Generate Conversation Title

curl --request POST \
  --url https://api.example.com/api/conversations/{conversation_id}/generate_title \
  --header 'Content-Type: application/json' \
  --data '
{
  "max_length": 50,
  "llm": {
    "model": "claude-sonnet-4-20250514",
    "api_key": "<string>",
    "base_url": "<string>",
    "api_version": "<string>",
    "aws_access_key_id": "<string>",
    "aws_secret_access_key": "<string>",
    "aws_region_name": "<string>",
    "openrouter_site_url": "https://docs.all-hands.dev/",
    "openrouter_app_name": "OpenHands",
    "num_retries": 5,
    "retry_multiplier": 8,
    "retry_min_wait": 8,
    "retry_max_wait": 64,
    "timeout": 1,
    "max_message_chars": 30000,
    "temperature": 1,
    "top_p": 1,
    "top_k": 1,
    "custom_llm_provider": "<string>",
    "max_input_tokens": 2,
    "max_output_tokens": 2,
    "model_canonical_name": "<string>",
    "extra_headers": {},
    "input_cost_per_token": 1,
    "output_cost_per_token": 1,
    "ollama_base_url": "<string>",
    "stream": false,
    "drop_params": true,
    "modify_params": true,
    "disable_vision": true,
    "disable_stop_word": false,
    "caching_prompt": true,
    "log_completions": false,
    "log_completions_folder": "logs/completions",
    "custom_tokenizer": "<string>",
    "native_tool_calling": true,
    "force_string_serializer": true,
    "reasoning_effort": "high",
    "reasoning_summary": "auto",
    "enable_encrypted_reasoning": true,
    "prompt_cache_retention": "24h",
    "extended_thinking_budget": 200000,
    "seed": 123,
    "safety_settings": [
      {}
    ],
    "usage_id": "default",
    "litellm_extra_body": {},
    "OVERRIDE_ON_SERIALIZE": [
      "api_key",
      "aws_access_key_id",
      "aws_secret_access_key",
      "litellm_extra_body"
    ]
  }
}
'

{
  "title": "<string>"
}

POST

api

conversations

{conversation_id}

generate_title

Generate Conversation Title

curl --request POST \
  --url https://api.example.com/api/conversations/{conversation_id}/generate_title \
  --header 'Content-Type: application/json' \
  --data '
{
  "max_length": 50,
  "llm": {
    "model": "claude-sonnet-4-20250514",
    "api_key": "<string>",
    "base_url": "<string>",
    "api_version": "<string>",
    "aws_access_key_id": "<string>",
    "aws_secret_access_key": "<string>",
    "aws_region_name": "<string>",
    "openrouter_site_url": "https://docs.all-hands.dev/",
    "openrouter_app_name": "OpenHands",
    "num_retries": 5,
    "retry_multiplier": 8,
    "retry_min_wait": 8,
    "retry_max_wait": 64,
    "timeout": 1,
    "max_message_chars": 30000,
    "temperature": 1,
    "top_p": 1,
    "top_k": 1,
    "custom_llm_provider": "<string>",
    "max_input_tokens": 2,
    "max_output_tokens": 2,
    "model_canonical_name": "<string>",
    "extra_headers": {},
    "input_cost_per_token": 1,
    "output_cost_per_token": 1,
    "ollama_base_url": "<string>",
    "stream": false,
    "drop_params": true,
    "modify_params": true,
    "disable_vision": true,
    "disable_stop_word": false,
    "caching_prompt": true,
    "log_completions": false,
    "log_completions_folder": "logs/completions",
    "custom_tokenizer": "<string>",
    "native_tool_calling": true,
    "force_string_serializer": true,
    "reasoning_effort": "high",
    "reasoning_summary": "auto",
    "enable_encrypted_reasoning": true,
    "prompt_cache_retention": "24h",
    "extended_thinking_budget": 200000,
    "seed": 123,
    "safety_settings": [
      {}
    ],
    "usage_id": "default",
    "litellm_extra_body": {},
    "OVERRIDE_ON_SERIALIZE": [
      "api_key",
      "aws_access_key_id",
      "aws_secret_access_key",
      "litellm_extra_body"
    ]
  }
}
'

{
  "title": "<string>"
}

Path Parameters

conversation_id

string<uuid>

required

Body

application/json

Payload to generate a title for a conversation.

max_length

integer

default:50

Maximum length of the generated title

Required range: 1 <= x <= 200

llm

LLM · object

Optional LLM to use for title generation

Show child attributes

llm.model

string

default:claude-sonnet-4-20250514

Model name.

llm.api_key

API key.

llm.base_url

string | null

Custom base URL.

llm.api_version

string | null

API version (e.g., Azure).

llm.aws_access_key_id

llm.aws_secret_access_key

llm.aws_region_name

string | null

llm.openrouter_site_url

string

default:https://docs.all-hands.dev/

llm.openrouter_app_name

string

default:OpenHands

llm.num_retries

integer

default:5

Required range: x >= 0

llm.retry_multiplier

number

default:8

Required range: x >= 0

llm.retry_min_wait

integer

default:8

Required range: x >= 0

llm.retry_max_wait

integer

default:64

Required range: x >= 0

llm.timeout

integer | null

HTTP timeout (s).

