spb/llm-api-toolkits

1<!-- Generated by build-skill.mjs from live API probes and official documentation (2026-11-10). Do not edit by hand. -->2# What each model accepts34Every cell is an observed API response (2026-11-10). "rejected" means HTTP 400 (or 404 for an unsupported endpoint).56## Responses API78| Model | Reasoning effort levels | Default effort is `none` | `temperature` / `top_p` | `text.verbosity` | Code interpreter |9|---|---|---|---|---|---|10| `gpt-6-sol` | none, low, medium, high, xhigh, max | no | only with effort `none` | low, medium, high | yes |11| `gpt-6.1-terra` | none, low, medium, high, xhigh, max | no | only with effort `none` | low, medium, high | yes |12| `gpt-6.1-sol` | low, medium, high, xhigh, max | no | **never** | low, medium, high | yes |13| `gpt-6-luna` | none, low, medium, high, xhigh, max | no | only with effort `none` | low, medium, high | yes |14| `gpt-5.6-terra` | none, low, medium, high, xhigh, max | no | only with effort `none` | low, medium, high | yes |15| `gpt-5.6-sol` | none, low, medium, high, xhigh, max | no | only with effort `none` | low, medium, high | yes |16| `gpt-6-astra` | low, medium, high, xhigh, max | no | **never** | low, medium, high | yes |17| `gpt-5.5` | none, low, medium, high, xhigh | no | only with effort `none` | low, medium, high | yes |18| `gpt-5.4` | none, low, medium, high, xhigh | yes | only with effort `none` | low, medium, high | yes |19| `gpt-5.4-mini` | none, low, medium, high, xhigh | yes | only with effort `none` | low, medium, high | yes |20| `gpt-5.4-nano` | none, low, medium, high, xhigh | yes | only with effort `none` | low, medium, high | yes |21| `gpt-5.3-codex` | none, low, medium, high, xhigh | yes | only with effort `none` | low, medium, high | yes |22| `gpt-5.2` | none, low, medium, high, xhigh | yes | only with effort `none` | low, medium, high | yes |23| `gpt-5.6-luna` | none, low, medium, high, xhigh, max | no | only with effort `none` | low, medium, high | yes |24| `gpt-5.1` | none, low, medium, high | yes | only with effort `none` | low, medium, high | yes |25| `gpt-5.2-pro` | medium, high, xhigh | no | **never** | low, medium, high | **rejected** |26| `gpt-5-mini` | minimal, low, medium, high | no | **never** | low, medium, high | yes |27| `gpt-5-nano` | minimal, low, medium, high | no | **never** | low, medium, high | yes |28| `gpt-5` | minimal, low, medium, high | no | **never** | low, medium, high | yes |29| `gpt-4.1` | **not a reasoning model** | — | always | medium | yes |30| `gpt-4.1-mini` | **not a reasoning model** | — | always | medium | yes |31| `gpt-4o` | **not a reasoning model** | — | always | medium | yes |32| `gpt-4o-mini` | **not a reasoning model** | — | always | medium | yes |33| `o3` | low, medium, high | no | **never** | medium | yes, `tool_choice: auto` only |34| `gpt-5-pro` | high | no | **never** | low, medium, high | **rejected** |35| `chat-latest` | medium | no | **never** | medium | yes |36| `gpt-5.4-pro` | medium, high, xhigh | no | **never** | low, medium, high | yes |37| `gpt-5.5-pro` | medium, high, xhigh | no | **never** | low, medium, high | yes |38| `o3-pro` | low, medium, high | no | **never** | medium | yes, `tool_choice: auto` only |3940Accepted on the Responses API by every probed model: `instructions`, system and developer roles, strict structured outputs (`text.format` json_schema), `json_object`, function tools with `tool_choice` auto / required / none / forced function, `parallel_tool_calls`, web search, image input, `store: false`, `truncation`, `prompt_cache_key`, `prompt_cache_retention`, `metadata`, `max_tool_calls`, background mode, `include: ["reasoning.encrypted_content"]`. `max_output_tokens` below 16 is rejected everywhere. `top_logprobs` is rejected by every reasoning model.4142## Chat Completions4344| Model | Served | Legacy `max_tokens` | Custom `temperature` | `stop` | Function tools | `logprobs` |45|---|---|---|---|---|---|---|46| `gpt-6-sol` | yes | **rejected** | only with effort `none` | **rejected** | only with `reasoning_effort: "none"` | **rejected** |47| `gpt-6.1-terra` | yes | **rejected** | only with effort `none` | **rejected** | only with `reasoning_effort: "none"` | **rejected** |48| `gpt-6.1-sol` | yes | **rejected** | **never** | **rejected** | **rejected** — use Responses | **rejected** |49| `gpt-6-luna` | yes | **rejected** | only with effort `none` | **rejected** | only with `reasoning_effort: "none"` | **rejected** |50| `gpt-5.6-terra` | yes | **rejected** | only with effort `none` | **rejected** | only with `reasoning_effort: "none"` | **rejected** |51| `gpt-5.6-sol` | yes | **rejected** | only with effort `none` | **rejected** | only with `reasoning_effort: "none"` | **rejected** |52| `gpt-6-astra` | yes | **rejected** | **never** | **rejected** | **rejected** — use Responses | **rejected** |53| `gpt-5.5` | yes | **rejected** | only with effort `none` | **rejected** | yes | **rejected** |54| `gpt-5.4` | yes | **rejected** | only with effort `none` | **rejected** | yes | yes |55| `gpt-5.4-mini` | yes | **rejected** | only with effort `none` | **rejected** | yes | yes |56| `gpt-5.4-nano` | yes | **rejected** | only with effort `none` | **rejected** | yes | yes |57| `gpt-5.3-codex` | **no — Responses only** | — | — | — | — | — |58| `gpt-5.2` | yes | **rejected** | only with effort `none` | **rejected** | yes | yes |59| `gpt-5.6-luna` | yes | **rejected** | only with effort `none` | **rejected** | only with `reasoning_effort: "none"` | **rejected** |60| `gpt-5.1` | yes | **rejected** | only with effort `none` | **rejected** | yes | yes |61| `gpt-5.2-pro` | **no — Responses only** | — | — | — | — | — |62| `gpt-5-mini` | yes | **rejected** | **never** | **rejected** | yes | **rejected** |63| `gpt-5-nano` | yes | **rejected** | **never** | **rejected** | yes | **rejected** |64| `gpt-5` | yes | **rejected** | **never** | **rejected** | yes | **rejected** |65| `gpt-4.1` | yes | yes | always | yes | yes | yes |66| `gpt-4.1-mini` | yes | yes | always | yes | yes | yes |67| `gpt-4o` | yes | yes | always | yes | yes | yes |68| `gpt-4o-mini` | yes | yes | always | yes | yes | yes |69| `o3` | yes | **rejected** | **never** | **rejected** | yes | **rejected** |70| `gpt-5-pro` | **no — Responses only** | — | — | — | — | — |71| `chat-latest` | yes | **rejected** | **never** | **rejected** | yes | **rejected** |72| `gpt-5.4-pro` | **no — Responses only** | — | — | — | — | — |73| `gpt-5.5-pro` | **no — Responses only** | — | — | — | — | — |74| `o3-pro` | **no — Responses only** | — | — | — | — | — |7576## Exact error texts7778- `max_output_8`: Invalid 'max_output_tokens': integer below minimum value. Expected a value >= 16, but got 8 instead.79- `chat_temperature`: Unsupported value: 'temperature' does not support 0.5 with this model. Only the default (1) value is supported.80- `chat_logprobs`: Unsupported parameter: 'logprobs' is not supported with this model.81- `chat_max_tokens_legacy`: Unsupported parameter: 'max_tokens' is not supported with this model. Use 'max_completion_tokens' instead.82- `top_p`: Unsupported parameter: 'top_p' is not supported with this model.83- `chat_stop`: Unsupported parameter: 'stop' is not supported with this model.84- `chat_tools`: Function tools with reasoning_effort are not supported for <model> in /v1/chat/completions. To use function tools, use /v1/responses or set reasoning_effort to 'none'.85- `effort_minimal`: Unsupported value: 'minimal' is not supported with the '<model>' model. Supported values are: 'none', 'low', 'medium', 'high', 'xhigh', and 'max'.86- `temperature`: Unsupported parameter: 'temperature' is not supported with this model.87- `top_logprobs`: logprobs are not supported with reasoning models.88- `effort_minimal`: Unsupported value: 'minimal' is not supported with the '<model>' model. Supported values are: 'low', 'medium', 'high', 'xhigh', and 'max'.89- `effort_none`: Unsupported value: 'none' is not supported with the '<model>' model. Supported values are: 'low', 'medium', 'high', 'xhigh', and 'max'.90- `chat_tools_effort_none`: Unsupported value: 'reasoning_effort' does not support 'none' with this model. Supported values are: 'low', 'medium', 'high', and 'xhigh'.91- `effort_minimal`: Unsupported value: 'minimal' is not supported with the '<model>' model. Supported values are: 'none', 'low', 'medium', 'high', and 'xhigh'.92- `effort_max`: Unsupported value: 'max' is not supported with the '<model>' model. Supported values are: 'none', 'low', 'medium', 'high', and 'xhigh'.93- `chat_basic`: This model is not supported in the v1/chat/completions endpoint. Use the v1/responses endpoint instead.94- `chat_logprobs`: You are not allowed to request logprobs from this model95- `service_tier_flex`: Flex is not available for this model.96- `effort_max`: Unsupported value: 'max' is not supported with the '<model>' model. Supported values are: 'none', 'low', 'medium', and 'high'.97- `effort_minimal`: Unsupported value: 'minimal' is not supported with the '<model>' model. Supported values are: 'none', 'low', 'medium', and 'high'.98- `effort_xhigh`: Unsupported value: 'xhigh' is not supported with the '<model>' model. Supported values are: 'none', 'low', 'medium', and 'high'.99- `chat_developer_role`: This is not a chat model and thus not supported in the v1/chat/completions endpoint. Did you mean to use v1/completions?100- `effort_none`: Unsupported value: 'none' is not supported with the '<model>' model. Supported values are: 'medium', 'high', and 'xhigh'.101- `effort_max`: Unsupported value: 'max' is not supported with the '<model>' model. Supported values are: 'medium', 'high', and 'xhigh'.102- `effort_minimal`: Unsupported value: 'minimal' is not supported with the '<model>' model. Supported values are: 'medium', 'high', and 'xhigh'.103- `effort_low`: Unsupported value: 'low' is not supported with the '<model>' model. Supported values are: 'medium', 'high', and 'xhigh'.104- `code_interpreter`: Tool 'code_interpreter' is not supported with <model>.105- `effort_xhigh`: Unsupported value: 'xhigh' is not supported with the '<model>' model. Supported values are: 'minimal', 'low', 'medium', and 'high'.106- `effort_max`: Unsupported value: 'max' is not supported with the '<model>' model. Supported values are: 'minimal', 'low', 'medium', and 'high'.107- `effort_none`: Unsupported value: 'none' is not supported with the '<model>' model. Supported values are: 'minimal', 'low', 'medium', and 'high'.108- `chat_tools_effort_none`: Unsupported value: 'reasoning_effort' does not support 'none' with this model. Supported values are: 'minimal', 'low', 'medium', and 'high'.109- `verbosity_low`: Unsupported value: 'low' is not supported with the '<model>' model. Supported values are: 'medium'.110- `effort_low`: Unsupported parameter: 'reasoning.effort' is not supported with this model.111- `verbosity_high`: Unsupported value: 'high' is not supported with the '<model>' model. Supported values are: 'medium'.112- `chat_reasoning_effort`: Unrecognized request argument supplied: reasoning_effort113- `service_tier_flex`: Invalid service_tier argument114- `service_tier_flex`: There was an issue with your request. Please check your inputs and try again115- `effort_xhigh`: Unsupported value: 'xhigh' is not supported with the '<model>' model. Supported values are: 'low', 'medium', and 'high'.116- `effort_none`: Unsupported value: 'none' is not supported with the '<model>' model. Supported values are: 'low', 'medium', and 'high'.117- `code_interpreter`: Tool choices other than 'auto' are not supported with model '<model>' and the following tool types: 'code_interpreter'.118- `effort_max`: Unsupported value: 'max' is not supported with the '<model>' model. Supported values are: 'low', 'medium', and 'high'.119- `effort_minimal`: Unsupported value: 'minimal' is not supported with the '<model>' model. Supported values are: 'low', 'medium', and 'high'.120- `web_search`: Tool choices other than 'auto' are not supported with model '<model>' and the following tool types: 'web_search_preview'.121- `chat_temperature`: This model is only supported in v1/responses and not in v1/chat/completions.122- `effort_none`: Unsupported value: 'none' is not supported with the '<model>' model. Supported values are: 'high'.123- `effort_max`: Unsupported value: 'max' is not supported with the '<model>' model. Supported values are: 'high'.124- `effort_xhigh`: Unsupported value: 'xhigh' is not supported with the '<model>' model. Supported values are: 'high'.125- `effort_low`: Unsupported value: 'low' is not supported with the '<model>' model. Supported values are: 'high'.126- `effort_medium`: Unsupported value: 'medium' is not supported with the '<model>' model. Supported values are: 'high'.127- `effort_minimal`: Unsupported value: 'minimal' is not supported with the '<model>' model. Supported values are: 'high'.128- `chat_reasoning_effort`: Unsupported value: 'reasoning_effort' does not support 'low' with this model. Supported values are: 'medium'.129- `effort_minimal`: Unsupported value: 'minimal' is not supported with the '<model>' model. Supported values are: 'medium'.130- `effort_xhigh`: Unsupported value: 'xhigh' is not supported with the '<model>' model. Supported values are: 'medium'.131- `effort_none`: Unsupported value: 'none' is not supported with the '<model>' model. Supported values are: 'medium'.132- `effort_max`: Unsupported value: 'max' is not supported with the '<model>' model. Supported values are: 'medium'.133- `chat_temperature_effort_none`: Unsupported value: 'reasoning_effort' does not support 'none' with this model. Supported values are: 'medium'.134