You can convert text into high-dimensional vectors (embeddings) and use them for various natural language processing (NLP) tasks such as similarity calculation between texts, clustering, and search.
Compatible with OpenAI’s Responses API, it can generate text or JSON output from text, image, or file inputs, and supports function calls and built-in tools.
Adjust the probability of a specific token (example: { “100”: 2.0 })
null
Key: Token ID, Value: -100 ~ 100
{ “100”: 2.0 }
logprobs
-
boolean
❌
Returns token probabilities for the top logprobs count
false
true, false
true
max_completion_tokens
-
integer
❌
Limit the maximum number of generated tokens
None
0 ~ model maximum value
100
max_tokens (Deprecated)
-
integer
❌
Limit the maximum number of generated tokens
None
0 ~ model maximum value
100
n
-
integer
❌
Specify the number of responses to generate
1
3
presence_penalty
-
number
❌
Adjust the penalty for tokens in the existing text.
0
-2.0 ~ 2.0
1.0
seed
-
integer
❌
Specify the seed value for controlling randomness
None
stop
-
string / array / null
❌
Stop generation when a specific string appears.
null
"\n"
stream
-
boolean
❌
Whether to return results in streaming mode
false
true/false
true
stream_options
include_usage, continuous_usage_stats
object
❌
Control streaming options (e.g., whether to include usage statistics)
null
{ “include_usage”: true }
temperature
-
number
❌
Adjust the creativity of the generated output (higher values are more random)
1
0.0 ~ 1.0
0.7
tool_choice
-
string
❌
Adjust which Tool is invoked by the model
none: Do not invoke any Tool
auto: Let the model decide whether to generate a message or invoke a Tool
required: The model must invoke one or more Tools
when there is no tool: none
when there is a tool: auto
tools
-
array
❌
list of Tools that the model can invoke
only functions are supported as Tools
supports up to 128 functions
None
top_logprobs
-
integer
❌
Specify the number of tokens with the highest probability for an integer between 0 and 20
Each is associated with a log probability value
logprobs must be set to true
Shows the probability values for the top k of completions
None
0 ~ 20
3
top_p
-
number
❌
Limit token sampling probability (higher values consider more tokens)
1
0.0 ~ 1.0
0.9
prompt_safety_model
-
string
❌
Specify a guard model for prompt inspection. When set, the guard model checks the prompt first, returning the guard result if it is deemed unsafe, and processing the request with the model specified in the model parameter if it is safe.
“meta-llama/Llama-Guard-4-12B”
chat_template_kwargs
-
object
❌
Additional keyword arguments to pass to the template renderer. Used for per-model reasoning configuration (see Reasoning configuration for details)
null
{ “enable_thinking”: true }
Table. Chat Completions API - Body Parameters
Example
Color mode
curl-X'POST'\{SimpleAIInferenceendpoint}/v1/chat/completions\-H'Authorization:bearersai-xxxxxxx...'\-H'Content-Type:application/json'\-d'{"model":"google/gemma-4-31B-it","messages":[{"role":"assistant","content":"You are a helpful assistant."},{"role":"user","content":"What is the capital of South Korea?"}]}'
curl-X'POST'\ {SimpleAIInferenceendpoint}/v1/chat/completions\-H'Authorization:bearersai-xxxxxxx...'\-H'Content-Type:application/json'\-d'{
"model": "google/gemma-4-31B-it",
"messages": [
{
"role": "assistant",
"content": "You are a helpful assistant." },
{
"role": "user",
"content": "What is the capital of South Korea?" }
]
}'
Code block. Chat Completions API Request Example
Response
200 OK
Name
Type
Description
id
string
Unique identifier of the response
object
string
Response object’s type (example: “chat.completion”)
created
integer
Creation time (Unix timestamp, in seconds)
model
string
Name of the model used
choices
array
List of generated response options
choices[].index
integer
The index of the corresponding choice
choices[].message
object
