Modern API Interface

Responses API

DEVUP AI provides an OpenAI-compatible Responses API endpoint for supported models. This endpoint exposes a structured request/response interface with native Responses output payloads, built-in reasoning configuration, and transparent billing in Algerian Dinar (DZD).

POST

https://api.devupai.com/v1/responses

Current limitation: Non-streaming requests only

Streaming is not currently supported on /v1/responses. Requests must set stream: false or omit the parameter entirely. Sending stream: true returns an HTTP 400 streaming_not_supported error.

Authentication & Billing

The Responses API uses standard Bearer token authentication with your existing DEVUP AI API key. It connects directly to our canonical billing engine, applying exact balance reservation and settlement in Algerian Dinar (DZD) without separate subscription tiers or secondary ledgers.

Authorization: Bearer <YOUR_API_KEY>

Quick Start

You can interact with /v1/responses using official OpenAI SDKs or standard HTTP clients by setting the base URL to https://api.devupai.com/v1.

import os
from openai import OpenAI

# Initialize client pointing to DEVUP AI gateway
client = OpenAI(
    api_key=os.environ.get("DEVUP_API_KEY"),
    base_url="https://api.devupai.com/v1",
)

# Call the Responses endpoint with a compatible model
response = client.responses.create(
    model="openai/gpt-5.3-codex",
    input="Explain how quantum entanglement enables quantum key distribution.",
    max_output_tokens=1024,
)

# Output items are preserved in provider-native format
for item in response.output:
    if item.type == "message":
        for content in item.content:
            if content.type == "text":
                print(content.text)

# Token usage metrics
print(f"Input: {response.usage.input_tokens}, Output: {response.usage.output_tokens}")

Note: Examples use openai/gpt-5.3-codex, or another catalog model configured for Responses compatibility.

Request Parameters

The DEVUP AI gateway accepts native Responses parameters and validates them before forwarding to the upstream provider.

Parameter	Type	Requirement	Description
model	string	Required	Identifier of a Responses-compatible catalog model.
input	string \| array	Optional	The text prompt or array of input content items to process.
instructions	string	Optional	System-level instructions directing the model's behavior.
max_output_tokens	integer	Optional	Ceiling on generated output tokens. Must be a positive integer within model capabilities.
reasoning	object	Optional	Nested reasoning object. Supports `effort` (accepted values vary by model; see Reasoning Configuration below).
temperature	number	Optional	Sampling temperature. Passed through to compatible providers.
top_p	number	Optional	Nucleus sampling threshold.
user	string	Optional	End-user identifier for abuse monitoring and logging.
metadata	object	Optional	Developer metadata key-value pairs attached to the request.
store	boolean	Forced False	DEVUP AI strictly forces `store: false` upstream to ensure zero data retention. Client values are overridden.
stream	boolean	Omit / False	Streaming is not supported. Must be omitted or `false`. Setting `true` returns HTTP 400.

Reasoning Configuration

In the Responses API, reasoning parameters must be nested under the reasoning object. Top-level parameters such as Chat's reasoning_effort are explicitly rejected with an HTTP 400 error. Accepted effort levels depend on the model:

Model	Accepted Values
openai/gpt-5.3-codex	none, low, medium, high, xhigh
openai/gpt-5.5-pro	medium, high (none and low not accepted)
openai/gpt-5.4-pro	medium, high (none and low not accepted)

json

{
  "model": "openai/gpt-5.3-codex",
  "input": "Prove whether P equals NP or explain why the problem remains unresolved.",
  "reasoning": {
    "effort": "high"
  },
  "max_output_tokens": 2048
}

Native Responses Output

The endpoint returns the provider-native Responses object rather than Chat Completions choices[]. DEVUP AI cleanses provider infrastructure headers, preserves structured content parts, and attaches canonical billing telemetry under _devup.

json

{
  "id": "resp_01j8k9m0n1p2q3r4s5t6u7v8w9",
  "object": "response",
  "created_at": 1700000000,
  "model": "openai/gpt-5.3-codex",
  "status": "completed",
  "output": [
    {
      "id": "msg_01j8k9m0n1p2q3r4s5t6u7v8wa",
      "type": "message",
      "role": "assistant",
      "content": [
        {
          "type": "text",
          "text": "Quantum key distribution (QKD) leverages the fundamental quantum principle..."
        }
      ]
    }
  ],
  "usage": {
    "input_tokens": 24,
    "output_tokens": 182,
    "total_tokens": 206,
    "input_tokens_details": {
      "cached_tokens": 0,
      "cache_write_tokens": 0
    },
    "output_tokens_details": {
      "reasoning_tokens": 0
    }
  },
  "_devup": {
    "cost_dzd": "<settled_cost_dzd>",
    "balance_dzd": "<remaining_balance_dzd>"
  }
}

Usage Metrics & Token Accounting

The usage object reports detailed token metrics normalized by DEVUP AI:

input_tokens

Total prompt tokens counted for the input request.

output_tokens

Total tokens generated by the model (including reasoning tokens).

input_tokens_details.cached_tokens

Prompt tokens served from cache with discounted billing rates.

output_tokens_details.reasoning_tokens

Internal reasoning tokens generated prior to final answer output.

Model Compatibility

Responses API compatibility is capability-based. Not all models in the catalogue support the Responses protocol. To use this endpoint, the target model must support the native Responses protocol and input-token preflight counter.

If a request targets a model whose provider destination does not support the Responses protocol, the gateway fails safely with an HTTP 400 unsupported_destination error before reserving funds or invoking upstream resources. Check the Model Catalog for compatible model identifiers.

Error Reference

The Responses API adheres to the standard DEVUP AI error envelope. For the complete reference of gateway error codes, visit the API Error Reference.

Status	Error Code	Description & Resolution
400	missing_model	The `model` parameter is missing or empty. Provide a valid model string.
400	streaming_not_supported	The request specified `stream: true`. Set `stream: false` or omit the parameter.
400	unsupported_parameter	An unsupported parameter was provided. Top-level `reasoning_effort` must be moved to `reasoning: { effort }`; multi-turn continuation parameters are not supported (provide full conversation in `input`).
400	unsupported_destination	The selected model does not support the Responses protocol. Select a compatible model from the catalog.
400	invalid_request_error	`max_output_tokens` must be a positive integer within model limits.
401	missing_api_key / invalid_api_key	Provide a valid active API key in the `Authorization: Bearer` header.
402	insufficient_balance	Your DZD balance is insufficient for the request reservation. Top up via the dashboard.
404	model_not_found	The requested model identifier was not found in the DEVUP AI catalog.
429	rate_limit_exceeded	Standard per-account rate limit (100 req/min) reached. Back off and retry.

Related Guides

Chat Completions

OpenAI-compatible chat completion endpoint.

OpenAI Compatibility

Parameter mapping and model rules.

Model Catalog

Browse all supported foundation models.

Error Reference

Status codes and troubleshooting.