Required range: x >= 0

llm.max_message_chars

integer

default:30000

Approx max chars in each event/content sent to the LLM.

Required range: x >= 1

llm.temperature

number | null

Sampling temperature for response generation. Defaults to 0 for most models and provider default for reasoning models.

Required range: x >= 0

llm.top_p

number | null

default:1

Required range: 0 <= x <= 1

llm.top_k

number | null

Required range: x >= 0

llm.custom_llm_provider

string | null

llm.max_input_tokens

integer | null

The maximum number of input tokens. Note that this is currently unused, and the value at runtime is actually the total tokens in OpenAI (e.g. 128,000 tokens for GPT-4).

Required range: x >= 1

llm.max_output_tokens

integer | null

The maximum number of output tokens. This is sent to the LLM.

Required range: x >= 1

llm.model_canonical_name

string | null

Optional canonical model name for feature registry lookups. The OpenHands SDK maintains a model feature registry that maps model names to capabilities (e.g., vision support, prompt caching, responses API support). When using proxied or aliased model identifiers, set this field to the canonical model name (e.g., 'openai/gpt-4o') to ensure correct capability detection. If not provided, the 'model' field will be used for capability lookups.

llm.extra_headers

Extra Headers · object

Optional HTTP headers to forward to LiteLLM requests.

Show child attributes

llm.extra_headers.{key}

string

llm.input_cost_per_token

number | null

The cost per input token. This will available in logs for user.

Required range: x >= 0

llm.output_cost_per_token

number | null

The cost per output token. This will available in logs for user.

Required range: x >= 0

llm.ollama_base_url

string | null

llm.stream

boolean

default:false

Enable streaming responses from the LLM. When enabled, the provided on_token callback in .completions and .responses will be invoked for each chunk of tokens.

llm.drop_params

boolean

default:true

llm.modify_params

boolean

default:true

Modify params allows litellm to do transformations like adding a default message, when a message is empty.

llm.disable_vision

boolean | null

If model is vision capable, this option allows to disable image processing (useful for cost reduction).

llm.disable_stop_word

boolean | null

default:false

Disable using of stop word.

llm.caching_prompt

boolean

default:true

Enable caching of prompts.

llm.log_completions

boolean

default:false

Enable logging of completions.

llm.log_completions_folder

string

default:logs/completions

The folder to log LLM completions to. Required if log_completions is True.

llm.custom_tokenizer

string | null

A custom tokenizer to use for token counting.

llm.native_tool_calling

boolean

default:true

Whether to use native tool calling.

llm.force_string_serializer

boolean | null

Force using string content serializer when sending to LLM API. If None (default), auto-detect based on model. Useful for providers that do not support list content, like HuggingFace and Groq.

llm.reasoning_effort

enum<string> | null

default:high

The effort to put into reasoning. This is a string that can be one of 'low', 'medium', 'high', 'xhigh', or 'none'. Can apply to all reasoning models.

Available options:

low,

medium,

high,

xhigh,

none

llm.reasoning_summary

enum<string> | null

The level of detail for reasoning summaries. This is a string that can be one of 'auto', 'concise', or 'detailed'. Requires verified OpenAI organization. Only sent when explicitly set.

Available options:

auto,

concise,

detailed

llm.enable_encrypted_reasoning

boolean

default:true

If True, ask for ['reasoning.encrypted_content'] in Responses API include.

llm.prompt_cache_retention

string | null

default:24h

Retention policy for prompt cache. Only sent for GPT-5+ models; explicitly stripped for all other models.

llm.extended_thinking_budget

integer | null

default:200000

The budget tokens for extended thinking, supported by Anthropic models.

llm.seed

integer | null

The seed to use for random number generation.

llm.safety_settings

Safety Settings · object[] | null

Safety settings for models that support them (like Mistral AI and Gemini)

Show child attributes

llm.safety_settings.{key}

string

llm.usage_id

string

default:default

Unique usage identifier for the LLM. Used for registry lookups, telemetry, and spend tracking.

llm.litellm_extra_body

Litellm Extra Body · object

Additional key-value pairs to pass to litellm's extra_body parameter. This is useful for custom inference endpoints that need additional parameters for configuration, routing, or advanced features. NOTE: Not all LLM providers support extra_body parameters. Some providers (e.g., OpenAI) may reject requests with unrecognized options. This is commonly supported by: - LiteLLM proxy servers (routing metadata, tracing) - vLLM endpoints (return_token_ids, etc.) - Custom inference clusters Examples: - Proxy routing: {'trace_version': '1.0.0', 'tags': ['agent:my-agent']} - vLLM features: {'return_token_ids': True}

llm.OVERRIDE_ON_SERIALIZE

string[]

Response

Successful Response

Response containing the generated conversation title.

title

string

required

The generated title for the conversation

Set Conversation Security Analyzer Ask Agent

⌘I

Guides

Architecture

API Reference

Generate Conversation Title

Path Parameters

Body

Response