Generated message object
choices[].message.role
string
The role of the message author (e.g., “assistant”)
choices[].message.content
string
The actual content of the generated message
choices[].message.reasoning
string
The actual content of the generated inference message
choices[].message.tool_calls
array (optional)
Tool invocation information (may be included depending on model/settings)
choices[].finish_reason
string or null
Reason why the response was terminated (e.g., “stop”, “length”, etc)
choices[].stop_reason
object or null
Additional stop reason details
choices[].logprobs
object or null
Log probability information per token (included depending on settings)
usage
object
Token Usage Statistics
usage.prompt_tokens
integer
Number of tokens used in the input prompt
usage.completion_tokens
integer
Number of tokens used in the generated response
usage.total_tokens
integer
Total token count (input + output)
Table. Chat Completions API - 200 OK
Error Code
HTTP status code
ErrorCode description
400
Bad Request
422
When a request is denied due to policies such as Prompt Guard
500
Internal Server Error
Table. Chat Completions API - Error Code
Example
Color mode
{"id":"chatcmpl-xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx","object":"chat.completion","created":1749702816,"model":"google/gemma-4-31B-it","choices":[{"index":0,"message":{"role":"assistant","reasoning":null,"content":"The capital of South Korea is Seoul.","tool_calls":[]},"logprobs":null,"finish_reason":"stop","stop_reason":null}],"usage":{"prompt_tokens":54,"total_tokens":62,"completion_tokens":8,"prompt_tokens_details":null},"prompt_logprobs":null}
{
"id": "chatcmpl-xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
"object": "chat.completion",
"created": 1749702816,
"model": "google/gemma-4-31B-it",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"reasoning": null,
"content": "The capital of South Korea is Seoul.",
"tool_calls": []
},
"logprobs": null,
"finish_reason": "stop",
"stop_reason": null }
],
"usage": {
"prompt_tokens": 54,
"total_tokens": 62,
"completion_tokens": 8,
"prompt_tokens_details": null },
"prompt_logprobs": null}
Code block. Chat Completions API Response Example
Prompt Guard response
If the prompt_safety_model parameter is set, the guard model checks the prompt first.
safe: model The request is processed unchanged using the model specified in the parameter.
unsafe: Returns a guard result in the following form and the request is terminated.
Color mode
{"guard_result":"unsafe","categories":["S1","S2"],"categories_description":["Violent Crimes","Non-Violent Crimes"],"messages":["Cannot fulfill the request due to violent content.","Cannot respond as it may promote illegal activities."]}
{
"guard_result": "unsafe",
"categories": ["S1", "S2"],
"categories_description": ["Violent Crimes", "Non-Violent Crimes"],
"messages": [
"Cannot fulfill the request due to violent content.",
"Cannot respond as it may promote illegal activities." ]
}
Code block. Chat Completions API Prompt Guard response Example (unsafe)
Reasoning configuration
Through the chat_template_kwargs parameter, you can control the reasoning (inference mode) configuration for each model. The default behavior and supported options vary by model.
model
basic reasoning
Configure chat_template_kwargs
Explanation
zai-org/GLM-5.2
On (Think Max)
Think Max(default): {“reasoning_effort”: “max”} or omit — deepest reasoning
Think High: {“reasoning_effort”: “high”} — balanced depth and latency
Non-think: {“enable_thinking”: false} — fast response, no reasoning
Adjust inference depth with reasoning_effort, disable with enable_thinking=false
Qwen/Qwen3.6-27B
On
Disabled: {“enable_thinking”: false}
Reasoning is enabled by default and can be disabled when needed.
google/gemma-4-31B-it
Off
Enable: {“enable_thinking”: true}
By default, reasoning is disabled, but it can be enabled when needed.
