【已解决】Opencode接的gpt没有多模态功能，怎么弄？

问题描述：

接了很多中转，但是配到opencode里面，都是没有多模态的，有佬知道为什么吗？
image478×314 7.74 KB

"openai": { "options": { "baseURL": "xxxxxxxxxx", "apiKey": "xxxxxxxxxxx", "api": "openai-responses" }, "models": { "gpt-5.2": { "name": "GPT-5.2", "limit": { "context": 400000, "output": 128000 }, "options": { "store": false }, "variants": { "low": {}, "medium": {}, "high": {}, "xhigh": {} } }, "gpt-5.4": { "name": "GPT-5.4", "limit": { "context": 1050000, "output": 128000 }, "options": { "store": false }, "variants": { "low": {}, "medium": {}, "high": {}, "xhigh": {} } }, "gpt-5.3-codex": { "name": "GPT-5.3 Codex", "limit": { "context": 400000, "output": 128000 }, "options": { "store": false }, "variants": { "low": {}, "medium": {}, "high": {}, "xhigh": {} } } } }, 网友解答：

---

--【壹】--：

image507×237 7.21 KB

---

--【贰】--：

配置json里好像填一下输入类型就可以了

---

--【叁】--：

"codex-rev": { "npm": "@ai-sdk/openai-compatible", "name": "codex-rev", "options": { "baseURL": "http://127.0.0.1:8317/v1" }, "models": { "gpt-5.2": { "name": "gpt-5.2", "attachment": true, "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] } }, "gpt-5.2-codex": { "name": "gpt-5.2-codex", "attachment": true, "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] } }, "gpt-5.3-codex": { "name": "gpt-5.3-codex", "attachment": true, "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] } } } },

注意input中的image

---

--【肆】--：

“options”: {
“store”: false,
“reasoningSummary”: “auto”,
“textVerbosity”: “low”
},
“variants”: {
“low”: {
“reasoningEffort”: “low”
},
“medium”: {
“reasoningEffort”: “medium”
},
“high”: {
“reasoningEffort”: “high”
},
“xhigh”: {
“reasoningEffort”: “xhigh”
}
},

思考模式匹配ui选择

---

--【伍】--： 夜深楼鼓:

"api": "openai-responses"

是这个吗？