curl -X POST https://api-llm.sunra.ai/v1/messages \
-H "Authorization: Bearer <SUNRA_KEY>" \
-H "Content-Type: application/json" \
-d '{
"model": "anthropic/claude-sonnet-4-6",
"max_tokens": 1024,
"messages": [
{
"role": "user",
"content": "Hello, how are you?"
}
]
}'
import requests
response = requests.post(
"https://api-llm.sunra.ai/v1/messages",
headers={
"Authorization": "Bearer <SUNRA_KEY>",
"Content-Type": "application/json"
},
json={
"model": "anthropic/claude-sonnet-4-6",
"max_tokens": 1024,
"messages": [
{"role": "user", "content": "Hello, how are you?"}
]
}
)
print(response.json())
const response = await fetch("https://api-llm.sunra.ai/v1/messages", {
method: "POST",
headers: {
"Authorization": "Bearer <SUNRA_KEY>",
"Content-Type": "application/json"
},
body: JSON.stringify({
model: "anthropic/claude-sonnet-4-6",
max_tokens: 1024,
messages: [
{ role: "user", content: "Hello, how are you?" }
]
})
});
const data = await response.json();
console.log(data);
{
"id": "msg_01XFDUDYJgAACzvnptvVoYEL",
"type": "message",
"role": "assistant",
"container": null,
"content": [
{
"type": "text",
"text": "Hello! I'm doing well, thank you for asking. How can I help you today?",
"citations": null
}
],
"model": "anthropic/claude-sonnet-4-6",
"stop_reason": "end_turn",
"stop_sequence": null,
"usage": {
"input_tokens": 12,
"output_tokens": 19,
"total_tokens": 31,
"cache_creation_input_tokens": null,
"cache_read_input_tokens": null,
"cache_creation": null,
"inference_geo": null,
"server_tool_use": null,
"service_tier": null,
"sunra_usage_semantics": "anthropic.exclusive.v1"
}
}
LLM
Create a message
POST
/
v1
/
messages
curl -X POST https://api-llm.sunra.ai/v1/messages \
-H "Authorization: Bearer <SUNRA_KEY>" \
-H "Content-Type: application/json" \
-d '{
"model": "anthropic/claude-sonnet-4-6",
"max_tokens": 1024,
"messages": [
{
"role": "user",
"content": "Hello, how are you?"
}
]
}'
import requests
response = requests.post(
"https://api-llm.sunra.ai/v1/messages",
headers={
"Authorization": "Bearer <SUNRA_KEY>",
"Content-Type": "application/json"
},
json={
"model": "anthropic/claude-sonnet-4-6",
"max_tokens": 1024,
"messages": [
{"role": "user", "content": "Hello, how are you?"}
]
}
)
print(response.json())
const response = await fetch("https://api-llm.sunra.ai/v1/messages", {
method: "POST",
headers: {
"Authorization": "Bearer <SUNRA_KEY>",
"Content-Type": "application/json"
},
body: JSON.stringify({
model: "anthropic/claude-sonnet-4-6",
max_tokens: 1024,
messages: [
{ role: "user", content: "Hello, how are you?" }
]
})
});
const data = await response.json();
console.log(data);
{
"id": "msg_01XFDUDYJgAACzvnptvVoYEL",
"type": "message",
"role": "assistant",
"container": null,
"content": [
{
"type": "text",
"text": "Hello! I'm doing well, thank you for asking. How can I help you today?",
"citations": null
}
],
"model": "anthropic/claude-sonnet-4-6",
"stop_reason": "end_turn",
"stop_sequence": null,
"usage": {
"input_tokens": 12,
"output_tokens": 19,
"total_tokens": 31,
"cache_creation_input_tokens": null,
"cache_read_input_tokens": null,
"cache_creation": null,
"inference_geo": null,
"server_tool_use": null,
"service_tier": null,
"sunra_usage_semantics": "anthropic.exclusive.v1"
}
}
Creates a message using the Anthropic Messages API format. Supports text, images, PDFs, tools, and extended thinking.
Authentication
string
required
Bearer token. Use your API key as the bearer token in the Authorization header.Format:
Bearer <SUNRA_KEY>Request
This endpoint expects an object.string
required
The model that will complete your prompt. Browse available models at sunra.ai/models.
object
Optional provider routing preferences. Omit for automatic routing. See Provider routing for supported fields and provider discovery.
object[] | null
required
Input messages. Each input message must be an object with a
role and content. You can specify a single user-role message, or include multiple user and assistant messages for multi-turn conversations.Show properties
Show properties
string
required
The role of the message author. Supported values:
user, assistant.string | object[]
required
The content of the message. Can be a single string or an array of content blocks.
