Responses API

POST https://llmoxy.com/v1/responses 接收 JSON 請求。請求頭:

Authorization: Bearer <LLMOXY_API_KEY>
Content-Type: application/json

閘道把正文解析成固定結構。model 為空,或正文裡沒有 input,請求會被拒絕。max_output_tokens 大於 1,073,741,823 時也會被拒絕。background 不在這個結構裡。

沒有打開請求體透傳時,只保留下表欄位,並預設去掉 service_tier、safety_identifier 和 stream_options.include_obfuscation。store 預設保留。可空數字寫成 0、stream 寫成 false 時仍會發出。stream_options 裡的布林值在重新組包時,false 會被省略。表以外的欄位不會發出。

請求欄位

欄位類型必填閘道行為
modelstring是非空模型 ID。
inputstring 或 array是必須出現。字串按一段輸入文字計。陣列元素可帶 role。content 為字串時按輸入文字計;為陣列時識別 input_text、input_image、input_file。image_url 和 file_url 可以是字串,或帶 url 的物件。
includeJSON否原樣保留。
conversationJSON否原樣保留。
context_managementJSON否原樣保留。
instructionsJSON否原樣保留。常見寫法是字串。
max_output_tokensnumber否可空。顯式 0 會保留。
top_logprobsnumber否可空。顯式 0 會保留。
metadataJSON否原樣保留。
parallel_tool_callsJSON否原樣保留。顯式 false 會保留。
previous_response_idstring否空字串省略。
reasoning.effortstring否空字串省略。閘道不校驗取值。
reasoning.summarystring否空字串省略。閘道不校驗取值。
service_tierstring否預設去掉。
storeJSON否預設保留。顯式 false 會保留。
prompt_cache_keyJSON否原樣保留。
prompt_cache_retentionJSON否原樣保留。
safety_identifierJSON否預設去掉。
streamboolean否缺省按非流式處理。顯式 false 會保留。
stream_options.include_usageboolean否重新組包時 false 省略。
stream_options.include_obfuscationboolean否預設去掉。重新組包時 false 省略。
temperaturenumber否可空。顯式 0 會保留。
textJSON否原樣保留。
tool_choiceJSON否原樣保留。
toolsJSON否原樣保留。
top_pnumber否可空。顯式 0 會保留。
truncationJSON否原樣保留。
userJSON否原樣保留。
max_tool_callsnumber否可空。顯式 0 會保留。
promptJSON否原樣保留。
enable_thinkingJSON否原樣保留。
presetJSON否原樣保留。

grok-4.6 與 grok-4.7

2026-10-03 對 https://llmoxy.com/v1/responses 的流式呼叫裡,grok-4.6 和 grok-4.7 都返回 HTTP 200,並完成同一組事件。

模型HTTP響應裡的 modelstatus正文input / output / total
grok-4.6200grok-4.6completedpong212 / 98 / 310
grok-4.7200grok-4.7completedpong1248 / 55 / 1303

grok-4.6 的 input_tokens_details.cached_tokens 為 128,output_tokens_details.reasoning_tokens 為 97。grok-4.7 分別為 1152 和 54。

正文位於 output 中 type 為 message 的項,content 裡 type 為 output_text 的 text。兩個模型都會先輸出 type 為 reasoning 的項。response.completed 裡該 reasoning 項的 status 仍是 in_progress。

當前這兩個模型的請求打開了請求體透傳,所以下一節的最小 JSON 按客戶端原文發出。

最小成功請求

grok-4.6 使用同一正文,只把 model 換成 grok-4.6。

curl https://llmoxy.com/v1/responses \
  -H "Authorization: Bearer <LLMOXY_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "grok-4.7",
    "input": "Reply with exactly: pong",
    "max_output_tokens": 64,
    "stream": true
  }'
BASH

響應的 Content-Type 為 text/event-stream。每條事件是一行 event: 和一行 data:。閘道轉發已解析事件的原始 JSON,事件名取自 JSON 裡的 type。結束標記是最後一條 response.completed。

兩個模型的事件名順序相同:

response.created,response.in_progress,response.output_item.added,response.reasoning_summary_part.added,response.reasoning_summary_text.delta,response.reasoning_summary_text.delta,response.reasoning_summary_text.done,response.reasoning_summary_part.done,response.output_item.done,response.output_item.added,response.content_part.added,response.output_text.delta,response.output_text.done,response.content_part.done,response.output_item.done,response.completed。

