GET
/v1/schemas/nvidia/chat/deepseek-ai/deepseek-v4.1-flash
Accept:
| field | recorded source |
|---|---|
| schema | Source linked above. upstream-spec Source traceed11128493da4568f788b8f76acfc9bb9a88cddf23e0c0725fd7a24deee14973{
"fetchedAt": 1791535404,
"extractorVersion": "1",
"verifiedAt": null
} |
Request body
6 properties · 1 required · 3 $defs| property | type | description | constraints |
|---|---|---|---|
| messages* | ChatRequestMessage[] | A list of messages comprising the conversation so far. | |
| model | string | default: "deepseek-ai/deepseek-v4.1-flash… | |
| max_tokens | integer | The maximum number of tokens to generate in any given call. Note that the model is not aware of this value, and generation will simply stop at the number of tokens specified. | 1 ≤ n ≤ 1048576 · default: 262144 |
| stream | boolean | If set, partial message deltas will be sent. Tokens will be sent as data-only server-sent events (SSE) as they become available (JSON responses are prefixed by `data: `), with the stream terminated by a `data: [DONE]` message. | default: false |
| temperature | number | The sampling temperature to use for text generation. The higher the temperature value is, the less deterministic the output text will be. DeepSeek recommends temperature 1.0 and top_p 0.95 or 1.0. | 0 ≤ n ≤ 1 · default: 1 |
| top_p | number | The top-p sampling mass used for text generation. The top-p value determines the probability mass that is sampled at sampling time. For example, if top_p = 0.2, only the most likely tokens (summing to 0.2 cumulative probability) will be sampled. DeepSeek recom… | 0 ≤ n ≤ 1 · default: 0.95 |
Types
3 $defsChatRequestMessageobject
| role* | string | ||
| content* | string | TextContentPart | ImageContentPart[] |
ImageContentPartobject
| type* | enum | image_url | |
| image_url* | object |
TextContentPartobject
| type* | enum | text | |
| text* | string |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"nvidia","endpointId":"deepseek-ai/deepseek-v4.1-flash","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}