openai/gpt-oss-120b
medium
{“reasoning_effort”: “low”}
{“reasoning_effort”: “medium”} (default)
{“reasoning_effort”: “high”}
Adjust inference depth with reasoning_effort (default: medium)
Table. Chat Completions API - Model-specific Reasoning Configuration
Color mode
curl-X'POST'\{SimpleAIInferenceendpoint}/v1/chat/completions\-H'Authorization:bearersai-xxxxxxx...'\-H'Content-Type:application/json'\-d'{"model":"zai-org/GLM-5.2","messages":[{"role":"user","content":"Please solve a complex math problem."}],"chat_template_kwargs":{"reasoning_effort":"high"}}'
Adjust the probability of a specific token (example: { “100”: 2.0 })
null
Key: Token ID, Value: -100~100
{ “100”: 2.0 }
logprobs
-
integer
❌
Returns token probabilities for the top logprobs count
null
1 ~ 5
5
max_completion_tokens
-
integer
❌
Limit the maximum number of generated tokens
None
0~model maximum value
100
max_tokens (Deprecated)
-
integer
❌
Limit the maximum number of generated tokens
None
0~model maximum value
100
n
-
integer
❌
Specify the number of responses to generate
1
3
presence_penalty
-
number
❌
Adjust the penalty for tokens in the existing text.
0
-2.0 ~ 2.0
1.0
seed
-
integer
❌
Specify the seed value for controlling randomness
None
stop
-
string / array / null
❌
Stop generation when a specific string appears.
null
"\n"
stream
-
boolean
❌
Whether to return results in streaming mode
false
true/false
true
stream_options
include_usage, continuous_usage_stats
object
❌
Control streaming options (e.g., whether to include usage statistics)
null
{ “include_usage”: true }
temperature
-
number
❌
Adjust the creativity of the generated output (higher values are more random)
1
0.0 ~ 1.0
0.7
top_p
-
number
❌
Limit the sampling probability of tokens (higher values consider more tokens)
1
0.0 ~ 1.0
0.9
Table. Completions API - Body Parameters
Example
Color mode
curl-X'POST'\{SimpleAIInferenceendpoint}/v1/completions\-H'Authorization:bearersai-xxxxxxx...'\-H'Content-Type:application/json'\-d'{"model":"google/gemma-4-31B-it","prompt":"What is the capital of South Korea?","temperature":0.7}'
curl-X'POST'\ {SimpleAIInferenceendpoint}/v1/completions\-H'Authorization:bearersai-xxxxxxx...'\-H'Content-Type:application/json'\-d'{
"model": "google/gemma-4-31B-it",
"prompt": "What is the capital of South Korea?",
"temperature": 0.7 }'
Code block. Completions API Request Example
Response
200 OK
Name
Type
Description
id
string
Unique identifier of the response
object
string
Response object’s type (example: “text_completion”)
created
integer
Creation time (Unix timestamp, in seconds)
model
string
Name of the model used
choices
array
List of generated response options
choices[].index
number
The index of the corresponding choice
choices[].text
string
Generated text object
choices[].logprobs
object
Log probability information per token (included depending on settings)
choices[].finish_reason
string or null
Reason why the response was terminated (e.g., “stop”, “length”, etc)
choices[].stop_reason
object or null
Additional stop reason details
choices[].prompt_logprobs
object or null
Log probability per input prompt token (nullable)
usage
object
Token Usage Statistics
usage.prompt_tokens
number
Number of tokens used in the input prompt
usage.total_tokens
number
Total token count (input + output)
usage.completion_tokens
number
Number of tokens used in the generated response
usage.prompt_tokens_details
object
Prompt token usage details
Table. Completions API - 200 OK
Error Code
HTTP status code
ErrorCode description
400
Bad Request
422
When a request is denied due to policies such as Prompt Guard
500
Internal Server Error
Table. Completions API - Error Code
Example
Color mode
{"id":"cmpl-xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx","object":"text_completion","created":1749702612,"model":"google/gemma-4-31B-it","choices":[{"index":0,"text":" \nOur capital city is Seoul. \n\nA. 1\nB. ","logprobs":null,"finish_reason":"length","stop_reason":null,"prompt_logprobs":null}],"usage":{"prompt_tokens":9,"total_tokens":25,"completion_tokens":16,"prompt_tokens_details":null}}
The Embedding API converts given text into high-dimensional vectors (embeddings), enabling support for various natural language processing (NLP) tasks such as similarity calculation between texts, clustering, and search.
