Messages

curl --request POST \
  --url https://api.tikway.ai/v1/messages \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <api-key>' \
  --data '
{
  "model": "claude-sonnet-4-6",
  "max_tokens": 1024,
  "system": "You are a helpful assistant.",
  "messages": [
    {
      "role": "user",
      "content": "Write a short bedtime story about a unicorn."
    }
  ]
}
'

{
  "id": "msg_013Zva2CMHLNnXjNJJKqJ2EF",
  "container": {
    "id": "container_011CpZohnwH4vuy7gazohgSP",
    "expires_at": "2019-12-27T18:11:19.117Z",
    "skills": [
      {
        "skill_id": "pdf",
        "type": "anthropic",
        "version": "latest"
      }
    ]
  },
  "content": [
    {
      "citations": [
        {
          "cited_text": "The grass is green. The sky is blue.",
          "document_index": 0,
          "document_title": "My Document",
          "end_char_index": 0,
          "file_id": "file_011CNha8iCJcU1wXNR6q4V8w",
          "start_char_index": 0,
          "type": "char_location"
        }
      ],
      "text": "Hi! My name is Claude.",
      "type": "text"
    }
  ],
  "context_management": {
    "applied_edits": [
      {
        "cleared_input_tokens": 0,
        "cleared_tool_uses": 0,
        "type": "clear_tool_uses_20250919"
      }
    ]
  },
  "diagnostics": {
    "cache_miss_reason": {
      "cache_missed_input_tokens": 0,
      "type": "model_changed"
    }
  },
  "model": "claude-opus-5",
  "role": "assistant",
  "stop_details": {
    "category": "cyber",
    "explanation": "This request was declined because it conflicts with Anthropic's Usage Policy.",
    "fallback_credit_token": "QW50aHJvcGljL0NsYXVkZQ==",
    "fallback_has_prefill_claim": true,
    "recommended_model": "claude-opus-4-8",
    "type": "refusal"
  },
  "stop_reason": "end_turn",
  "stop_sequence": null,
  "type": "message",
  "usage": {
    "cache_creation": {
      "ephemeral_1h_input_tokens": 0,
      "ephemeral_5m_input_tokens": 0
    },
    "cache_creation_input_tokens": 2051,
    "cache_read_input_tokens": 2051,
    "fallback_credit": {
      "status": {
        "type": "redeemed"
      }
    },
    "inference_geo": "global",
    "input_tokens": 2095,
    "iterations": [
      {
        "cache_creation": {
          "ephemeral_1h_input_tokens": 0,
          "ephemeral_5m_input_tokens": 0
        },
        "cache_creation_input_tokens": 0,
        "cache_read_input_tokens": 0,
        "input_tokens": 0,
        "model": "claude-fable-5-1",
        "output_tokens": 0,
        "type": "message"
      }
    ],
    "output_tokens": 503,
    "output_tokens_details": {
      "thinking_tokens": 0
    },
    "server_tool_use": {
      "web_fetch_requests": 2,
      "web_search_requests": 0
    },
    "service_tier": "standard",
    "speed": "standard"
  },
  "input_transformations": [
    {
      "path": "path",
      "reason": "model_binding_mismatch",
      "type": "thinking_dropped"
    }
  ]
}

POST

https://api.tikway.ai

messages

curl --request POST \
  --url https://api.tikway.ai/v1/messages \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <api-key>' \
  --data '
{
  "model": "claude-sonnet-4-6",
  "max_tokens": 1024,
  "system": "You are a helpful assistant.",
  "messages": [
    {
      "role": "user",
      "content": "Write a short bedtime story about a unicorn."
    }
  ]
}
'

