DeepSeek Flash

Model IDdeepseek-flash

DeepSeek
Language

Chat and reasoning through the OpenAI-compatible chat API.

Call this model API quickstart

Overview

Model developer: DeepSeek
Supported protocols: openai
anthropic
openai-response

Call this model

Create an API key, add account credit, and confirm this model is available to your key before sending a request.

LLM index

Copy the complete model reference, including every published protocol, for your AI assistant.

API protocol

POST/v1/chat/completions

Request parameters

Parameter Required Type Description

model

Required

string

Use this exact published model ID.

Constraints

deepseek-flash

messages

Required

object[]

Send the conversation history in order.

Constraints

At least one message

These fields apply when messages is supplied. A required child does not make its optional parent required.

Parameter Required Type Description

messages[].role

Required

string

Role of the message author.

Constraints

system
user
assistant
tool

messages[].content

Required

string | object[] | null

Message text; assistant tool-call messages may use null.

These fields apply when messages[].content is supplied. A required child does not make its optional parent required.

Parameter Required Type Description

messages[].content[].type

Required

string

Choose a text part or an image part.

Constraints

text
image_url

messages[].content[].text

Conditional

string

Required for a text part.

messages[].content[].image_url

Conditional

object

Image input for user and tool messages.

Required when content part type is image_url.

These fields apply when messages[].content[].image_url is supplied. A required child does not make its optional parent required.

Fields in messages[].content[].image_url
Parameter	Required	Type	Description
`messages[].content[].image_url.url`	Required	`string`	HTTPS image URL or base64 image data URL.
`messages[].content[].image_url.detail`	Optional	`string`	Image processing detail. Constraints low high original auto

messages[].name

Optional

string

Optional participant name.

messages[].tool_call_id

Conditional

string

Required for a tool reply; match the earlier tool-call ID.

messages[].tool_calls

Optional

object[]

Replay assistant function calls when returning tool results.

These fields apply when messages[].tool_calls is supplied. A required child does not make its optional parent required.

Parameter Required Type Description

messages[].tool_calls[].id

Required

string

Identifier used by the matching tool reply.

messages[].tool_calls[].type

Required

string

Function call type.

Constraints

function

messages[].tool_calls[].function

Required

object

Function name and JSON-encoded arguments.

These fields apply when messages[].tool_calls[].function is supplied. A required child does not make its optional parent required.

Fields in messages[].tool_calls[].function
Parameter	Required	Type	Description
`messages[].tool_calls[].function.name`	Required	`string`	Name of the declared function.
`messages[].tool_calls[].function.arguments`	Required	`string`	JSON string containing the function arguments.

messages[].reasoning_content

Conditional

string

Replay prior assistant reasoning when continuing a thinking tool-call conversation.

thinking

Optional

object

Enable or disable thinking mode.

These fields apply when thinking is supplied. A required child does not make its optional parent required.

Fields in thinking
Parameter	Required	Type	Description
`thinking.type`	Optional	`string`	Thinking mode switch. Default `enabled` Constraints enabled disabled

reasoning_effort

Optional

string

Choose reasoning effort; none disables thinking.

Default: high

Constraints

none
low
high
max

max_tokens

Optional

integer

Maximum generated tokens; input and output must also fit the model context.

Constraints

1–393216

stream

Optional

boolean

Receive incremental server-sent events.

Default: false

stream_options

Optional

object

Streaming options; use together with stream=true.

These fields apply when stream_options is supplied. A required child does not make its optional parent required.

Fields in stream_options
Parameter	Required	Type	Description
`stream_options.include_usage`	Optional	`boolean`	Request token-usage information in the stream.

temperature

Optional

number

Sampling randomness; ignored while thinking is enabled.

Default: 1

Constraints

0–2

top_p

Optional

number

Thinking-mode sampling threshold; ignored in non-thinking mode.

Default: 1

Constraints

0 < top_p ≤ 1
Thinking mode: values below 0.95 become 0.95

stop

Optional

string | string[]

Stop generation at any supplied sequence.

Constraints

Up to 16 sequences

response_format

Optional

object

Select ordinary text or JSON object output.

These fields apply when response_format is supplied. A required child does not make its optional parent required.

Fields in response_format
Parameter	Required	Type	Description
`response_format.type`	Optional	`string`	Output format. Default `text` Constraints text json_object

tools

Optional

object[]

Declare functions the model may request; your application executes them.

These fields apply when tools is supplied. A required child does not make its optional parent required.

Parameter Required Type Description

tools[].type

Required

string

Function tool type.

Constraints

function

tools[].function

Required

object

Function definition.