curl-X'POST'\{SimpleAIInferenceendpoint}/v1/embeddings\-H'Authorization:bearersai-xxxxxxx...'\-H'Content-Type:application/json'\-d'{"model":"Qwen/Qwen3-VL-Embedding-8B","input":"What is the capital of France?","encoding_format":"float"}'
curl-X'POST'\ {SimpleAIInferenceendpoint}/v1/embeddings\-H'Authorization:bearersai-xxxxxxx...'\-H'Content-Type:application/json'\-d'{
"model": "Qwen/Qwen3-VL-Embedding-8B",
"input": "What is the capital of France?",
"encoding_format": "float" }'
Code block. Embedding API Request Example
Response
200 OK
Name
Type
Description
id
string
Unique identifier of the response
object
string
Response object’s type (example: “list”)
created
number
Creation time (Unix timestamp, in seconds)
model
string
Name of the model used
data
array
Array of objects containing embedding results
data.index
number
Order index of the input text (example: indicates the order when there are multiple input texts)
data.object
string
Data item type
data.embedding
array
Embedding vector values of the input text (composed of a float array according to the model’s embedding dimensions)
usage
object
Token Usage Statistics
usage.prompt_tokens
number
Number of tokens used in the input prompt
usage.total_tokens
number
Total token count (input + output)
usage.completion_tokens
number
Number of tokens used in the generated response
usage.prompt_tokens_details
object
Prompt token details
Table. Embedding API - 200 OK
Error Code
HTTP status code
ErrorCode description
400
Bad Request
422
When the request is denied due to policies such as Prompt Guard
The Rerank API applies an embedding model or a cross‑encoder model to calculate similarity scores between a single query and each document in a list, and reorders the document ranking based on these scores.
Generally, the score of a sentence pair represents the similarity between the two sentences on a scale from 0 to 1.
Embedding-based model: After converting the query and documents each into vectors, we measure the similarity between vectors (e.g., cosine similarity) and calculate a score.
Reranker(Cross-Encoder) based model: The query and document are input as a pair to the model for evaluation.
Specify the number of top documents to return (0 returns all)
0
> 0
5
truncate_prompt_tokens
-
integer
❌
Limit the number of input tokens
> 0
100
Table. Rerank API - Body Parameters
Example
Color mode
curl-X'POST'\{SimpleAIInferenceendpoint}/v2/rerank\-H'Authorization:bearersai-xxxxxxx...'\-H'Content-Type:application/json'\-d'{"model":"Qwen/Qwen3-VL-Reranker-8B","query":"What is the capital of France?","documents":["The capital of France is Paris.","France capital city is known for the Eiffel Tower.","Paris is located in the north-central part of France."],"top_n":2,"truncate_prompt_tokens":512}'
curl-X'POST'\ {SimpleAIInferenceendpoint}/v2/rerank\-H'Authorization:bearersai-xxxxxxx...'\-H'Content-Type:application/json'\-d'{
"model": "Qwen/Qwen3-VL-Reranker-8B",
"query": "What is the capital of France?",
"documents": [
"The capital of France is Paris.",
"France capital city is known for the Eiffel Tower.",
"Paris is located in the north-central part of France." ],
"top_n": 2,
"truncate_prompt_tokens": 512 }'
Code block. Rerank API Request Example
Response
200 OK
Name
Type
Description
id
string
Unique identifier of the API response (UUID format)
model
string
Name of the model that generated the result
usage
object
Object containing resource information used in the request
usage.prompt_tokens
integer
Number of tokens used in the input prompt
usage.total_tokens
integer
Total number of tokens used for request processing
results
array
An array containing the results of documents related to the query.
