Chat

Available Providers
ProviderModelVersionPriceBilling unit
anthropicclaude-3-5-haiku-latestbedrock-2023-05-314.0 (per 1000000 token)1 token
anthropic-bedrock-2023-05-3115.0 (per 1000000 token)1 token
anthropicclaude-3-7-sonnet-20250219bedrock-2023-05-3115.0 (per 1000000 token)1 token
googlegemini-1.5-flashv10.6 (per 1000000 token)1 token
googlegemini-1.5-prov110.0 (per 1000000 token)1 token
googlegemini-1.5-flash-latestv10.6 (per 1000000 token)1 token
google-v10.6 (per 1000000 token)1 token
googlegemini-2.0-flash-litev10.3 (per 1000000 token)1 token
googlegemini-2.5-flashv12.5 (per 1000000 token)1 token
googlegemini-3-pro-previewv118.0 (per 1000000 token)1 token
googlegemini-2.0-flashv10.4 (per 1000000 token)1 token
googlegemini-2.5-prov115.0 (per 1000000 token)1 token
googlegemini-2.5-pro-preview-03-25v115.0 (per 1000000 token)1 token
googlegemini-1.5-pro-latestv110.0 (per 1000000 token)1 token
googlegemini-2.0-flash-expv110.0 (per 1000000 token)1 token
googlegemini-2.5-pro-exp-03-25v10.0 (per 1000000 token)1 token
openaio1v1Beta60.0 (per 1000000 token)1 token
openaigpt-4ov1Beta10.0 (per 1000000 token)1 token
openaigpt-4-turbov1Beta30.0 (per 1000000 token)1 token
openai-v1Beta10.0 (per 1000000 token)1 token
openaigpt-4.1-2025-04-14v1Beta8.0 (per 1000000 token)1 token
openaigpt-4.1-mini-2025-04-14v1Beta1.6 (per 1000000 token)1 token
openaigpt-4.1-nano-2025-04-14v1Beta0.4 (per 1000000 token)1 token
openaigpt-4o-miniv1Beta0.6 (per 1000000 token)1 token
openaigpt-5.2v1Beta14.0 (per 1000000 token)1 token
openaigpt-5v1Beta10.0 (per 1000000 token)1 token
openaigpt-5-miniv1Beta2.0 (per 1000000 token)1 token
openaigpt-5-nanov1Beta0.4 (per 1000000 token)1 token
openaigpt-5-chat-latestv1Beta10.0 (per 1000000 token)1 token
openaio1-miniv1Beta12.0 (per 1000000 token)1 token
openaio1-2024-12-17v1Beta60.0 (per 1000000 token)1 token
xai-v110.0 (per 1000000 token)1 token
xaigrok-2-visionv110.0 (per 1000000 token)1 token
xaigrok-2-vision-latestv110.0 (per 1000000 token)1 token
xaigrok-2-vision-1212v110.0 (per 1000000 token)1 token
amazon-boto3 (v1.29.6)3.2 (per 1000000 token)1 token
amazonamazon.nova-pro-v1:0boto3 (v1.29.6)3.2 (per 1000000 token)1 token
mistral-v0.0.16.0 (per 1000000 token)1 token
mistralpixtral-large-latestv0.0.16.0 (per 1000000 token)1 token
microsoftgpt-4oAzure AI Foundry15.0 (per 1000000 token)1 token

Default Models
NameValue
anthropicclaude-3-5-sonnet-latest
googlegemini-2.0-flash
openaigpt-4o
xaigrok-2-vision-latest
amazonamazon.nova-pro-v1:0
mistralpixtral-large-latest
microsoftgpt-4o
Recent Requests
Log in to see full request history
TimeStatusUser Agent
Retrieving recent requests…
LoadingLoading…
Body Params
string
Defaults to [object Object]

A dictionnary or a json object to specify specific models to use for some providers.
It can be in the following format: {"google" : "google_model", "ibm": "ibm_model"...}.

providers
array of strings
required

It can be one (ex: 'amazon' or 'google') or multiple provider(s) (ex: 'amazon,microsoft,google') that the data will be redirected to in order to get the processed results.
Providers can also be invoked with specific models (ex: providers: 'amazon/model1, amazon/model2, google/model3')

providers*
fallback_providers
array of strings
length ≤ 5
Defaults to

Providers in this list will be used as fallback if the call to provider in providers parameter fails. To use this feature, you must input only one provider in the providers parameter. but you can put up to 5 fallbacks.