These fields apply when tools[].function is supplied. A required child does not make its optional parent required.

Fields in tools[].function
Parameter	Required	Type	Description
`tools[].function.name`	Required	`string`	Unique function name. Constraints 1–128 characters A–Z, a–z, 0–9, underscore or hyphen
`tools[].function.description`	Optional	`string`	Explain when the function should be used.
`tools[].function.parameters`	Optional	`object`	JSON Schema for the function arguments; omission means no arguments.

tool_choice

Optional

string | object

Allow, disable, require, or select a function call.

Constraints

none
auto
required
{"type":"function","function":{"name":"FUNCTION_NAME"}}

logprobs

Optional

boolean

Return log probabilities for generated text.

top_logprobs

Optional

integer

Number of candidate-token probabilities; requires logprobs=true.

Constraints

0–20

Request notes

Use a Scenepond Bearer API key and the Scenepond base URL; no provider key is required.
Thinking is enabled by default. Temperature has no effect in thinking mode; top_p has no effect in non-thinking mode.
When max_tokens is omitted, the provider defaults to 8192 without thinking, 65536 with thinking, or 131072 at max reasoning effort.
JSON object output also needs an instruction to produce JSON. Check finish_reason before treating truncated output as complete JSON.
Required or named tool_choice needs thinking disabled. Validate function arguments before executing a tool.
Preserve assistant tool_calls, their reasoning_content, and matching tool replies across thinking tool-call turns.
Chat streaming ends with [DONE]. The provider includes final token usage; the gateway may normalize usage-chunk delivery.
The gateway removes stream_options when stream is false and may request usage automatically on supported channels.
frequency_penalty and presence_penalty no longer affect native DeepSeek output. Do not rely on seed, n, or max_completion_tokens as supported DeepSeek controls.
The provider documents user_id, but the current gateway Chat DTO does not preserve that field. Extra undocumented fields are not guaranteed to reach the provider.
Assistant prefix completion and strict tool schemas are provider beta features; their beta routing is not verified by this standard Chat endpoint.
DeepSeek Flash accepts image URLs and inline image data in user or tool messages. Image input in system or assistant messages is rejected; Scenepond Files API support is not established here.

Minimum request

1curl --fail-with-body -X POST "https://scenepond-api-production.up.railway.app/v1/chat/completions" \
2  -H "Authorization: Bearer $SCENEPOND_API_KEY" \
3  -H "Content-Type: application/json" \
4  --data-binary @- <<'JSON'
5{
6  "model": "deepseek-flash",
7  "messages": [
8    {
9      "role": "user",
10      "content": "Hello"
11    }
12  ]
13}
14JSON

Run this example in a shell with cURL installed. Set SCENEPOND_API_KEY before running.

Illustrative responses

Response examples show the structure only. IDs, URLs, and values are placeholders.

Completed chat response

1{
2  "id": "chatcmpl_example",
3  "object": "chat.completion",
4  "created": 1790812800,
5  "model": "deepseek-flash",
6  "choices": [
7    {
8      "index": 0,
9      "message": {
10        "role": "assistant",
11        "content": "Hello! How can I help?"
12      },
13      "finish_reason": "stop"
14    }
15  ],
16  "usage": {
17    "prompt_tokens": 8,
18    "completion_tokens": 9,
19    "total_tokens": 17
20  }
21}

Chat streaming text chunk

1{
2  "id": "chatcmpl_example",
3  "object": "chat.completion.chunk",
4  "created": 1790812800,
5  "model": "deepseek-flash",
6  "choices": [
7    {
8      "index": 0,
9      "delta": {
10        "content": "Hello"
11      },
12      "finish_reason": null
13    }
14  ]
15}

Use it in your application

Connect an enabled chat model to Hermes Agent, OpenClaw, or DeepSeek Harness. Tool use, images, and reasoning depend on the model and its configured protocol.

Hermes Agent

Use Scenepond as the model provider for your Hermes agent.

Agent runtimeSetup guide

OpenClaw

Connect your personal assistant to an enabled model through a custom provider.

Personal assistantSetup guide

DeepSeek Harness

Add Scenepond as a custom model API for coding and repository tasks.

Coding agentSetup guide

All integrations

Model access and request limits depend on your account, API key, and service configuration.

Pricing

InputUSD 0.15 / 1 million tokensOutputUSD 0.6 / 1 million tokensCache ReadUSD 0.003 / 1 million tokensCurrent period price · 2 tiers

Prices by period

USD / 1 million tokens
Price tier	Input	Output
Peak hours	0.3	1.2
Off-peak hours	0.15	0.6

Get an API key Add funds

Prices depend on model settings. Usage records show recorded deductions; asynchronous task charges may be adjusted after completion.