results[].index
integer
Index number in the result array
results[].document
object
An object containing the contents of the retrieved document
results[].document.text
string
The actual text content of the retrieved document
results[].document.multi_modal
object or null
Multimodal document information
results[].relevance_score
float
Score indicating the relevance between the query and the document (0 ~ 1)
Table. Rerank API - 200 OK
Error Code
HTTP status code
ErrorCode description
400
Bad Request
422
When the request is denied due to policies such as Prompt Guard
500
Internal Server Error
Table. Rerank API - Error Code
Example
Color mode
{"id":"score-xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx","model":"Qwen/Qwen3-VL-Reranker-8B","usage":{"prompt_tokens":54,"total_tokens":54},"results":[{"index":0,"document":{"text":"The capital of France is Paris.","multi_modal":null},"relevance_score":0.9237253665924072},{"index":2,"document":{"text":"Paris is located in the north-central part of France.","multi_modal":null},"relevance_score":0.9181006550788879}]}
{
"id": "score-xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
"model": "Qwen/Qwen3-VL-Reranker-8B",
"usage": {
"prompt_tokens": 54,
"total_tokens": 54 },
"results": [
{
"index": 0,
"document": {
"text": "The capital of France is Paris.",
"multi_modal": null },
"relevance_score": 0.9237253665924072 },
{
"index": 2,
"document": {
"text": "Paris is located in the north-central part of France.",
"multi_modal": null },
"relevance_score": 0.9181006550788879 }
]
}
The Responses API is compatible with OpenAI’s Responses API and can be used in the OpenAI Python client. It can generate text or JSON output from text, image, or file inputs, and supports function calls and built-in tools (web search, file search, etc.).
{“model”: “openai/gpt-oss-120b”, “input”: “What is the capital of South Korea?” }
Table. Responses API - Context
Path Parameters
Name
type
Required
Description
Default value
Boundary value
Example
None
Table. Responses API - Path Parameters
Query Parameters
Name
type
Required
Description
Default value
Boundary value
Example
None
Table. Responses API - Query Parameters
Body Parameters
Name
Name Sub
type
Required
Description
Default value
Boundary value
Example
model
-
string
✅
Model ID to use for response generation
“openai/gpt-oss-120b”
input
-
string / array
✅
Text/image/file input for the model. String or InputItem array
“Tell me a story” or [{ “role” : “user”, “content” : “message” }]
instructions
-
string
❌
System (developer) message inserted into the model context
null
“You are a helpful assistant."
temperature
-
number
❌
Sampling temperature. The higher, the more random; the lower, the more deterministic.
1
0 ~ 2
0.7
top_p
-
number
❌
Limit the nucleus sampling probability. Changing it together with temperature is not recommended.
1
0 ~ 1
0.9
top_logprobs
-
integer
❌
Maximum log-probability token count to return at each token position
null
0 ~ 20
3
stream
-
boolean
❌
Whether to return results in streaming mode
false
true/false
true
stream_options
include_usage
object
❌
Control streaming options (e.g., whether to include usage statistics)
null
{ “include_usage”: true }
tools
-
array
❌
List of tools the model can invoke (built-in tools + function)
Built-in tools: web_search, file_search, code_interpreter etc.
function: supports up to 128
[]
tool_choice
-
string / object
❌
How the model selects tools
none: do not call a tool
auto: the model chooses whether to generate a message or call a tool
required: the model calls one or more tools
When there is no tool: none
When there is a tool: auto
prompt_safety_model
-
string
❌
Specify a guard model for prompt inspection. When set, the prompt is first checked by the guard model, and if judged unsafe, the guard result is returned; if safe, the request is processed with the model specified in the model parameter.
