GET

/v1/schemas/deepseek/chat/chat%2Fcompletions

kind inputactivity chathash c36c9016…extracted Nov 17, 2026version currentsource upstream spec ↗

Request body

20 properties · 2 required · 0 $defs
propertytypedescriptionconstraints
messages*System message | User message | Assistant message[]A list of messages comprising the conversation so far.items ≥ 1
model*enumID of the model to use. Use `deepseek-flash` or `deepseek-v4-pro`.deepseek-flash | deepseek-v4-pro
thinkingobjectControls the switch between thinking and non-thinking mode. When `thinking` is omitted or `null`, the mode follows `reasoning_effort`; if `reasoning_effort` is also omitted, thinking is enabled. When this object is provided, `type` is required and takes preced…
reasoning_effortenumControls the thinking mode toggle and the thinking effort. `none` disables thinking mode; `low` / `high` / `max` enable thinking mode. The default effort is `high`. For compatibility with existing software, `minimal` is accepted and mapped to `low`, and `mediu…none | low | high | max
max_tokensintegerThe maximum number of tokens that can be generated in the chat completion.
response_formatobjectAn object specifying the format that the model must output. If omitted or `null`, plain text is used. When this object is provided, `type` is required. Setting to { "type": "json_object" } enables JSON Output, which guarantees the message the model generates i…
stopstring | string[]Up to 16 sequences where the API will stop generating further tokens. Each sequence must be a non-empty string of at most 512 bytes (UTF-8 encoded).default: null
streambooleanIf set, partial message deltas will be sent. Tokens will be sent as data-only server-sent events (SSE) as they become available, with the stream terminated by a `data: [DONE]` message.default: false
stream_optionsobjectOptions for streaming response. Must be set together with `stream: true`; if `stream` is not set to `true`, the API returns a `400` error.default: null
temperaturenumberWhat sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.0 ≤ n ≤ 2 · default: 1
top_pnumberAn alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.0 ≤ n ≤ 1
toolsFunction tool | DeepSeek web search tool | DeepSeek read URL tool[]A list of tools the model may call: functions, and the web tools `deepseek_web_search` and `deepseek_read_url` (see the [Web Tools Guide](/guides/web_tools#chat-completions-api)). Use functions to provide a list of functions the model may generate JSON inputs …
tool_choiceenum | ChatCompletionNamedToolChoiceControls which (if any) tool is called by the model.
safety_checkobjectDeepSeek extension. Set `level` to `high` to turn on basic risk control, which reviews the model input and output. See the [Model Content Safety Guide](/guides/safety).
titleobjectDeepSeek extension. Set `{"enabled": true}` to have the response carry a short title for the conversation. See the [Conversation Title Guide](/guides/conversation_title).
logprobsbooleanWhether to return log probabilities of the output tokens or not. If `true`, returns the log probabilities of each output token returned in the `content` of `message`.default: false
top_logprobsintegerAn integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability. `logprobs` must be set to `true` if this parameter is used.0 ≤ n ≤ 20 · default: null
user_idanyA custom user_id. We recommend using only ASCII letters, digits, underscores (`_`), and hyphens (`-`). The UTF-8 encoded value must not exceed 512 bytes. Do not include user privacy information in the user_id. * user_id can be used to distinguish user identiti…
frequency_penaltyanyThis parameter is no longer supported. It will not take effect if you pass it to the API.deprecated
presence_penaltyanyThis parameter is no longer supported. It will not take effect if you pass it to the API.deprecated

Validate a payload

before you spend tokens
shell
$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"deepseek","endpointId":"chat/completions","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}