Changes to Start

removed the request property model_endpoint_config/anyOf[subschema #1: ModelEndpointConfig]/max_response_chars_per_tool_call

added the new required request property test_model_slug

removed the request property model_slug

removed the request property role

added the new optional request property model_endpoint_config/anyOf[subschema #1: ModelEndpointConfig]/top_k_override

added the new optional request property model_endpoint_config/anyOf[subschema #1: ModelEndpointConfig]/top_p_override

the request property model_endpoint_config/anyOf[subschema #1: ModelEndpointConfig]/max_output_tokens_per_step became optional

the request property model_endpoint_config/anyOf[subschema #1: ModelEndpointConfig]/max_response_chars_per_tool_call became optional

the disable_thinking request property default value false was removed

the max_context_tokens request property default value 262144 was removed

request property model_endpoint_config/anyOf[subschema #1: ModelEndpointConfig]/disable_thinking list-of-types was widened by adding types null to media type application/json

request property model_endpoint_config/anyOf[subschema #1: ModelEndpointConfig]/max_context_tokens list-of-types was widened by adding types null to media type application/json

request property model_endpoint_config/anyOf[subschema #1: ModelEndpointConfig]/max_output_tokens_per_step list-of-types was widened by adding types null to media type application/json

request property model_endpoint_config/anyOf[subschema #1: ModelEndpointConfig]/max_response_chars_per_tool_call list-of-types was widened by adding types null to media type application/json

request property model_endpoint_config/anyOf[subschema #1: ModelEndpointConfig]/max_turns_per_trajectory list-of-types was widened by adding types null to media type application/json

header request parameter Idempotency-Key list-of-types was narrowed by removing types null

for the header request parameter Idempotency-Key, the minLength was increased from 0 to 1

for the header request parameter Idempotency-Key, the maxLength was set to 256

for the header request parameter Idempotency-Key, the type was generalized from no type to string

added the new max enum value to the request property model_endpoint_config/anyOf[subschema #1: ModelEndpointConfig]/reasoning_effort/anyOf[subschema #1]

added the new optional header request parameter Idempotency-Key

added the new optional request property model_endpoint_config/anyOf[subschema #1: ModelEndpointConfig]/max_context_tokens

added the new optional request property model_endpoint_config/anyOf[subschema #1: ModelEndpointConfig]/tokenizer_path

removed the request property expected_concurrency

removed the request property output_speed

removed the request property provider

removed the optional property reused_merge from the response with the 202 status

added the new optional request property agent_id

added the new optional request property model_endpoint_config

added the new optional request property provider