Responses (Gateway)

Create responses via the AI Gateway

POST /v1/responses

Try it

cURL

curl https://ai-gateway.helicone.ai/v1/responses \
  -H "Authorization: Bearer $HELICONE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "input": "Say hello in one sentence."
  }'

200

{}

This request schema applies when using the Helicone AI Gateway with pass‑through billing (credits). In BYOK mode, the standard OpenAI Responses API schema is allowed. The schema is defined based on fields that are stable across all provider-model mappings.

Learn more about pass‑through billing vs BYOK.

cURL

curl https://ai-gateway.helicone.ai/v1/responses \
  -H "Authorization: Bearer $HELICONE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "input": "Say hello in one sentence."
  }'

Body

application/json

top_logprobs · integer

Required range: 0 <= x <= 20

temperature

top_p

user · string

safety_identifier · string

prompt_cache_key · string

service_tier

Available options: auto, default, flex, scale, priority

model

reasoning

Show child attributes

reasoning. effort

Available options: minimal, low, medium, high

reasoning. summary

Available options: auto, concise, detailed

reasoning. generate_summary

Available options: auto, concise, detailed

reasoning. {key} · any

max_output_tokens

max_tool_calls

text · object

Show child attributes

text. format · object

Option 1

Option 2

Option 3

Show child attributes

text.format. type · enum<string> · required

Available options: text

text.format. {key} · any

text. verbosity

Available options: low, medium, high

text. {key} · any

tools · object[]

Option 1

Option 2

Option 3

Option 4

Option 5

Option 6

Show child attributes

tools. name · string · required

tools. parameters · required

Show child attributes

tools.parameters. {key} · any

tools. strict · required

tools. type · enum<string> · default: function

Available options: function

tools. description

tools. {key} · any

tool_choice

Available options: none, auto, required

truncation

Available options: auto, disabled

input

include

Available options: message.input_image.image_url, code_interpreter_call.outputs, reasoning.encrypted_content, message.output_text.logprobs

parallel_tool_calls

instructions

stream

stream_options

Show child attributes

stream_options. include_obfuscation · boolean

stream_options. {key} · any

{key} · any

Response

200

Request accepted