OpenAI Chat Completions on a PopNow text model

Accepts an OpenAI Chat Completions request. messages, tools, tool_choice, parallel_tool_calls, response_format, max_tokens (or max_completion_tokens), temperature, top_p, top_k, seed and stop map onto the model's public input fields of the same name when the model declares them (each model page lists its own set); stream, stream_options, user, metadata and store are handled by this layer. Pure sampling parameters the model does not declare (temperature, top_p, top_k, min_p, top_a, frequency_penalty, presence_penalty, repetition_penalty), n: 1, an empty stop, stop on a model without stop sequences, reasoning_effort on a model without reasoning levels, and a reasoning object that cannot be translated are ignored, and the response lists them in the X-PopNow-Ignored-Params header. Values the model declares but cannot take as sent are changed to the nearest accepted value and listed as name=value in the X-PopNow-Adjusted-Params header: a sampling value outside the model's range is clamped to the bound, a stop list longer than the model allows keeps its first entries, a reasoning_effort level the model does not offer becomes the nearest level it does (the lower one on a tie), and reasoning.effort (or reasoning.enabled: false, as none) becomes reasoning_effort. Any other parameter is forwarded to the model's input schema and rejected with 400 when the model does not declare it.

stream: true returns a Server-Sent Events stream of chat.completion.chunk objects terminated by data: [DONE]. Every chunk has a non-empty choices array and each choice ends with exactly one chunk carrying finish_reason. Usage follows OpenAI: a stream carries no usage unless stream_options.include_usage is true, in which case one extra chunk with choices: [] and the final usage comes right before [DONE] and every other chunk has usage: null. stream: false returns one chat.completion object that always has usage. Billing: chat models are priced per token in credits (1 credit = $0.001), listed per 1M input and output tokens in credits on GET /api/v1/models and GET /v1/models. When the request is accepted, the most it can cost is held from your balance, computed from the input and max_tokens (the model's maximum output when you omit it, so set max_tokens to keep holds small). When the reply ends you are charged its actual usage in fractional credits, with no per-request minimum, and the rest of the hold is released. A balance below the hold, or a key spend limit that would be exceeded, returns 402 before anything is sent to the model. A request that fails or that the model refuses is refunded in full. The X-PopNow-Task-Id response header names the task; GET /api/v1/jobs/recordInfo shows the final charge in cost (USD) and exactCredits. Message text is not kept after the charge settles. Requests are forwarded to the model as sent and each model's own usage policy applies.

A non-streaming call that is still running after about 30 seconds is kept open: the 200 status and the X-PopNow-Keepalive: 1 header go out first, followed by a newline every 15 seconds and then the JSON body. A failure after that point is the usual {"error": {...}} object in the body of that 200 response, so check for an error key when the header is present. The same applies to /v1/responses, /v1/messages (Anthropic error object) and :generateContent (Gemini error object, whose error.code keeps the HTTP status the error would have had).

Errors a client can act on: an unknown model returns 404 with code: model_not_found, the ID shape (publisher/model/chat) and the closest callable chat model; a model that is not a chat model returns 400 with param: model; a field or message part the model does not accept (for example an image_url part on a text-only model) returns 400 with code: unsupported_parameter and param pointing at it; a content-policy refusal returns 400 with code: content_rejected.