Call this model

Create an API key, add account credit, and confirm this model is available to your key before sending a request.

LLM index

Copy the complete model reference, including every published protocol, for your AI assistant.

API protocol

POST/v1/chat/completions

Request parameters

Parameter Required Type Description

model

Required

string

Use this exact published model ID.

Constraints

deepseek-flash

messages

Required

object[]

Send the conversation history in order.

Constraints

At least one message

These fields apply when messages is supplied. A required child does not make its optional parent required.

Parameter Required Type Description

messages[].role

Required

string

Role of the message author.

Constraints

system
user
assistant
tool

messages[].content

Required

string | object[] | null

Message text; assistant tool-call messages may use null.

These fields apply when messages[].content is supplied. A required child does not make its optional parent required.

Parameter Required Type Description

messages[].content[].type

Required

string

Choose a text part or an image part.

Constraints

text
image_url

messages[].content[].text

Conditional

string

Required for a text part.

messages[].content[].image_url

Conditional

object

Image input for user and tool messages.

Required when content part type is image_url.

These fields apply when messages[].content[].image_url is supplied. A required child does not make its optional parent required.

Fields in messages[].content[].image_url
Parameter	Required	Type	Description
`messages[].content[].image_url.url`	Required	`string`	HTTPS image URL or base64 image data URL.
`messages[].content[].image_url.detail`	Optional	`string`	Image processing detail. Constraints low high original auto

messages[].name

Optional

string

Optional participant name.

messages[].tool_call_id

Conditional

string

Required for a tool reply; match the earlier tool-call ID.

messages[].tool_calls

Optional

object[]

Replay assistant function calls when returning tool results.

These fields apply when messages[].tool_calls is supplied. A required child does not make its optional parent required.

Parameter Required Type Description

messages[].tool_calls[].id

Required

string

Identifier used by the matching tool reply.

messages[].tool_calls[].type

Required

string

Function call type.

Constraints

function

messages[].tool_calls[].function

Required

object

Function name and JSON-encoded arguments.

These fields apply when messages[].tool_calls[].function is supplied. A required child does not make its optional parent required.

Fields in messages[].tool_calls[].function
Parameter	Required	Type	Description
`messages[].tool_calls[].function.name`	Required	`string`	Name of the declared function.
`messages[].tool_calls[].function.arguments`	Required	`string`	JSON string containing the function arguments.

messages[].reasoning_content

Conditional

string

Replay prior assistant reasoning when continuing a thinking tool-call conversation.

thinking

Optional

object

Enable or disable thinking mode.

These fields apply when thinking is supplied. A required child does not make its optional parent required.

Fields in thinking
Parameter	Required	Type	Description
`thinking.type`	Optional	`string`	Thinking mode switch. Default `enabled` Constraints enabled disabled

reasoning_effort

Optional

string

Choose reasoning effort; none disables thinking.

Default: high

Constraints

none
low
high
max

max_tokens

Optional

integer

Maximum generated tokens; input and output must also fit the model context.

Constraints

1–393216

stream

Optional

boolean

Receive incremental server-sent events.

Default: false

stream_options

Optional

object

Streaming options; use together with stream=true.

These fields apply when stream_options is supplied. A required child does not make its optional parent required.

Fields in stream_options
Parameter	Required	Type	Description
`stream_options.include_usage`	Optional	`boolean`	Request token-usage information in the stream.

temperature

Optional

number

Sampling randomness; ignored while thinking is enabled.

Default: 1

Constraints

0–2

top_p

Optional

number

Thinking-mode sampling threshold; ignored in non-thinking mode.

Default: 1

Constraints

0 < top_p ≤ 1
Thinking mode: values below 0.95 become 0.95

stop

Optional

string | string[]

Stop generation at any supplied sequence.

Constraints

Up to 16 sequences

response_format

Optional

object

Select ordinary text or JSON object output.

These fields apply when response_format is supplied. A required child does not make its optional parent required.

Fields in response_format
Parameter	Required	Type	Description
`response_format.type`	Optional	`string`	Output format. Default `text` Constraints text json_object

tools

Optional

object[]

Declare functions the model may request; your application executes them.

These fields apply when tools is supplied. A required child does not make its optional parent required.

Parameter Required Type Description

tools[].type

Required

string

Function tool type.

Constraints

function

tools[].function

Required

object

Function definition.

These fields apply when tools[].function is supplied. A required child does not make its optional parent required.

