API reference/Request handling
Protocol conversion & parameter handling
The gateway converts each request to the model's native format and removes parameters the model rejects or ignores. So a request that returns 400 from the official API can return 200 through Wokey. This page explains that handling by endpoint and model.
On this pageexpand_more
Principleslink
- The gateway removes or clamps two kinds of fields: those the target model is certain to reject, and those that have no effect on it. The request is then sent upstream as usual. So a request that returns 400 from the official API can return 200 through Wokey. For example, Claude Sonnet 5.5 with
temperature: 0.5returns 400 from the official API; through Wokey,temperatureis removed and the request completes. - A request that has no equivalent form is not rewritten. It goes upstream as is, and the upstream returns the 400. For example, Claude Sonnet 5.5 with
tool_choiceset toanyortool. - The sections below list common parameter handling by model. Rules for a model change as its upstream changes.
To confirm a response really came from the official API, turn on Official direct verification for your key. About the verifiable API →
Sampling parameterslink
Most current reasoning models set their own sampling and ignore or reject parameters such as temperature. The table shows how each model is handled.
| Model | Handling |
|---|---|
| Claude Opus 4.6, Sonnet 4.6, Sonnet 4.5, Haiku 4.5 | temperature is forwarded, clamped to 0–1. top_p and top_k are not forwarded. |
| Other Claude models | temperature, top_p, and top_k are not forwarded. |
| GPT | temperature is not forwarded. Called through Chat Completions or Messages, top_p is not forwarded either. GPT-6 Astra and GPT-6.1 Sol never receive top_p, logprobs, or top_logprobs, whichever endpoint you call. |
| Grok | Through Chat Completions, sampling parameters are forwarded as is; Grok 4.3, 4.5, 4.6, and 4.7 do not receive stop, presence_penalty, or frequency_penalty. Through Responses or Messages, temperature and top_p are not forwarded. |
| Kimi K3, K3.1 Pro | The gateway validates first: temperature must be within 0–1, top_p must be 0.95, presence_penalty and frequency_penalty must be 0, and n must be 1; otherwise it returns 400. After validation, temperature, top_p, and presence_penalty are not forwarded. |
| Other models | temperature is usually not forwarded; top_p and other parameters are. |
Thinking and reasoning effortlink
Thinking settings a model does not accept are rewritten or removed. Once removed, the model uses its default adaptive thinking.
| Model | Handling |
|---|---|
| Claude Sonnet 5.5 | thinking: {"type": "disabled"} becomes between_tools at effort low, medium, high, or unset, and is removed at xhigh and max. enabled and manual budget_tokens are removed. |
| Claude Haiku 5.5 | disabled is kept at effort low, medium, high, or unset, and removed at xhigh and max. enabled and manual budget_tokens are removed. |
| Claude Opus 5.5, Fable 5 series | Only adaptive is accepted; any other thinking setting is removed. |
| Claude Opus 5 | disabled is removed at effort xhigh and max. |
| GPT-6 Astra, GPT-6.1 Sol, GPT-5.3-Codex | Effort none or minimal is raised to low. |
| DeepSeek | When the Responses endpoint forces a tool call (tool_choice is required or names a tool), thinking is turned off (reasoning.effort: none). The upstream does not support forced tool calls while thinking. |
Output lengthlink
- Claude: through Chat Completions or Responses, the output limit defaults to 4096. Through Messages,
max_tokensis required; without it the gateway returns 400 and nothing is sent upstream. - Gemini: defaults to 65536.
- GPT:
max_tokensandmax_output_tokensare not forwarded; the upstream decides.
Other handlinglink
- Calling Claude through Chat Completions,
reasoning_efforthas no effect; Claude thinks the way the model does by default. - Calling GPT through Chat Completions or Messages, reasoning effort defaults to
medium. - Calling Claude or GPT through Chat Completions,
response_formathas no effect. - Calling Claude through Chat Completions or Responses,
parallel_tool_callshas no effect. provider: a Wokey extension used only to choose providers; it is never sent upstream.metadata: not forwarded upstream.- Claude
speed(fast mode): not supported. The gateway does not forward it; the request runs at standard speed and the response reportsusage.speedasstandard. - GPT
userandsafety_identifier: not forwarded. - Assistant prefill: some Claude channels do not accept a request that ends with an assistant message. The gateway turns the whole conversation into one user message asking the model to continue from the prefill without repeating it. The multi-turn structure is not kept in that case.