GET
/v1/schemas/nvidia/chat/stepfun-ai/step-5-preview
Accept:
| field | recorded source |
|---|---|
| schema | Source linked above. upstream-spec Source trace0c341a8260dcfa03ea2cbd94d9dcd425afcfdc366ed26034198566e0cd7789b8{
"fetchedAt": 1792127519,
"extractorVersion": "1",
"verifiedAt": null
} |
Request body
13 properties · 2 required · 4 $defs| property | type | description | constraints |
|---|---|---|---|
| model* | enum | stepfun-ai/step-5-preview · default: "stepfun-ai/step-5-preview" | |
| messages* | ChatMessage[] | Conversation history. Use content-part arrays for images. After an assistant tool call, include a tool message with its tool_call_id. Preserve assistant reasoning_content when continuing a conversation. | items ≥ 1 |
| max_tokens | integer | Maximum generated tokens, including reasoning and the final answer. Small budgets may end during reasoning with null content and finish_reason=length. Prompt plus output must fit the context window. | 1 ≤ n ≤ 1048576 · default: 4096 |
| stream | boolean | default: false | |
| temperature | number | 0 ≤ n ≤ 2 · default: 0.5 | |
| top_p | number | 0 < n ≤ 1 · default: 1 | |
| frequency_penalty | number | -2 ≤ n ≤ 2 · default: 0 | |
| presence_penalty | number | -2 ≤ n ≤ 2 · default: 0 | |
| seed | integer | Optional sampling seed, limited to JavaScript-safe integers for the interactive examples. Deterministic output is not guaranteed. | 0 ≤ n ≤ 9007199254740991 |
| stop | string | string[] | Stop string or list of stop strings; omitted from the output. | nullable |
| tools | FunctionTool[] | Functions the model may request; the caller executes them. | |
| tool_choice | enum | object | Choose auto, none, required, or force a named function. | |
| chat_template_kwargs | object | Reasoning remains enabled on this checkpoint. Do not set enable_thinking=false: it does not stop reasoning generation. |
Types
4 $defsChatMessageobject
| role* | enum | system | user | assistant | tool | |
| content | string | ContentPart[] | nullable | |
| reasoning_content | any | Assistant reasoning, separate from the final answer. | |
| tool_calls | ToolCall[] | ||
| tool_call_id | string | Required on tool-result messages; matches an assistant tool call ID. | |
| name | string |
ContentPartobject | object
FunctionToolobject
| type* | const | "function" | |
| function* | object |
ToolCallobject
| id* | string | ||
| type* | const | "function" | |
| function* | object |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"nvidia","endpointId":"stepfun-ai/step-5-preview","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}