They will be tried in the same order they are input, and it will stop to the first provider who doesn't fail.

Doesn't work with async subfeatures.

fallback_providers
boolean
Defaults to true

Optional : When set to true (default), the response is an object of responses with providers names as keys :
{"google" : { "status": "success", ... }, }
When set to false the response structure is a list of response objects :
[{"status": "success", "provider": "google" ... }, ].

boolean
Defaults to false

Optional : When set to false (default) the structure of the extracted items is list of objects having different attributes :
{'items': [{"attribute_1": "x1","attribute_2": "y2"}, ... ]}
When it is set to true, the response contains an object with each attribute as a list :
{ "attribute_1": ["x1","x2", ...], "attribute_2": [y1, y2, ...]}

boolean
Defaults to true
boolean
Defaults to false

Optional : Shows the original response of the provider.
When set to true, a new attribute original_response will appear in the response object.

messages
array of objects
required

A list containing all the conversations between the user and the assistant. Each item in the list should be a dictionary with two keys: 'role' and 'message'.

role: Specifies the role of the speaker and can have the values 'user' or 'assistant'.

message: A list of dictionaries. Each dictionary in the 'message' list must contain the keys 'type' and 'content'.

Structure

  • type: Specifies the type of content and can be 'media_url', 'media_base64', or 'text'.
  • content: A dictionary with the actual content based on the 'type':
    • If 'type' is 'media_url', 'content' must contain 'media_url' and must not contain 'media_base64' or 'text'.
    • If 'type' is 'media_base64', 'content' must contain 'media_base64' and must not contain 'media_url' or 'text'.
    • If 'type' is 'text', 'content' must contain 'text' and must not contain 'media_url' or 'media_base64'.

Example

[
  {
    'role': 'user',
    'content': [
      {
        'type': 'text',
        'content': {'text': 'Describe this image'}
      },
      {
        'type': 'media_url',
        'content': {
           'media_url': 'https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg',
           'media_type': 'image/jpeg'}
      },
    ]
  }
]
messages*
string | null

A system message that helps set the behavior of the assistant. For example, 'You are a helpful assistant'.

double
0 to 2
Defaults to 0

Controls the creativity of the model's responses. Higher values (up to 2) make the output more random, while lower values make it more focused and deterministic. A value of 0 (argmax sampling) is useful for scenarios requiring precise answers.

integer
1 to 300000
Defaults to 2048

The maximum number of tokens to generate in the completion. This value, combined with the token count of your prompt, cannot exceed the model's context length.

stop_sequences
array of strings
Defaults to

A list of sequences where the model will stop generating further tokens. Useful for controlling response length and format.

stop_sequences
integer
0 to 500

Limits the sampling pool to the top K options for each token. Setting this to a lower value can make the output more focused and deterministic.

double
0 to 1

Enables nucleus sampling, where the model considers the smallest number of tokens whose cumulative probability is at least top_p. This allows for a dynamic selection of tokens based on probability, offering a balance between focus and creativity.

string
enum

Choices:

  • 'low': Minimal reasoning, quick responses
  • 'medium': Balanced reasoning approach
  • 'high': In-depth, comprehensive reasoning

Example: 'high' for complex problem-solving tasks

  • low - low
  • medium - medium
  • high - high
Allowed:
Responses

Language
Credentials
Bearer
JWT
LoadingLoading…
Response
Click Try It! to start a request and see the response here! Or choose an example:
application/json