{
  "id": "msg_013Zva2CMHLNnXjNJJKqJ2EF",
  "container": {
    "id": "container_011CpZohnwH4vuy7gazohgSP",
    "expires_at": "2019-12-27T18:11:19.117Z",
    "skills": [
      {
        "skill_id": "pdf",
        "type": "anthropic",
        "version": "latest"
      }
    ]
  },
  "content": [
    {
      "citations": [
        {
          "cited_text": "The grass is green. The sky is blue.",
          "document_index": 0,
          "document_title": "My Document",
          "end_char_index": 0,
          "file_id": "file_011CNha8iCJcU1wXNR6q4V8w",
          "start_char_index": 0,
          "type": "char_location"
        }
      ],
      "text": "Hi! My name is Claude.",
      "type": "text"
    }
  ],
  "context_management": {
    "applied_edits": [
      {
        "cleared_input_tokens": 0,
        "cleared_tool_uses": 0,
        "type": "clear_tool_uses_20250919"
      }
    ]
  },
  "diagnostics": {
    "cache_miss_reason": {
      "cache_missed_input_tokens": 0,
      "type": "model_changed"
    }
  },
  "model": "claude-opus-5",
  "role": "assistant",
  "stop_details": {
    "category": "cyber",
    "explanation": "This request was declined because it conflicts with Anthropic's Usage Policy.",
    "fallback_credit_token": "QW50aHJvcGljL0NsYXVkZQ==",
    "fallback_has_prefill_claim": true,
    "recommended_model": "claude-opus-4-8",
    "type": "refusal"
  },
  "stop_reason": "end_turn",
  "stop_sequence": null,
  "type": "message",
  "usage": {
    "cache_creation": {
      "ephemeral_1h_input_tokens": 0,
      "ephemeral_5m_input_tokens": 0
    },
    "cache_creation_input_tokens": 2051,
    "cache_read_input_tokens": 2051,
    "fallback_credit": {
      "status": {
        "type": "redeemed"
      }
    },
    "inference_geo": "global",
    "input_tokens": 2095,
    "iterations": [
      {
        "cache_creation": {
          "ephemeral_1h_input_tokens": 0,
          "ephemeral_5m_input_tokens": 0
        },
        "cache_creation_input_tokens": 0,
        "cache_read_input_tokens": 0,
        "input_tokens": 0,
        "model": "claude-fable-5-1",
        "output_tokens": 0,
        "type": "message"
      }
    ],
    "output_tokens": 503,
    "output_tokens_details": {
      "thinking_tokens": 0
    },
    "server_tool_use": {
      "web_fetch_requests": 2,
      "web_search_requests": 0
    },
    "service_tier": "standard",
    "speed": "standard"
  },
  "input_transformations": [
    {
      "path": "path",
      "reason": "model_binding_mismatch",
      "type": "thinking_dropped"
    }
  ]
}

Authorizations

x-api-key

string

header

required

Tikway API Key. Passed through the x-api-key request header according to the Anthropic native protocol.

Body

application/json

model

string

required

The Claude model ID used to generate the message, for example claude-opus-5.

max_tokens

integer

required

The maximum number of tokens to generate content. The model can be stopped before reaching the upper limit; set to 0 to only warm up the prompt cache without generating a reply.

Required range: x >= 0

messages

object[]

required

Enter the conversation message. The model works in user and assistant turns; consecutive messages with the same role will be merged. If there is no system role, please use the top-level system for system prompt words.

Maximum array length: 100000

Hide child attributes

messages.role

enum<string>

required

Message role. When the last item is assistant , the model will continue to be generated from its content.

Available options:

user,

assistant

messages.content

required

Message content. A string is equivalent to an array containing only one text block.

system

System prompt word. The Messages API does not support system role messages, this field should be used.

stream

boolean

Whether to stream message events as Server-Sent Events.

stop_sequences

string[]

Customize stop sequence; model generation stops when it reaches any sequence.

temperature

number

Sampling temperature. Higher values make the output more random; usually adjusted with top_p, top_k.

Required range: 0 <= x <= 1

top_p

number

Kernel sampling threshold.

Required range: 0 <= x <= 1

top_k

integer

The number of candidate tokens with the highest probability retained during each sampling step.

Required range: x >= 0

thinking

Enabled thinking · object

Extended thinking configuration. Optional enabled, adaptive, disabled, or passed in null. When think is enabled, think tokens count toward max_tokens.

Enabled thinking
Adaptive thinking
Disabled thinking

Hide child attributes

thinking.type

enum<string>

required

Available options:

enabled

thinking.budget_tokens

integer

required

Think about the token budget, which must be less than max_tokens.

Required range: x >= 1024

thinking.block_binding

object | null

How to handle when the returned thought block does not pass the dialog prefix check; omitted, null or empty objects use the default behavior.

Hide child attributes

thinking.block_binding.prefix_mismatch_behavior

enum<string> | null

default:error

error will return 400; drop_block will remove unmatched think blocks.

Available options:

error,

drop_block,

null

thinking.display

enum<string> | null

default:summarized

Think about how the content is presented; omitted will hide the content but retain the signature for multiple rounds of conversation.

Available options:

summarized,

omitted,

updates,

null

tools

object[]

A tool definition that can be called by Claude.

Hide child attributes

tools.name

string

Tool name.

tools.description

string

Description of tool usage.

tools.input_schema

object

JSON Schema of tool input parameters.

tools.type

string

Tool type; custom tools are usually custom or omitted.

tools.cache_control

object

Hide child attributes

tools.cache_control.type

enum<string>

Available options:

ephemeral

tools.cache_control.ttl

enum<string>

Available options:

5m,

1h

tool_choice

object

Controls whether and how Claude selects tools.

Hide child attributes

tool_choice.type

enum<string>

Tool selection mode.

Available options:

auto,

any,

tool,

none

tool_choice.name

string

The name of the tool that is forced to be called when type is tool.

tool_choice.disable_parallel_tool_use

boolean

Whether to disable parallel tool calls.

output_config

object

Output configuration.

Hide child attributes

output_config.effort

enum<string>

Output reasoning/quality input level.

Available options:

low,

medium,

high

output_config.format

object

Structured output format.

Hide child attributes

output_config.format.type

enum<string>

Available options:

json_schema

output_config.format.schema

object

Target JSON Schema.

output_format

object

JSON output format configuration.