“meta-llama/Llama-Guard-4-12B”
chat_template_kwargs
-
object
❌
Additional keyword arguments to pass to the template renderer. Used for per-model reasoning configuration (gpt-oss-120b uses the reasoning parameter, see Reasoning configuration for details).
null
{ “enable_thinking”: true }
reasoning
-
object
❌
gpt-oss-120b model’s reasoning configuration. Specify inference depth with the effort field (low/medium/high, default medium)
null
{ “effort”: “high” }
Table. Responses API - Body Parameters
Example
Color mode
curl-X'POST'\{SimpleAIInferenceendpoint}/v1/responses\-H'Authorization:bearersai-xxxxxxx...'\-H'Content-Type:application/json'\-d'{"model":"openai/gpt-oss-120b","input":"What is the capital of South Korea?"}'
curl-X'POST'\ {SimpleAIInferenceendpoint}/v1/responses\-H'Authorization:bearersai-xxxxxxx...'\-H'Content-Type:application/json'\-d'{
"model": "openai/gpt-oss-120b",
"input": "What is the capital of South Korea?" }'
Code block. Responses API Request Example
Response
200 OK
Name
Type
Description
id
string
Unique identifier of the response
object
string
Response object type (always “response”)
created_at
integer
Creation time (Unix timestamp, in seconds)
completed_at
integer or null
Completion time (exists only when in completed state)
status
string
Response status (completed/failed/in_progress/cancelled/queued/incomplete)
model
string
Used model name
output
array
Array of output items generated by the model
output[].type
string
Output item type (example: “message”)
output[].id
string
Output Item ID
output[].status
string
Item status (example: “completed”)
output[].role
string
Message author role (example: “assistant”)
output[].content
array
Content array
output[].content[].type
string
Content type (example: “output_text”)
output[].content[].text
string
Generated text
output[].content[].annotations
array
annotation array
error
object or null
Error information
incomplete_details
object or null
Reason for incompletion (reason: max_output_tokens / content_filter)
instructions
string or null
System/Developer Message
max_output_tokens
integer or null
Maximum output token count
parallel_tool_calls
boolean
Whether to allow parallel tool invocation
previous_response_id
string or null
Previous response ID
reasoning
object or null
reasoning composition (effort, summary)
store
boolean
Whether to save the response
temperature
number
Sampling temperature
text
object
Text response configuration (format, etc)
tool_choice
string / object
Tool selection method
tools
array
Tool List
top_p
number
Top P value
truncation
string
Cutting strategy
usage
object
Token Usage Statistics
usage.input_tokens
integer
Number of input tokens
usage.input_tokens_details.cached_tokens
integer
Number of cached tokens
usage.output_tokens
integer
Number of output tokens
usage.output_tokens_details.reasoning_tokens
integer
reasoning token count
usage.total_tokens
integer
Total token count
metadata
object
metadata
Table. Responses API - 200 OK
Error Code
HTTP status code
ErrorCode description
400
Bad Request
422
When the request is denied due to policies such as Prompt Guard
500
Internal Server Error
Table. Responses API - Error Code
Example
Color mode
{"id":"resp_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx","object":"response","created_at":1741476542,"status":"completed","completed_at":1741476543,"error":null,"incomplete_details":null,"instructions":null,"max_output_tokens":null,"model":"openai/gpt-oss-120b","output":[{"type":"message","id":"msg_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx","status":"completed","role":"assistant","content":[{"type":"output_text","text":"The capital of South Korea is Seoul.","annotations":[]}]}],"parallel_tool_calls":true,"previous_response_id":null,"reasoning":{"effort":null,"summary":null},"store":true,"temperature":1.0,"text":{"format":{"type":"text"}},"tool_choice":"auto","tools":[],"top_p":1.0,"truncation":"disabled","usage":{"input_tokens":54,"input_tokens_details":{"cached_tokens":0},"output_tokens":8,"output_tokens_details":{"reasoning_tokens":0},"total_tokens":62},"metadata":{}}
If the prompt_safety_model parameter is set, the guard model checks the prompt first.
safe: model The request is processed unchanged with the model specified in the model parameter.
unsafe: Returns a guard result in the following form and the request is terminated.