Show content block types
Show content block types
- TextBlockParam
- ImageBlockParam
- DocumentBlockParam
- ToolUseBlockParam
- ToolResultBlockParam
- ThinkingBlockParam
- RedactedThinkingBlockParam
string
required
Value:
text.string
required
The text content.
object[] | null
Citations for the text block.
string
required
Value:
image.object
required
object
Cache control breakpoint at this content block.
string
required
Value:
document.object
required
Document source.
Show source variants
Show source variants
- base64
- text
- content
- url
string
required
Value:
base64.string
required
Value:
application/pdf.string
required
Base64-encoded PDF data.
object
Citations configuration.
Show properties
Show properties
boolean
Whether citations are enabled for this document.
string
Additional context for the document.
string
Title of the document.
object
Cache control breakpoint at this content block.
string
required
Value:
tool_use.string
required
The ID of the tool use.
string
required
The name of the tool.
object
required
The input to the tool.
object
Cache control breakpoint at this content block.
string
required
Value:
tool_result.string
required
The ID of the tool use this result corresponds to.
string | object[]
The result content. Can be a string or an array of content blocks.
boolean
Whether this is an error result.
object
Cache control breakpoint at this content block.
string
required
Value:
thinking.string
required
The thinking content.
string
required
The signature of the thinking block.
number
The maximum number of tokens to generate before stopping. Note that the model may stop before reaching this maximum. Different models have different maximum values for this parameter; a value above a model’s own ceiling is rejected with
400 rather than reduced. See Output limits.string | object[]
System prompt. A system prompt is a way of providing context and instructions to the model.Can be a string or an array of
TextBlockParam objects, each containing text, type ("text"), optional cache_control, and optional citations.boolean
default:false
Whether to incrementally stream the response using server-sent events (SSE). Streams are subject to an idle timeout and a lifetime ceiling — see Output limits and stream lifetime. A non-streaming request is terminated at the edge if the response takes too long to arrive, so any request that may generate for more than ~90 seconds must set
stream: true — see the edge timeout.number
default:1
Amount of randomness injected into the response. Ranges from 0.0 to 1.0. Use
temperature closer to 0.0 for analytical/multiple choice tasks, and closer to 1.0 for creative and generative tasks. Note that even with temperature of 0.0, the results will not be fully deterministic. For OpenAI reasoning models (gpt-5.x, gpt-6-*) with reasoning enabled, temperature and top_p are not supported upstream and are dropped silently by the gateway.number
Use nucleus sampling. Computes the cumulative distribution over all options for each subsequent token in decreasing probability order and cuts it off once it reaches the probability specified by
top_p. Recommended for advanced use cases only. You usually only need to use temperature.number
Only sample from the top K options for each subsequent token. Used to remove “long tail” low probability responses. Recommended for advanced use cases only.
string[]
Custom text sequences that will cause the model to stop generating. If the model encounters one of the custom sequences, the response
stop_reason value will be "stop_sequence" and the response stop_sequence value will contain the matched stop sequence.object[]
Definitions of tools that the model may use. Supports custom tools, Anthropic built-in tools, and server tools.
Show tool types
Show tool types
- Custom Tool
- Bash Tool
- Text Editor Tool
- Web Search Tool
string
required
Name of the tool. This is how the tool will be called by the model.
object
required
JSON schema for the tool’s input. This defines the shape of the
input that your tool accepts and that the model will produce.string
Description of what this tool does. Tool descriptions should be as detailed as possible.
string
Value:
custom.string
required
Value:
text_editor_20250124.string
required
Value:
str_replace_editor.object
Cache control breakpoint.
string
required
Value:
web_search_20250305.string
required
Value:
web_search.string[] | null
If provided, only these domains will be included in results. Cannot be used alongside
blocked_domains.string[] | null
If provided, these domains will never appear in results. Cannot be used alongside
allowed_domains.number | null
Maximum number of times the tool can be used in the API request.
object | null
object
Cache control breakpoint.
object
How the model should use the provided tools. The model can use a specific tool, any available tool, decide by itself, or not use tools at all.
Show variants
Show variants
- auto
- any
- none
- tool
string
required
Value:
auto.boolean
Whether to disable parallel tool use. Defaults to
false. If true, the model will output at most one tool use.string
required
Value:
any.boolean
Whether to disable parallel tool use. Defaults to
false. If true, the model will output exactly one tool use.string
required
Value:
none.object
Configuration for enabling Claude’s extended thinking. When enabled, responses include
thinking content blocks showing Claude’s thinking process before the final answer. Requires a minimum budget of 1,024 tokens. For OpenAI-family reasoning models (gpt-5.x, gpt-6-*) the gateway maps this to reasoning_effort: {"type": "disabled"} becomes reasoning_effort: "none", budget_tokens still selects the effort level, and an explicit reasoning_effort always wins.object
Configuration for controlling output behavior. Supports the effort parameter and structured output format.
Show properties
Show properties
string | null
How much effort the model should put into its response. Higher effort levels may result in more thorough analysis but take longer. Valid values:
low, medium, high, max.object
string
Determines whether to use priority capacity or standard capacity for this request. Supported values:
auto, standard_only.object
An object describing metadata about the request.