Hide child attributes

output_format.type

enum<string>

Available options:

json_schema

output_format.schema

object

Target JSON Schema.

metadata

object

Request metadata.

Hide child attributes

metadata.user_id

string

End user identification.

service_tier

enum<string>

Service level selection.

Available options:

auto,

standard_only

speed

enum<string>

Inference speed mode.

Available options:

standard,

fast

container

Code execution container configuration or container ID.

context_management

object

Context management configuration.

mcp_servers

object[]

MCP server definition.

Hide child attributes

mcp_servers.name

string

mcp_servers.url

string

mcp_servers.authorization_token

string

cache_control

object

Request-level prompt word cache control.

Hide child attributes

cache_control.type

enum<string>

Available options:

ephemeral

cache_control.ttl

enum<string>

Available options:

5m,

1h

diagnostics

object

Diagnostic information configuration.

fallback_credit_token

Fallback service deduction token.

fallbacks

object

Model fallback configuration.

inference_geo

string

Reasoning about geographic preferences.

compaction

object | null

Anthropic conversation compaction. Non-null values cannot be combined with context_management.

Hide child attributes

compaction.type

string

required

Allowed value: "summarize"

compaction.instructions

string | null

Maximum string length: 16384

Response

200 - application/json

string

required

Message unique ID.

type

enum<string>

required

Object type, fixed to message.

Available options:

message

role

enum<string>

required

Message role, fixed to assistant.

Available options:

assistant

model

string

required

The actual Claude model ID used.

content

object[]

required

List of content blocks generated by Claude.

Hide child attributes

content.type

enum<string>

required

Output content block type.

Available options:

text,

thinking,

redacted_thinking,

tool_use,

server_tool_use,

web_search_tool_result,

web_fetch_tool_result,

code_execution_tool_result

content.text

string

text Generated text for the content block.

content.citations

object[]

List of textual references.

Hide child attributes

content.citations.type

string

Reference type.

content.citations.cited_text

string

Quoted text.

content.citations.document_index

integer

Source document index.

content.citations.document_title

string

Source document title.

content.citations.start_char_index

integer

content.citations.end_char_index

integer

content.citations.url

string

content.citations.title

string

content.thinking

string

Extended reflection text.

content.signature

string

Think about the content signature; it must remain the same the next time you pass it around.

content.data

string

Encrypted data for redacted_thinking.

content.id

string

Tool call ID.

content.name

string

The name of the called tool.

content.input

object

Tool call input parameters.

content.content

any

Server tool call result content.

content.tool_use_id

string

The associated tool call ID.

content.is_error

boolean

Whether the server tool results are in error.

stop_reason

enum<string>

required

Generate a stop reason.

Available options:

end_turn,

max_tokens,

stop_sequence,

tool_use,

pause_turn,

refusal,

model_context_window_exceeded

usage

object

required

Billing and current limiting word usage statistics.

Hide child attributes

usage.input_tokens

integer

required

Enter the number of tokens.

Required range: x >= 0

usage.output_tokens

integer

required

Output the number of tokens.

Required range: x >= 0

usage.cache_creation_input_tokens

integer

The number of input tokens used to create the cache.

Required range: x >= 0

usage.cache_read_input_tokens

integer

The number of input tokens read from the cache.

Required range: x >= 0

usage.cache_creation

object

Hide child attributes

usage.cache_creation.ephemeral_5m_input_tokens

integer

usage.cache_creation.ephemeral_1h_input_tokens

integer

usage.output_tokens_details

object

Hide child attributes

usage.output_tokens_details.thinking_tokens

integer

Think about word count.

usage.server_tool_use

object

Hide child attributes

usage.server_tool_use.web_search_requests

integer

usage.server_tool_use.web_fetch_requests

integer

usage.service_tier

enum<string>

Actual service level.

Available options:

standard,

priority,

batch

usage.speed

enum<string>

Actual reasoning speed.

Available options:

standard,

fast

stop_sequence

string

If the sequence ends due to a custom stop, it is a hit sequence.

stop_details

object

Structured information for rejection and other stopping situations.

Hide child attributes

stop_details.type

string

stop_details.category

string

stop_details.explanation

string

stop_details.recommended_model

string

container

object

Code execution container information.

Hide child attributes

container.id

string

container.expires_at

string

Container expiration time.

container.skills

string[]

context_management

object

Context management results of server-side applications.

diagnostics

object

Diagnostic information, such as cache miss reasons.

input_transformations

object[]

Transformations applied by the API to the input, such as chunks of thought that are discarded.

Hide child attributes

input_transformations.type

enum<string>

Available options:

thinking_dropped

input_transformations.path

string

input_transformations.reason

enum<string>

Available options:

model_binding_mismatch,

prefix_binding_mismatch,

organization_binding_mismatch,

end_user_binding_mismatch

Chat completions

Image generation

Video generation

Embeddings

Transcriptions

Speech synthesis

Decisions

Utilities

Authorizations

Body

Response