下面是 grok-4.7 的實測事件。響應 ID 和輸出項 ID 已換成占位符,其餘欄位與當次響應一致。

event: response.created
data: {"type":"response.created","sequence_number":0,"response":{"object":"response","id":"resp_example","created_at":1791015238,"model":"grok-4.7","output":[],"status":"in_progress"},"output_index":0}

event: response.in_progress
data: {"type":"response.in_progress","sequence_number":1,"response":{"object":"response","id":"resp_example","created_at":1791015238,"model":"grok-4.7","output":[],"status":"in_progress"},"output_index":0}

event: response.output_item.added
data: {"type":"response.output_item.added","sequence_number":2,"output_index":0,"item":{"id":"item_reasoning","type":"reasoning","status":"in_progress","summary":[]}}

event: response.reasoning_summary_part.added
data: {"type":"response.reasoning_summary_part.added","sequence_number":3,"output_index":0,"item_id":"item_reasoning","part":{"type":"summary_text","text":""},"summary_index":0}

event: response.reasoning_summary_text.delta
data: {"type":"response.reasoning_summary_text.delta","sequence_number":4,"output_index":0,"item_id":"item_reasoning","delta":"The user wants a reply","summary_index":0}

event: response.reasoning_summary_text.delta
data: {"type":"response.reasoning_summary_text.delta","sequence_number":5,"output_index":0,"item_id":"item_reasoning","delta":" of exactly \"pong\".","summary_index":0}

event: response.reasoning_summary_text.done
data: {"type":"response.reasoning_summary_text.done","sequence_number":6,"output_index":0,"item_id":"item_reasoning","text":"The user wants a reply of exactly \"pong\".","summary_index":0}

event: response.reasoning_summary_part.done
data: {"type":"response.reasoning_summary_part.done","sequence_number":7,"output_index":0,"item_id":"item_reasoning","part":{"type":"summary_text","text":"The user wants a reply of exactly \"pong\"."},"summary_index":0}

event: response.output_item.done
data: {"type":"response.output_item.done","sequence_number":8,"output_index":0,"item":{"id":"item_reasoning","type":"reasoning","summary":[{"text":"The user wants a reply of exactly \"pong\".","type":"summary_text"}]}}

event: response.output_item.added
data: {"type":"response.output_item.added","sequence_number":9,"output_index":1,"item":{"id":"item_message","type":"message","role":"assistant","content":[],"status":"in_progress"}}

event: response.content_part.added
data: {"type":"response.content_part.added","sequence_number":10,"output_index":1,"item_id":"item_message","content_index":0,"part":{"type":"output_text","text":"","annotations":[]}}

event: response.output_text.delta
data: {"type":"response.output_text.delta","sequence_number":11,"output_index":1,"item_id":"item_message","content_index":0,"delta":"pong"}

event: response.output_text.done
data: {"type":"response.output_text.done","sequence_number":12,"output_index":1,"item_id":"item_message","content_index":0,"text":"pong"}

event: response.content_part.done
data: {"type":"response.content_part.done","sequence_number":13,"output_index":1,"item_id":"item_message","content_index":0,"part":{"type":"output_text","text":"pong","annotations":[]}}

event: response.output_item.done
data: {"type":"response.output_item.done","sequence_number":14,"output_index":1,"item":{"id":"item_message","type":"message","role":"assistant","content":[{"type":"output_text","annotations":[],"text":"pong"}],"status":"completed"}}

event: response.completed
data: {"type":"response.completed","sequence_number":15,"response":{"object":"response","id":"resp_example","created_at":1791015238,"model":"grok-4.7","output":[{"id":"item_reasoning","type":"reasoning","status":"in_progress","summary":[{"text":"The user wants a reply of exactly \"pong\".","type":"summary_text"}]},{"id":"item_message","type":"message","role":"assistant","content":[{"type":"output_text","text":"pong"}],"status":"completed"}],"status":"completed","usage":{"input_tokens":1248,"input_tokens_details":{"cached_tokens":1152},"output_tokens":55,"output_tokens_details":{"reasoning_tokens":54},"total_tokens":1303}},"output_index":0}

對話壓縮

POST https://llmoxy.com/v1/responses/compact

請求欄位是 model(必填)、input、instructions、previous_response_id。上面的 grok 實測沒有呼叫這個路由。