API Overview

Accessing the API

All API endpoints are available at https://api.thesys.dev/v1.

Authentication

Authentication is done via API keys. You can create API keys from the keys page. API keys must be sent as a Authorization header with the value Bearer <api_key>. If the API key is not valid, you will receive a 403 error.

Rate Limits

Please refer to the Rate Limits page for more information.

Errors

Please refer to the Errors page for more information.

Examples

For Chat Completions API

from openai import OpenAI
client = OpenAI(
    base_url="https://api.thesys.dev/v1/embed",
    api_key="<api_key>"
)

completion = client.chat.completions.create(
model="c1/anthropic/claude-sonnet-4/v-20250930",
messages=[
{
"role": "user",
"content": "How did the population of the world grow from 1950 to 2020?"
}
])

Stream this response via the language specific helper functions to the react client.

For Responses API

from openai import OpenAI
client = OpenAI(
    base_url="https://api.thesys.dev/v1/embed",
    api_key="<api_key>"
)

response = client.responses.create(
model="c1/anthropic/claude-sonnet-4/v-20250930",
input="How did the population of the world grow from 1950 to 2020?"
)

print(response)

Chat Completions API

For C1 Gemini models, the reasoning_effort parameter translates to the following max reasoning tokens:

`reasoning_effort`	3 Flash - Max reasoning tks	3 Pro - Max reasoning tks
`none`	0	256
`minimal`	512	512
`low`	1024	1024
`medium`	2048	2048
`high`	4096	4096
`xhigh`	8192	8192

Property	C1 OpenAI models	C1 Anthropic Models
`messages`	(audio not supported)	(audio not supported)
`model`
`audio`
`frequency_penalty`
`function_call`	use `tool_choice`	use `tool_choice`
`functions`	use `tools`	use `tools`
`logit_bias`
`logprobs`
`max_completion_tokens`
`max_tokens`
`metadata`	`thesys` metadata only	`thesys` metadata only
`modalities`
`n`	must be `1`	must be `1`
`parallel_tool_calls`	`true` by default	`true` by default
`prediction`
`presence_penalty`
`prompt_cache_key`
`reasoning_effort`
`response_format`
`service_tier`
`stop`
`stream`
`temperature`
`tool_choice`
`tools`
`top_p`
`verbosity`
`web_search_options`

Responses API

All C1 models are supported via the Responses API, including OpenAI and non-OpenAI models. Our Responses API implementation is Open Responses compliant.

There are three ways to maintain chat history in Responses API:

Pass the full conversation history — Include all previous messages in the input array with each request.
Use previous_response_id — Reference a prior response by its ID to automatically chain conversations (requires store: true).
Use conversation — Group related responses into a named conversation for persistent multi-turn context (requires store: true).

To create a conversation using previous_response_id:

from openai import OpenAI
client = OpenAI(
    base_url="https://api.thesys.dev/v1/embed",
    api_key="<api_key>"
)

response = client.responses.create(
model="c1/anthropic/claude-sonnet-4/v-20250930",
input="What is the capital of France?"
)

follow_up = client.responses.create(
model="c1/anthropic/claude-sonnet-4/v-20250930",
input="And what is its population?",
previous_response_id=response.id
)

print(follow_up)

To create a conversation and use it across multiple requests:

from openai import OpenAI

# Client for conversation management

conv_client = OpenAI(
base_url="https://api.thesys.dev",
api_key="<api_key>"
)

# Client for generation

embed_client = OpenAI(
base_url="https://api.thesys.dev/v1/embed",
api_key="<api_key>"
)

conversation = conv_client.conversations.create()

response = embed_client.responses.create(
model="c1/anthropic/claude-sonnet-4/v-20250930",
input="What is the capital of France?",
store=True,
conversation={"id": conversation.id}
)

follow_up = embed_client.responses.create(
model="c1/anthropic/claude-sonnet-4/v-20250930",
input="And what is its population?",
store=True,
conversation={"id": conversation.id}
)

print(follow_up)

Built-in tools (web_search, file_search, code_interpreter, computer_use, mcp) will be supported soon.

Property	Supported
`background`	Always `false`
`conversation`	with `store: true`
`include`
`input`
`instructions`
`max_output_tokens`
`max_tool_calls`
`metadata`	`thesys` metadata only
`model`
`parallel_tool_calls`	`true` by default
`previous_response_id`	with `store: true`
`prompt`
`prompt_cache_key`
`prompt_cache_retention`
`reasoning`	`effort` only
`safety_identifier`
`service_tier`
`store`	`true` by default
`stream`
`temperature`
`text`	`verbosity` only
`tool_choice`
`tools`	`function` only; built-in tools coming soon
`top_logprobs`
`top_p`

`input` item types

Input Item Type	Supported
`message` (user/system/developer/assistant)
`function_call`
`function_call_output`
`item_reference`
`reasoning`
`compaction`	coming soon
`web_search_call`	coming soon
`file_search_call`	coming soon
`computer_call` / `computer_call_output`	coming soon
`code_interpreter_call`	coming soon
`image_generation_call`	coming soon
`local_shell_call` / `local_shell_call_output`
`shell_call` / `shell_call_output`
`apply_patch_call` / `apply_patch_call_output`
`mcp_list_tools` / `mcp_approval_request` / `mcp_approval_response` / `mcp_call`	coming soon
`custom_tool_call` / `custom_tool_call_output`

`text` sub-fields

Property	Supported
`text.verbosity`
`text.format`	Always Thesys format

API

React

SDK

Accessing the API

Authentication

Rate Limits

Errors

Examples

For Chat Completions API

For Responses API

Chat Completions API

Responses API

`input` item types

`text` sub-fields

API

React

SDK

​Accessing the API

​Authentication

​Rate Limits

​Errors

​Examples

​For Chat Completions API

​For Responses API

​Chat Completions API

​Responses API

​input item types

​text sub-fields

Accessing the API

Authentication

Rate Limits

Errors

Examples

For Chat Completions API

For Responses API

Chat Completions API

Responses API

`input` item types

`text` sub-fields