Chat Completions

POST https://api.tikway.ai/v1/chat/completions

cURL

Text input

curl --request POST \
  --url https://api.tikway.ai/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "gpt-5.6-terra",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "Write a short bedtime story about a unicorn."
        }
      ]
    }
  ]
}
'

200

{
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "message": {
        "content": "Hello! Nice to meet you. Is there anything I can do to help you?",
        "role": "assistant"
      }
    }
  ],
  "created": 1788668575,
  "id": "resp_0adb07c2e5dd99b5016a9cea9f1ea887d09cf2363ffb74d438",
  "model": "gpt-5.6-sol",
  "object": "chat.completion",
  "usage": {
    "completion_tokens": 20,
    "prompt_tokens": 8,
    "total_tokens": 28
  }
}

Authorizations

Authorization · string · header · required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json

model · string · required

The model ID used to generate the reply, such as gpt-5.6-sol or o3.

messages · object[] · required

List of conversation messages as of current date.

Minimum array length: 1

Hide child attributes

messages. role · enum<string> · required

Message author role. Newer inference models recommend using developer instead of system.

Available options: developer, system, user, assistant, tool, function

messages. name · string

Optional participant name used to distinguish different participants under the same role.

messages. content · string object[]

Message content. It can be a string, or an array composed of text, pictures, audio, and file content blocks. The assistant tool call message can be null.

messages. tool_call_id · string

When role is tool, the tool call ID to which this message responds.

messages. tool_calls · object[]

List of tool calls generated by the model when role is assistant.

Hide child attributes

messages.tool_calls. id · string

Tool call ID.

messages.tool_calls. type · enum<string>

Tool type.

Available options: function, custom

messages.tool_calls. function · object

Hide child attributes

messages.tool_calls.function. name · string

function name.

messages.tool_calls.function. arguments · string

Function parameters as JSON strings.

messages.tool_calls. custom · object

Hide child attributes

messages.tool_calls.custom. name · string

Custom tool name.

messages.tool_calls.custom. input · string

Custom tool input.

messages. function_call · object

Legacy function call information, deprecated, please use tool_calls.

Hide child attributes

messages.function_call. name · string

function name.

messages.function_call. arguments · string

Function parameters as JSON strings.

messages. refusal · string

Assistant's rejection message.

messages. audio · object

The message of the previous model audio reply.

Hide child attributes

messages.audio. id · string

Audio response ID.

audio · object | null

Audio output parameters. Required when modalities contains audio.

Hide child attributes

audio. format · enum<string>

Output audio format.

Available options: wav, aac, mp3, flac, opus, pcm16

audio. voice · string object

The sound used by the model can be a built-in sound name or a custom sound object.

temperature · number | null

Sampling temperature. Higher values ​​make the output more random; usually adjusted with top_p alternatively.

Required range: 0 <= x <= 2

top_p · number | null

Kernel sampling threshold; usually adjusted alternatively with temperature.

Required range: 0 <= x <= 1

n · integer | null

The number of candidate responses generated for each input.

Required range: x >= 1

stream · boolean | null

Whether to return incremental results in SSE streaming.

stream_options · object | null

Additional configuration for streaming output, only takes effect when stream is true.

Hide child attributes

stream_options. include_usage · boolean

Whether to return usage information in the final statistics block.

max_completion_tokens · integer | null

The maximum number of generated tokens, including visible output and inference tokens.

Required range: x >= 1

max_tokens · integer | null

Deprecated, use max_completion_tokens instead.

Required range: x >= 1

frequency_penalty · number | null

Frequency penalty. Positive values ​​reduce duplicate expressions.

Required range: -2 <= x <= 2

presence_penalty · number | null

There are penalties. This is a great time to encourage models to introduce new content.

Required range: -2 <= x <= 2

logit_bias · object | null

Specifies the generation tendency of the word element. The attribute is named token ID and has values ​​from -100 to 100.

Hide child attributes

logit_bias. {key} · number

Required range: -100 <= x <= 100

logprobs · boolean | null

Whether to return the log probability of the output token.

top_logprobs · integer | null

The number of high-probability candidate tokens returned for each output position; logprobs needs to be enabled at the same time.

Required range: 0 <= x <= 20

stop · string string[]

Stop sequence, some new models do not support it.

response_format · object

Output format configuration.

