · enum · required
The forecasting model to use for inference. Note that only tabpfn-ts, moirai and moirai-moe support exogenous variables.
Enum values:
moirai
chronos
chronos-bolt
timesfm
timesfm-2
moirai-moe
moirai-2
tabpfn-ts
Default: tabpfn-ts
cloudstring · enum
Specify the cloud provider to use for inference. If none is set then any may be used depending on availability.
Enum values:
gcp
aws
oci

Model inference › Headers

Authorizationstring · required
The Authorization header is used to authenticate with the API using your API key. Value is of the format Bearer YOUR_KEY_HERE.

Model inference › Request Body

seriesobject[] · required
Example: {"0":{"future_variables":{"local_attendance_forecast":[125,75,200,122,123,150,100,120,121,119]},"future_variables_index":["2001-01-06","2001-01-07","2001-01-08","2001-01-09","2001-01-10","2001-01-11","2001-01-12","2001-01-13","2001-01-14","2001-01-15"],"hist_variables":{"temperature":[74,72,79,77,75]},"index":["2001-01-06","2001-01-07","2001-01-08","2001-01-09","2001-01-10"],"static_variables":{"Population":100000},"target":[125,120,140,135,133]}}
horizoninteger · min: 1 · max: 10000 · required
Number of steps to forecast given the frequency.
Example: 5
freqstring · enum · required
Frequency of the time series.
Enum values:
5min
15min
30min
H
D
W
M
Q
Example: D

context
The amount of history to use when forecasting. This is the number of steps to look back in the target series. More history can improve the forecast accuracy, but can also increase the computation time. By default this is set to the max of model capability or the length of the provided target series, whichever is shorter.
Example: 20
Default: null
quantiles
Default: [0.1,0.9,0.4,0.5]
covariates
Apply additional co-variates provided by TFC. Only supported by the following models: Navi, Moirai, Moriai-MoE and TabPFN-TS.
Example: {"0":{"config":{"country":"US"},"type":"holidays"}}
Default: null
model_config
Optional model-specific configuration overrides.
Example: {"config":{"season_length":7},"model":"aarima"}
Default: null

Model inference › Responses

Success

series
Default: null
status
Default: completed

curl --request POST \ --url 'https://api.retrocast.com/forecast?model=tabpfn-ts' \ --header 'Authorization: <string>' \ --header 'Content-Type: application/json' \ --data ' { "series": [ { "index": [ "2001-01-06", "2001-01-07", "2001-01-08", "2001-01-09", "2001-01-10" ], "target": [ 125, 120, 140, 135, 133 ] } ], "horizon": 5, "freq": "D", "context": null, "quantiles": [ 0.1, 0.9, 0.4, 0.5 ] } '

{ "series": [ { "index": [ "2001-01-06", "2001-01-07", "2001-01-08", "2001-01-09", "2001-01-10" ], "target": [ 125, 120, 140, 135, 133 ] } ], "horizon": 5, "freq": "D", "context": null, "quantiles": [ 0.1, 0.9, 0.4, 0.5 ] }

Submit job for forecasting

POST

https://api.retrocast.com

/forecast-jobs

Perform historic inference for a range of forecast creation dates (fcds). These jobs can run longer and need to be retrieved with a separate endpoint and the returned job ID.

Submit job for forecasting › query Parameters

modelstring · enum · required
The forecasting model to use for inference. Note that only tabpfn-ts, moirai, and moirai-moe support exogenous variables.
Enum values:
moirai
chronos
chronos-bolt
timesfm
timesfm-2
moirai-moe
moirai-2
tabpfn-ts
Default: tabpfn-ts

Submit job for forecasting › Headers

Authorizationstring · required
The Authorization header is used to authenticate with the API using your API key. Value is of the format Bearer YOUR_KEY_HERE.

Submit job for forecasting › Request Body

seriesobject[] · required
Example: {"0":{"future_variables":{"local_attendance_forecast":[125,75,200,122,123,150,100,120,121,119]},"future_variables_index":["2001-01-06","2001-01-07","2001-01-08","2001-01-09","2001-01-10","2001-01-11","2001-01-12","2001-01-13","2001-01-14","2001-01-15"],"hist_variables":{"temperature":[74,72,79,77,75]},"index":["2001-01-06","2001-01-07","2001-01-08","2001-01-09","2001-01-10"],"static_variables":{"Population":100000},"target":[125,120,140,135,133]}}
horizoninteger · min: 1 · max: 10000 · required
Number of steps to forecast given the frequency.
Example: 5
freqstring · enum · required
Frequency of the time series.
Enum values:
5min
15min
30min
H
D
W
M
Q
Example: D

context
The amount of history to use when forecasting. This is the number of steps to look back in the target series. More history can improve the forecast accuracy, but can also increase the computation time. By default this is set to the max of model capability or the length of the provided target series, whichever is shorter.
Example: 20
Default: null
quantiles
Default: [0.1,0.9,0.4,0.5]
covariates
Apply additional co-variates provided by TFC. Only supported by the following models: Navi, Moirai, Moriai-MoE and TabPFN-TS.
Example: {"0":{"config":{"country":"US"},"type":"holidays"}}
Default: null
model_config
Optional model-specific configuration overrides.
Example: {"config":{"season_length":7},"model":"aarima"}
Default: null

Submit job for forecasting › Responses

Job submitted successfully

call_idstring
The unique identifier of the submitted job

curl --request POST \ --url 'https://api.retrocast.com/forecast-jobs?model=tabpfn-ts' \ --header 'Authorization: <string>' \ --header 'Content-Type: application/json' \ --data ' { "series": [ { "index": [ "2001-01-06", "2001-01-07", "2001-01-08", "2001-01-09", "2001-01-10" ], "target": [ 125, 120, 140, 135, 133 ] } ], "horizon": 5, "freq": "D", "context": null, "quantiles": [ 0.1, 0.9, 0.4, 0.5 ] } '

Retrieve job result

GET

https://api.retrocast.com

/forecast-jobs/{job_id}

Retrieve the forecast result from a forecast job.

Retrieve job result › path Parameters

job_idstring · required

Retrieve job result › Headers

Authorizationstring · required
The Authorization header is used to authenticate with the API using your API key. Value is of the format Bearer YOUR_KEY_HERE.

Retrieve job result › Responses

Success

series
Default: null
status
Default: completed

OpenAPI spec

GET

https://api.retrocast.com

/openapi

Return the OpenAPI spec for the TFC API.

OpenAPI spec › Responses

Rate Limiting Response

typestring · required
A URI reference that identifies the problem.
titlestring · required
A short, human-readable summary of the problem.
statusnumber · required
The HTTP status code.

instancestring

Warmup model

GET

https://api.retrocast.com

/warmup

Warmup a model endpoint for better UX in embedded applications.

Warmup model › query Parameters

modelstring · enum · required
The forecasting model to warmup.
Enum values:
moirai
chronos
chronos-bolt
timesfm
timesfm-2
moirai-moe
moirai-2
tabpfn-ts
Default: tabpfn-ts
cloudstring · enum
Specify the cloud provider to use. If none is set then any may be used depending on availability.
Enum values:
gcp
aws
oci

Warmup model › Headers

Authorizationstring · required
The Authorization header is used to authenticate with the API using your API key. Value is of the format Bearer YOUR_KEY_HERE.

Warmup model › Responses

Rate Limiting Response

typestring · required
A URI reference that identifies the problem.
titlestring · required
A short, human-readable summary of the problem.
statusnumber · required
The HTTP status code.

instancestring