Color mode
{"guard_result":"unsafe","categories":["S1","S2"],"categories_description":["Violent Crimes","Non-Violent Crimes"],"messages":["Cannot fulfill the request due to violent content.","Cannot respond as it may promote illegal activities."]}
{
"guard_result": "unsafe",
"categories": ["S1", "S2"],
"categories_description": ["Violent Crimes", "Non-Violent Crimes"],
"messages": [
"Cannot fulfill the request due to violent content.",
"Cannot respond as it may promote illegal activities." ]
}
Code block. Responses API Prompt Guard response Example (unsafe)
Reasoning configuration
You can control the model-specific reasoning (inference mode) configuration via the chat_template_kwargs or reasoning parameters.
gpt-oss-120b: reasoning parameter’s effort field specifies the inference depth. * (low/medium/high, default medium)
Table. Responses API - Model-specific Reasoning Configuration
Color mode
curl-X'POST'\{SimpleAIInferenceendpoint}/v1/responses\-H'Authorization:bearersai-xxxxxxx...'\-H'Content-Type:application/json'\-d'{"model":"openai/gpt-oss-120b","input":"Please solve a complex math problem.","reasoning":{"effort":"high"}}'
curl-X'POST'\ {SimpleAIInferenceendpoint}/v1/responses\-H'Authorization:bearersai-xxxxxxx...'\-H'Content-Type:application/json'\-d'{
"model": "openai/gpt-oss-120b",
"input": "Please solve a complex math problem.",
"reasoning": {
"effort": "high" }
}'
Code block. Responses API Reasoning Setting Example
The Tokenize API converts text to token IDs. Supports two request types: Completion (prompt-based) and Chat (messages-based). Compatible with vLLM’s Tokenize API.
Body Parameters - Completion method (prompt-based)
Name
Name Sub
type
Required
Description
Default value
Boundary value
Example
prompt
-
string
✅
Text to be tokenized
“Hello, world!"
add_special_tokens
-
boolean
❌
If true, add special tokens (e.g., BOS) to the prompt.
true
true / false
true
return_token_strs
-
boolean
❌
If true, also return the token string corresponding to the token ID.
false
true / false
true
Table. Tokenize API - Body Parameters (Completion mode)
Body Parameters - Chat method (based on messages)
Name
Name Sub
type
Required
Description
Default value
Boundary value
Example
messages
role
string
✅
Message list containing conversation history
[{ “role”: “user”, “content”: “hi” }]
add_generation_prompt
-
boolean
❌
If true, add a generation prompt to the chat template. Cannot set to true simultaneously with continue_final_message.
true
true / false
true
continue_final_message
-
boolean
❌
If true, the last message is formatted in an open form without EOS. Instead of the model starting a new message, it continues that message. Cannot be set to true together with add_generation_prompt.
false
true / false
false
add_special_tokens
-
boolean
❌
If true, insert additional special tokens such as BOS in addition to the special tokens added by the chat template. Most models handle special tokens with the chat template, so the default false is recommended.
false
true / false
false
return_token_strs
-
boolean
❌
If true, also return the token string corresponding to the token ID.
false
true / false
true
chat_template
-
string
❌
Jinja template to use for conversion. Provide it if not defined in the tokenizer.
null
chat_template_kwargs
-
object
❌
Additional keyword arguments to pass to the template renderer
{"data":[{"id":"openai/gpt-oss-120b","created":1780979126,"object":"model","owned_by":"SCP Simple AI Inference"},{"id":"Qwen/Qwen3-VL-Embedding-8B","created":1781512915,"object":"model","owned_by":"SCP Simple AI Inference"},{"id":"Qwen/Qwen3-VL-Reranker-8B","created":1781512915,"object":"model","owned_by":"SCP Simple AI Inference"}],"object":"list"}