Fields in tools[].function
Parameter	Required	Type	Description
`tools[].function.name`	Required	`string`	Unique function name. Constraints 1–128 characters A–Z, a–z, 0–9, underscore or hyphen
`tools[].function.description`	Optional	`string`	Explain when the function should be used.
`tools[].function.parameters`	Optional	`object`	JSON Schema for the function arguments; omission means no arguments.

tool_choice

Optional

string | object

Allow, disable, require, or select a function call.

Constraints

none
auto
required
{"type":"function","function":{"name":"FUNCTION_NAME"}}

logprobs

Optional

boolean

Return log probabilities for generated text.

top_logprobs

Optional

integer

Number of candidate-token probabilities; requires logprobs=true.

Constraints

0–20

Request notes

Use a Scenepond Bearer API key and the Scenepond base URL; no provider key is required.
Thinking is enabled by default. Temperature has no effect in thinking mode; top_p has no effect in non-thinking mode.
When max_tokens is omitted, the provider defaults to 8192 without thinking, 65536 with thinking, or 131072 at max reasoning effort.
JSON object output also needs an instruction to produce JSON. Check finish_reason before treating truncated output as complete JSON.
Required or named tool_choice needs thinking disabled. Validate function arguments before executing a tool.
Preserve assistant tool_calls, their reasoning_content, and matching tool replies across thinking tool-call turns.
Chat streaming ends with [DONE]. The provider includes final token usage; the gateway may normalize usage-chunk delivery.
The gateway removes stream_options when stream is false and may request usage automatically on supported channels.
frequency_penalty and presence_penalty no longer affect native DeepSeek output. Do not rely on seed, n, or max_completion_tokens as supported DeepSeek controls.
The provider documents user_id, but the current gateway Chat DTO does not preserve that field. Extra undocumented fields are not guaranteed to reach the provider.
Assistant prefix completion and strict tool schemas are provider beta features; their beta routing is not verified by this standard Chat endpoint.
DeepSeek Flash accepts image URLs and inline image data in user or tool messages. Image input in system or assistant messages is rejected; Scenepond Files API support is not established here.

Minimum request

1curl --fail-with-body -X POST "https://scenepond-api-production.up.railway.app/v1/chat/completions" \
2  -H "Authorization: Bearer $SCENEPOND_API_KEY" \
3  -H "Content-Type: application/json" \
4  --data-binary @- <<'JSON'
5{
6  "model": "deepseek-flash",
7  "messages": [
8    {
9      "role": "user",
10      "content": "Hello"
11    }
12  ]
13}
14JSON

Run this example in a shell with cURL installed. Set SCENEPOND_API_KEY before running.

Illustrative responses

Response examples show the structure only. IDs, URLs, and values are placeholders.

Completed chat response

1{
2  "id": "chatcmpl_example",
3  "object": "chat.completion",
4  "created": 1790812800,
5  "model": "deepseek-flash",
6  "choices": [
7    {
8      "index": 0,
9      "message": {
10        "role": "assistant",
11        "content": "Hello! How can I help?"
12      },
13      "finish_reason": "stop"
14    }
15  ],
16  "usage": {
17    "prompt_tokens": 8,
18    "completion_tokens": 9,
19    "total_tokens": 17
20  }
21}

Chat streaming text chunk

1{
2  "id": "chatcmpl_example",
3  "object": "chat.completion.chunk",
4  "created": 1790812800,
5  "model": "deepseek-flash",
6  "choices": [
7    {
8      "index": 0,
9      "delta": {
10        "content": "Hello"
11      },
12      "finish_reason": null
13    }
14  ]
15}

Overview

Call this model

Request parameters

Fields in messages

Fields in messages[].content

Fields in messages[].content[].image_url

Fields in messages[].tool_calls

Fields in messages[].tool_calls[].function

Fields in thinking

Fields in stream_options

Fields in response_format

Fields in tools

Fields in tools[].function

Request notes

Minimum request

Illustrative responses

Completed chat response

Chat streaming text chunk

Use it in your application

Hermes Agent

OpenClaw

DeepSeek Harness

Overview

Call this model

Request parameters

Fields in messages

Fields in messages[].content

Fields in messages[].content[].image_url

Fields in messages[].tool_calls

Fields in messages[].tool_calls[].function

Fields in thinking

Fields in stream_options

Fields in response_format

Fields in tools

Fields in tools[].function

Request notes

Minimum request

Illustrative responses

Completed chat response

Chat streaming text chunk

Use it in your application

Hermes Agent

OpenClaw

DeepSeek Harness