Parameters
How sampling and output parameters apply on each model family, and how to request a service tier.
OhMyGPT adds no defaults or limits of its own to sampling and output parameters. The model's vendor sets them.
On the native protocol
On a model's native protocol, every parameter reaches the model as you sent it, including vendor-specific ones such as Mistral's safe_prompt or Qwen's enable_thinking. The vendor's defaults and limits apply, and if the vendor rejects a value, you get its error message. The exceptions are sampling parameters on OpenAI reasoning models and on recent Claude models.
Sampling on OpenAI reasoning models
OpenAI's reasoning models reject sampling parameters while they reason. On those requests OhMyGPT doesn't send temperature, top_p, logprobs or top_logprobs (on Responses: temperature, top_p, top_logprobs), the request runs without them, and the X-Parameters-Dropped response header lists the ones left out. This holds on every protocol you call these models through, and for each line of a Batch input file.
Whether a model is reasoning depends on the reasoning effort you send and the model's default, shown on each model's page:
- Models that default to
none, such as GPT-5.1, GPT-5.2 and GPT-5.4, keep the parameters unless you set another effort. - Models that reason by default, such as GPT-5.5, GPT-5.6 and GPT-6 Sol, keep them only when you set
reasoning_effort(on Responses,reasoning.effort) tonone. - Models without a
nonelevel, such as GPT-5, GPT-5.3-Codex and GPT-6 Astra, never receive them.
curl -i https://api.ohmygpt.com/v1/chat/completions \
-H "Authorization: Bearer $OHMYGPT_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "openai/gpt-5.5",
"temperature": 0,
"messages": [{"role": "user", "content": "Say hi."}]
}'x-parameters-dropped: temperatureA stream that sent a keep-alive line before its first output carries it as a comment line ahead of the first event instead: : x-parameters-dropped: temperature.
Sampling on recent Claude models
Claude Opus 4.7 and the Claude models released after it don't accept temperature, top_p or top_k. These are Opus 4.7, Opus 4.8, Opus 5, Opus 5.5, Sonnet 5, Sonnet 5.5, Haiku 5.5 and the Fable 5 family. OhMyGPT doesn't send these parameters to them on any protocol, the request runs without them, and the X-Parameters-Dropped response header lists the ones left out. Earlier Claude models, such as Opus 4.6 and Haiku 4.5, receive them as sent.
Claude and Gemini on Chat Completions
When you call Claude or Gemini through Chat Completions, these parameters take effect under the vendor's own name. Cells marked — have no equivalent on that model:
| Chat Completions | Claude | Gemini |
|---|---|---|
max_tokens, max_completion_tokens | max_tokens | maxOutputTokens |
temperature, top_p, top_k | temperature, top_p, top_k | temperature, topP, topK |
stop | stop_sequences | stopSequences |
frequency_penalty, presence_penalty | — | frequencyPenalty, presencePenalty |
seed | — | seed |
response_format with json_schema | output_config.format | responseMimeType and schema |
response_format with json_object | — | responseMimeType: "application/json" |
modalities with audio or image | — | responseModalities |
logprobs, top_logprobs, logit_bias, verbosity, audio, web_search_options, min_p, top_a, repetition_penalty | — | — |
n greater than 1 | 400 | 400 |
tools, tool_choice | tools, tool_choice | functionDeclarations, toolConfig |
parallel_tool_calls | disable_parallel_tool_use | — |
user | metadata.user_id | — |
reasoning_effort, thinking | see Thinking | see Thinking |
service_tier | see Service tiers | see Service tiers |
Claude requires max_tokens; if you leave it out, OhMyGPT sends the model's maximum output.
A model without an equivalent doesn't receive the parameter, and the request runs without it, as Anthropic's own OpenAI SDK compatibility does for fields Claude lacks. So one request body works across models, but the output follows the model's defaults for that setting, so Claude ignores seed. The exception is n: these models return one choice per request, so n above 1 returns 400 naming n before the request reaches the model, and nothing is charged. If a setting must take effect, send it to a model that has it. Whether a model accepts a particular value of a parameter it has is up to the model; its own error comes back to you as is.
For JSON output from Claude, use response_format with a json_schema:
curl https://api.ohmygpt.com/v1/chat/completions \
-H "Authorization: Bearer $OHMYGPT_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "anthropic/claude-haiku-4-5",
"max_tokens": 200,
"messages": [{"role": "user", "content": "Give me a color and its hex code."}],
"response_format": {
"type": "json_schema",
"json_schema": {
"name": "color",
"schema": {
"type": "object",
"properties": {"name": {"type": "string"}, "hex": {"type": "string"}},
"required": ["name", "hex"],
"additionalProperties": false
}
}
}
}'"message": { "role": "assistant", "content": "{\"hex\": \"#FF6B6B\", \"name\": \"Coral Red\"}" }Service tiers
Some models offer service tiers besides the standard one, each at its own price. The vendor defines what each tier provides. GET /v1/models lists the tiers that each provider of a model offers:
curl -s https://api.ohmygpt.com/v1/models/google/gemini-3.8-flash \
| jq -r '.providers[] | [.provider, ([.pricing.rules[]?.condition.service_tier // empty, .pricing.variants[]?.name] | unique - ["default", "batch"] | join(" "))] | @tsv'google flex priority
vertex flexThe command leaves out default, which is the standard tier, and batch, which prices Batch jobs. The same pricing object holds the price of each tier, in a rule whose condition.service_tier names the tier or in a variant of that name.
Request a tier that the model lists with the field of your protocol:
| Protocol | Models | Field |
|---|---|---|
| Chat Completions, Responses | GPT, Gemini | "service_tier": "flex" or "priority" |
| Gemini | Gemini | "serviceTier": "flex" or "priority" |
| Messages | Claude | "speed": "fast", as in Anthropic's fast mode |
curl https://api.ohmygpt.com/v1/chat/completions \
-H "Authorization: Bearer $OHMYGPT_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "google/gemini-3.8-flash",
"service_tier": "flex",
"messages": [{"role": "user", "content": "Say hi."}]
}'Claude models called through Chat Completions or Responses don't receive flex or priority.
On a model's native protocol, the response names the tier that served the request:
| Response | Field |
|---|---|
| GPT on Chat Completions or Responses | service_tier |
| Gemini on the Gemini endpoint | usageMetadata.serviceTier or usageMetadata.trafficType |
| Claude on Messages | usage.speed |
The charge follows the tier that served the request. If a request for another tier is served at the standard tier, you pay the standard price. The receipt shows the unit prices you paid, in cost.lines.
Routing
provider on Chat Completions, Responses and Messages chooses which provider serves the model. It is read by OhMyGPT and does not reach the model. See Provider routing.
Still stuck? Live chat · [email protected] · Telegram group