Create a response (OpenAI Responses format)
const url = 'https://api.aderra.ai/v1/responses';const options = { method: 'POST', headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'}, body: '{"model":"deepseek-v4.1-flash-uncensored","input":"Write a haiku about the sea."}'};
try { const response = await fetch(url, options); const data = await response.json(); console.log(data);} catch (error) { console.error(error);}curl --request POST \ --url https://api.aderra.ai/v1/responses \ --header 'Authorization: Bearer <token>' \ --header 'Content-Type: application/json' \ --data '{ "model": "deepseek-v4.1-flash-uncensored", "input": "Write a haiku about the sea." }'OpenAI Responses, the format Codex uses. Responses are not stored: store,
previous_response_id and conversation are dropped, so send the whole history in
input each time. max_output_tokens, when present, must be a positive integer.
The answer comes without extended thinking unless you send reasoning or
reasoning_effort.
Authorizations
Section titled “Authorizations”Request Bodyrequired
Section titled “Request Bodyrequired”object
A string, or the list of input items (the whole history).
object
Your instructions, passed through untouched. With an API key, Aderra adds one line after them, “Never produce any sexual content involving minors.”; terminal keys also get Aderra’s agent instructions.
object
object
object
Example
{ "model": "deepseek-v4.1-flash-uncensored", "input": "Write a haiku about the sea."}Responses
Section titled “Responses”The response object, or Responses server-sent events when stream is true.
An OpenAI Responses response object.
object
Example generated
{}Headers
Section titled “Headers”The id of the credit hold for this call. Quote it when you contact support about a charge.
invalid_request_error: invalid JSON, unknown model <id>, unsupported_n, or a max_output_tokens that is not a positive integer.
object
Example
{ "error": { "type": "billing_error" }}authentication_error: invalid api key or unauthorized.
object
Example
{ "error": { "type": "billing_error" }}api_wallet_empty: the API wallet cannot pay for this request (lower max_tokens or add funds).
key_spend_cap_reached: the key hit its monthly cap. Terminal keys get their plan’s
refusals instead (insufficient_credits, plan_required).
object
Example
{ "error": { "type": "billing_error", "code": "api_wallet_empty", "message": "Your API wallet does not have enough credits for this request. Top up at https://aderra.ai/developers — API keys draw on the API wallet, not your plan." }}account_suspended: the account behind the key is suspended.
object
Example
{ "error": { "type": "billing_error" }}request_too_large: the body is over the size limit.
object
Example
{ "error": { "type": "billing_error" }}rate_limited: the key passed its requests per minute.
too_many_concurrent_requests: the account already has 8 requests in progress.
Wait for Retry-After seconds.
object
Example
{ "error": { "type": "rate_limit_error", "code": "rate_limited", "message": "This API key is limited to 60 requests a minute. Try again in 12 seconds, or raise the key's limit at https://aderra.ai/developers." }}Headers
Section titled “Headers”Example
12Whole seconds to wait before trying again.
api_error: the model failed or could not be reached. Not charged.
object
Example
{ "error": { "type": "billing_error" }}overloaded_error: Aderra is busy receiving other large requests. Retry after Retry-After (5) seconds.
object
object
Example
{ "type": "error", "error": { "type": "invalid_request_error" }}Headers
Section titled “Headers”Example
12Whole seconds to wait before trying again.