Option 1

Option 2

Option 3

Hide child attributes

response_format. type · enum<string> · required

Available options: text

tools · object[]

A list of callable tools provided to the model.

Function tools.

Option 1

Option 2

Hide child attributes

tools. type · enum<string> · required

Available options: function

tools. function · object · required

Hide child attributes

tools.function. name · string · required

Maximum string length: 64

tools.function. description · string

tools.function. parameters · object

JSON Schema of function parameters.

tools.function. strict · boolean | null

tool_choice · Option 1 · enum<string> Option 2 · object Option 3 · object Option 4 · object

Controls whether the model calls the tool, automatically selects the tool, or forces the specified tool to be called.

Available options: none, auto, required

parallel_tool_calls · boolean

Whether the model is allowed to call multiple tools in parallel.

reasoning_effort · enum<string> | null

Inference strength settings for trade-offs between speed, cost, and inference depth.

Available options: none, minimal, low, medium, high, xhigh, max

verbosity · enum<string> | null

Output verbosity.

Available options: low, medium, high

seed · integer | null

A random seed used to try to make the output reproducible.

service_tier · enum<string> | null

The requested service level.

Available options: auto, default, flex, scale, priority, fast

store · boolean | null

Whether to store the output of this request.

metadata · object | null

Additional key-value pair metadata.

Hide child attributes

metadata. {key} · string

modalities · enum<string>[] | null

Specify the output type.

Available options: text, audio

prediction · object | null

Prediction output configuration.

Hide child attributes

prediction. type · enum<string> · required

Available options: content

prediction. content · string object[] · required

Expected output content.

prompt_cache_key · string | null

Stable key for hint word cache.

prompt_cache_retention · enum<string> | null

The length of time the prompt word cache is retained.

Available options: in_memory, 24h

prompt_cache_options · object

Prompt word caching options.

Hide child attributes

prompt_cache_options. mode · enum<string>

cache mode.

Available options: implicit, explicit

prompt_cache_options. ttl · enum<string>

Cache validity period.

Available options: 30m

safety_identifier · string | null

A stable end-user identifier used to assist in detecting abuse and should not be directly personally identifiable information.

user · string

Old version of end user identification, it is recommended to use safety_identifier.

web_search_options · object

Web search tool configuration.

Hide child attributes

web_search_options. search_context_size · string

Search context size.

web_search_options. user_location · object

Approximate location of the user, used to improve localized search relevancy.

Hide child attributes

web_search_options.user_location. type · enum<string>

Available options: approximate

web_search_options.user_location. country · string

Country code.

web_search_options.user_location. city · string

City name.

web_search_options.user_location. region · string

Region or province/state name.

web_search_options.user_location. timezone · string

Time zone identifier.

function_call · enum<string> object · deprecated

Deprecated, use tool_choice.

Available options: none, auto

functions · object[] · deprecated

Deprecated, please use tools.

Hide child attributes

functions. name · string · required

Maximum string length: 64

functions. description · string

functions. parameters · object

JSON Schema of function parameters.

moderation · object | null

Configuration to perform auditing on request input and build output.

Hide child attributes

moderation. model · string

Audit model ID, such as omni-moderation-latest.

moderation. policy · object | null

Input and output audit policies.

Hide child attributes

moderation.policy. input · object | null

Hide child attributes

moderation.policy.input. mode · enum<string>

Available options: score, block

moderation.policy. output · object | null

Hide child attributes

moderation.policy.output. mode · enum<string>

Available options: score, block

Response

200 - application/json

Chat Completions non-streaming responses (chat.completion). "Generate via JSON etc. → JSON Schema" direct import for Apifox.

id · string · required

The unique ID of this chat completion.

object · enum<string> · required

Object type, fixed to chat.completion.

Available options: chat.completion

created · integer · required

Unix timestamp of the time the response was created, in seconds.

model · string · required

The actual model ID used to generate the reply.

choices · object[] · required

A list of candidate responses generated by the model.

Hide child attributes

choices. index · integer · required

The sequence number of the candidate reply, starting from 0.

choices. finish_reason · enum<string> | null · required

The reason for the end of the generation: stop is the natural end, length is the length limit reached, tool_calls is the tool call, and content_filter is content filtering.

