Parameter Support by Model

These tables show which request parameters take effect for each model family. They are client-facing fields you send through any API format; the router translates each into whatever the model needs.

Legend: ✅ supported · ⚠️ conditional (see Per-Model Details) · — not supported (silently dropped).

Any parameter not listed here is silently dropped regardless of which format it arrives in. When a parameter is dropped, the request still succeeds — the field simply has no effect.

Core

Parameter	Type	GPT	Claude	Gemini	Other
model	string	✅	✅	✅	✅
messages	array	✅	✅	✅	✅
temperature	float	⚠️	✅	✅	✅
top_p	float	⚠️	✅	✅	✅
max_tokens	integer	✅	✅	✅	✅
max_completion_tokens	integer	✅	✅	✅	✅
stop	string/array	⚠️	✅	✅	✅
stream	boolean	✅	✅	✅	✅
stream_options	object	✅	✅	✅	✅

max_tokens is automatically converted to max_completion_tokens for GPT-5 models.

Tool use

Parameter	Type	GPT	Claude	Gemini	Other
tools	array	✅	✅	✅	✅
tool_choice	string/object	✅	✅	✅	✅
parallel_tool_calls	boolean	✅	✅	✅	⚠️
functions (legacy)	array	✅	—	—	—
function_call (legacy)	string/object	✅	—	—	—

Reasoning & extended thinking

Parameter	Type	GPT	Claude	Gemini	Other
thinking	object	—	✅	✅	—
reasoning_effort	string	✅	✅	✅	—

reasoning_effort and thinking are normalised per model — the router maps whichever you send to the target model's native mode. See Per-Model Details.

Output control

Parameter	Type	GPT	Claude	Gemini	Other
response_format	object	✅	✅	✅	✅
n	integer	✅	—	—	—
seed	integer	✅	—	✅	—
user	string	✅	✅	✅	✅
web_search_options	object	✅	—	—	—

Sampling & penalties

Parameter	Type	GPT	Claude	Gemini	Other
frequency_penalty	float	✅	—	⚠️	✅
presence_penalty	float	✅	—	⚠️	✅
logit_bias	object	✅	—	—	—

Penalties are not available on Gemini preview and Gemini 3 models.

Logprobs

Parameter	Type	GPT	Claude	Gemini	Other
logprobs	boolean	⚠️	—	—	—
top_logprobs	integer	⚠️	—	—	—

Logprobs apply to GPT models, and on GPT-5 only when reasoning_effort = "none".

Extended parameters

These are not top-level fields. Pass them inside extra_body; each is extracted by an allowlist before being merged into the outbound request. (service_tier is the exception — it is a standard top-level field.)

Parameter	Via	GPT	Claude	Gemini	Other
modalities	extra_body	✅	—	—	—
audio	extra_body	✅	—	—	—
prediction	extra_body	✅	—	—	—
service_tier	top-level	✅	—	—	—
top_k	extra_body	—	✅	✅	⚠️

top_k is not part of the standard request body — pass it via extra_body; it is forwarded only to models that support it natively.