Show properties
Show properties
string
An external identifier for the user who is associated with the request. This should be a uuid, hash value, or other opaque identifier.
Response
Successful message response.string
Unique message identifier, e.g.
msg_01XFDUDYJgAACzvnptvVoYEL. Currently the upstream model provider’s own id, forwarded as-is. This is switching to a Sunra-issued value (breaking change, date to be announced): see Response identifiers and tracking. The same id is always available via the x-sunra-prediction-id response header, unaffected by that change. On streaming responses, the equivalent value is message_start.message.id.string
Object type. Always
message.string
Conversational role of the generated message. Always
assistant.object | null
object[]
Content generated by the model. This is an array of content blocks, each of which has a
type that determines its shape.Show content block types
Show content block types
- TextBlock
- ToolUseBlock
- ThinkingBlock
- RedactedThinkingBlock
- ServerToolUseBlock
- WebSearchToolResultBlock
- WebFetchToolResultBlock
- CodeExecutionToolResultBlock
string
Value:
text.string
The generated text.
object[] | null
Citations supporting the text block. Can be
char_location, page_location, content_block_location, web_search_result_location, or search_result_location.string
Value:
tool_use.string
The ID of the tool use block.
string
The name of the tool.
object
The input to the tool as generated by the model.
string
Value:
server_tool_use.string
The ID of the tool use block.
string
The server tool name. e.g.,
web_search, web_fetch, code_execution.object
The input to the server tool.
string
Value:
web_search_tool_result.string
The ID of the tool use this result corresponds to.
object | object[]
Search results or error object.
string
Value:
web_fetch_tool_result.string
The ID of the tool use this result corresponds to.
object
Fetched content or error object.
string
The model that handled the request.
string | null
The reason that the model stopped generating. Possible values:
end_turn— the model reached a natural stopping pointmax_tokens— exceededmax_tokensor the model’s maximumstop_sequence— one of your custom stop sequences was generatedtool_use— the model invoked one or more toolspause_turn— a long-running turn was pausedrefusal— streaming classifiers intervened for potential policy violations
string | null
Which custom stop sequence was generated, if any.
object
Billing and rate-limit usage. The three input buckets are mutually exclusive — see Token usage.
Show properties
Show properties
integer
The number of fresh input tokens which were used. Excludes both cache buckets.
integer
The number of output tokens which were used.
integer
All input buckets plus
output_tokens. Omitted on streamed responses.integer | null
The number of input tokens used to create the cache entry.
integer | null
The number of input tokens read from the cache.
string | null
Present as
anthropic.exclusive.v1 when Sunra normalized this response. Assert on this value rather than inferring the convention from the numbers. See Token usage.object | null
string | null
The geographic region where inference was performed for this request.
object | null
string | null
If the request used the priority, standard, or batch tier. Values:
standard, priority, batch.curl -X POST https://api-llm.sunra.ai/v1/messages \
-H "Authorization: Bearer <SUNRA_KEY>" \
-H "Content-Type: application/json" \
-d '{
"model": "anthropic/claude-sonnet-4-6",
"max_tokens": 1024,
"messages": [
{
"role": "user",
"content": "Hello, how are you?"
}
]
}'
import requests
response = requests.post(
"https://api-llm.sunra.ai/v1/messages",
headers={
"Authorization": "Bearer <SUNRA_KEY>",
"Content-Type": "application/json"
},
json={
"model": "anthropic/claude-sonnet-4-6",
"max_tokens": 1024,
"messages": [
{"role": "user", "content": "Hello, how are you?"}
]
}
)
print(response.json())
const response = await fetch("https://api-llm.sunra.ai/v1/messages", {
method: "POST",
headers: {
"Authorization": "Bearer <SUNRA_KEY>",
"Content-Type": "application/json"
},
body: JSON.stringify({
model: "anthropic/claude-sonnet-4-6",
max_tokens: 1024,
messages: [
{ role: "user", content: "Hello, how are you?" }
]
})
});
const data = await response.json();
console.log(data);
{
"id": "msg_01XFDUDYJgAACzvnptvVoYEL",
"type": "message",
"role": "assistant",
"container": null,
"content": [
{
"type": "text",
"text": "Hello! I'm doing well, thank you for asking. How can I help you today?",
"citations": null
}
],
"model": "anthropic/claude-sonnet-4-6",
"stop_reason": "end_turn",
"stop_sequence": null,
"usage": {
"input_tokens": 12,
"output_tokens": 19,
"total_tokens": 31,
"cache_creation_input_tokens": null,
"cache_read_input_tokens": null,
"cache_creation": null,
"inference_geo": null,
"server_tool_use": null,
"service_tier": null,
"sunra_usage_semantics": "anthropic.exclusive.v1"
}
}