DeepSeek integration (AI). Imported from open-connector.
https://api.deepseek.com/anthropic/models
/user/balance
/chat/completions
| Param | Type | Required | Description |
|---|---|---|---|
| model | string | required | The DeepSeek model identifier. |
| messages | array | required | The ordered conversation history to send to the model. |
| frequency_penalty | number | optional | The frequency penalty to apply to repeated tokens. |
| logprobs | boolean | optional | Whether to include token-level log probability details in the response. |
| max_tokens | integer | optional | The maximum number of tokens to generate. |
| presence_penalty | number | optional | The presence penalty to apply to newly introduced tokens. |
| response_format | object | optional | — |
| stop | string | optional | One or more sequences that stop generation. |
| stream | boolean | optional | Whether to request a streaming response. This connector only accepts false or o… |
| stream_options | object | optional | Streaming options for the request. |
| temperature | number | optional | The sampling temperature to use for generation. |
| thinking | object | optional | — |
| tool_choice | string | optional | The tool selection policy for the chat completion request. |
| tools | array | optional | The tools available to the model. |
| top_logprobs | integer | optional | The number of top token log probabilities to return. |
| top_p | number | optional | The nucleus sampling threshold. |
/v1/messages
| Param | Type | Required | Description |
|---|---|---|---|
| model | string | required | The DeepSeek model identifier. |
| max_tokens | integer | required | The maximum number of tokens to generate. |
| messages | array | required | The ordered conversation history to send to the model. |
| stop_sequences | array | optional | Sequences that stop generation. |
| stream | boolean | optional | Whether to request a streaming response. This connector only accepts false or o… |
| system | string | optional | Message content as plain text or structured blocks. |
| temperature | number | optional | The sampling temperature to use for generation. |
| thinking | object | optional | Thinking configuration for the Anthropic-compatible request. |
| tool_choice | string | optional | How the model should choose tools for the request. |
| tools | array | optional | The tools available to the model. |
| top_p | number | optional | The nucleus sampling threshold. |