Available options: stop, length, tool_calls, content_filter, function_call, null

choices. message · object · required

Hide child attributes

choices.message. role · enum<string> · required

Message author role, fixed to assistant.

Available options: assistant

choices.message. content · string | null

Text content generated by the model; may be null when the tool is called.

choices.message. refusal · string | null

Description generated when the model rejects a request.

choices.message. annotations · object[]

Reply to comments such as URL references.

Hide child attributes

choices.message.annotations. type · string

Annotation type, such as url_citation.

choices.message.annotations. url_citation · object

Hide child attributes

choices.message.annotations.url_citation. start_index · integer

The starting character index of the quoted text.

choices.message.annotations.url_citation. end_index · integer

The ending character index of the quoted text.

choices.message.annotations.url_citation. title · string

Quote the page title.

choices.message.annotations.url_citation. url · string

The URL of the referring page.

choices.message. audio · object | null

Audio output related data.

Hide child attributes

choices.message.audio. id · string

The unique ID of the audio response.

choices.message.audio. data · string

Base64 encoded audio data.

choices.message.audio. expires_at · integer

Unix timestamp of the audio data expiration time, in seconds.

choices.message.audio. transcript · string

Text transcription of audio content.

choices.message. function_call · object | null

Legacy function call information, deprecated.

Hide child attributes

choices.message.function_call. name · string

function name.

choices.message.function_call. arguments · string

Function parameters as JSON strings.

choices.message. tool_calls · object[]

A list of tools called by the model request.

Hide child attributes

choices.message.tool_calls. id · string

The unique ID of the tool call.

choices.message.tool_calls. type · enum<string>

Tool type.

Available options: function

choices.message.tool_calls. function · object

Hide child attributes

choices.message.tool_calls.function. name · string

The name of the function called by the model.

choices.message.tool_calls.function. arguments · string

Function parameters in the form of JSON strings should be parsed and verified before use.

choices. logprobs · object | null

Outputs log-probability information for tokens; only returned if logprobs is enabled on request.

Hide child attributes

choices.logprobs. content · object[] | null

Output the probability information of each token in the content.

Hide child attributes

choices.logprobs.content. token · string

Tome text.

choices.logprobs.content. bytes · integer[] | null

The UTF-8 byte sequence corresponding to the token.

choices.logprobs.content. logprob · number

The logarithmic probability of this token.

choices.logprobs.content. top_logprobs · object[]

The most likely candidate token for this position.

Hide child attributes

choices.logprobs.content.top_logprobs. token · string

choices.logprobs.content.top_logprobs. bytes · integer[] | null

choices.logprobs.content.top_logprobs. logprob · number

usage · object

Word usage statistics for this request.

Hide child attributes

usage. prompt_tokens · integer

Enter the number of tokens used in the prompt word.

usage. completion_tokens · integer

The number of tokens used by the model to generate content.

usage. total_tokens · integer

The total number of tokens requested.

usage. prompt_tokens_details · object

Enter the word element details.

Hide child attributes

usage.prompt_tokens_details. cached_tokens · integer

The number of tokens in the input that hit the cache.

usage.prompt_tokens_details. audio_tokens · integer

The number of audio tokens in the input.

usage.prompt_tokens_details. image_tokens · integer

Number of image tokens in the input.

usage.prompt_tokens_details. text_tokens · integer

The number of text tokens in the input.

usage.prompt_tokens_details. cache_write_tokens · integer

The number of original tokens written to the prompt word cache.

usage. completion_tokens_details · object

Generate token details.

Hide child attributes

usage.completion_tokens_details. reasoning_tokens · integer

The number of tokens used by the model for inference.

usage.completion_tokens_details. audio_tokens · integer

The number of audio tokens generated by the model.

usage.completion_tokens_details. text_tokens · integer

The number of text tokens generated by the model.

usage.completion_tokens_details. accepted_prediction_tokens · integer

The number of predicted tokens that actually appear in the generated results.

usage.completion_tokens_details. rejected_prediction_tokens · integer

The number of predicted tokens that did not appear in the generated results.

service_tier · string | null

The actual service level used to handle this request.

system_fingerprint · string | null

The backend configuration fingerprint for the model to run on.

metadata · object

Metadata associated with the request.

Hide child attributes

metadata. {key} · string