---
title: "Patch Model"
method: PATCH
path: "/model/{model_id}/update"
tags: ["model management"]
---

# Patch Model

`PATCH /model/{model_id}/update`

PATCH Endpoint for partial model updates.

Only updates the fields specified in the request while preserving other existing values.
Follows proper PATCH semantics by only modifying provided fields.

Args:
    model_id: The ID of the model to update
    patch_data: The fields to update and their new values
    user_api_key_dict: User authentication information

Returns:
    Updated model information

Raises:
    ProxyException: For various error conditions including authentication and database errors

## Path parameters

- `model_id` string, required

## Request body

- UpdateDeployment
  - `model_name` string, nullable
  - `litellm_params` UpdateLiteLLMParams
    - `input_cost_per_token` number, nullable
    - `output_cost_per_token` number, nullable
    - `input_cost_per_character` number, nullable
    - `output_cost_per_character` number, nullable
    - `cache_read_input_token_cost` number, nullable
    - `cache_creation_input_token_cost` number, nullable
    - `tiered_pricing` object[], nullable
    - `input_cost_per_second` number, nullable
    - `output_cost_per_second` number, nullable
    - `output_cost_per_second_1080p` number, nullable
    - `output_cost_per_second_480p` number, nullable
    - `output_cost_per_second_4k` number, nullable
    - `input_cost_per_pixel` number, nullable
    - `output_cost_per_pixel` number, nullable
    - `input_cost_per_token_flex` number, nullable
    - `input_cost_per_token_priority` number, nullable
    - `input_cost_per_token_ultrafast` number, nullable
    - `cache_creation_input_token_cost_above_1hr` number, nullable
    - `cache_creation_input_token_cost_above_200k_tokens` number, nullable
    - `cache_creation_input_token_cost_above_272k_tokens` number, nullable
    - `cache_creation_input_token_cost_above_272k_tokens_priority` number, nullable
    - `cache_creation_input_token_cost_above_272k_tokens_flex` number, nullable
    - `cache_creation_input_token_cost_flex` number, nullable
    - `cache_creation_input_token_cost_priority` number, nullable
    - `cache_creation_input_token_cost_ultrafast` number, nullable
    - `cache_creation_input_audio_token_cost` number, nullable
    - `cache_read_input_token_cost_flex` number, nullable
    - `cache_read_input_token_cost_priority` number, nullable
    - `cache_read_input_token_cost_ultrafast` number, nullable
    - `cache_read_input_token_cost_above_200k_tokens` number, nullable
    - `cache_read_input_token_cost_above_200k_tokens_priority` number, nullable
    - `cache_read_input_token_cost_above_272k_tokens_priority` number, nullable
    - `cache_read_input_token_cost_above_272k_tokens_flex` number, nullable
    - `cache_read_input_audio_token_cost` number, nullable
    - `input_cost_per_character_above_128k_tokens` number, nullable
    - `input_cost_per_audio_token` number, nullable
    - `input_cost_per_token_cache_hit` number, nullable
    - `input_cost_per_token_above_128k_tokens` number, nullable
    - `input_cost_per_token_above_200k_tokens` number, nullable
    - `input_cost_per_token_above_200k_tokens_priority` number, nullable
    - `input_cost_per_token_above_272k_tokens_priority` number, nullable
    - `input_cost_per_token_above_272k_tokens_flex` number, nullable
    - `input_cost_per_query` number, nullable
    - `input_cost_per_image` number, nullable
    - `input_cost_per_image_above_128k_tokens` number, nullable
    - `input_cost_per_audio_per_second` number, nullable
    - `input_cost_per_audio_per_second_above_128k_tokens` number, nullable
    - `input_cost_per_video_per_second` number, nullable
    - `input_cost_per_video_per_second_above_128k_tokens` number, nullable
    - `input_cost_per_video_per_second_above_15s_interval` number, nullable
    - `input_cost_per_video_per_second_above_8s_interval` number, nullable
    - `input_cost_per_token_batches` number, nullable
    - `output_cost_per_token_batches` number, nullable
    - `output_cost_per_token_flex` number, nullable
    - `output_cost_per_token_priority` number, nullable
    - `output_cost_per_token_ultrafast` number, nullable
    - `output_cost_per_audio_token` number, nullable
    - `output_cost_per_token_above_128k_tokens` number, nullable
    - `output_cost_per_token_above_200k_tokens` number, nullable
    - `output_cost_per_token_above_200k_tokens_priority` number, nullable
    - `output_cost_per_token_above_272k_tokens_priority` number, nullable
    - `output_cost_per_token_above_272k_tokens_flex` number, nullable
    - `output_cost_per_character_above_128k_tokens` number, nullable
    - `output_cost_per_image` number, nullable
    - `output_cost_per_image_token` number, nullable
    - `output_cost_per_video_token` number, nullable
    - `output_cost_per_reasoning_token` number, nullable
    - `output_cost_per_reasoning_token_flex` number, nullable
    - `output_cost_per_reasoning_token_priority` number, nullable
    - `output_cost_per_video_per_second` number, nullable
    - `output_cost_per_audio_per_second` number, nullable
    - `search_context_cost_per_query` object, nullable
    - `google_maps_grounding_cost_per_query` number, nullable
    - `citation_cost_per_token` number, nullable
    - `cache_read_input_token_cost_above_272k_tokens` number, nullable
    - `cache_read_input_token_cost_above_512k_tokens` number, nullable
    - `input_cost_per_image_token` number, nullable
    - `input_cost_per_video_token` number, nullable
    - `input_cost_per_token_above_272k_tokens` number, nullable
    - `input_cost_per_token_above_512k_tokens` number, nullable
    - `output_cost_per_token_above_272k_tokens` number, nullable
    - `output_cost_per_token_above_512k_tokens` number, nullable
    - `output_vector_size` integer, nullable
    - `ocr_cost_per_page` number, nullable
    - `ocr_cost_per_credit` number, nullable
    - `annotation_cost_per_page` number, nullable
    - `regional_processing_uplift_multiplier_eu` number, nullable
    - `regional_processing_uplift_multiplier_us` number, nullable
    - `regional_endpoint_uplift_multiplier` number, nullable
    - `api_key` string, nullable
    - `api_base` string, nullable
    - `api_version` string, nullable
    - `azure_ad_token` string, nullable
    - `vertex_project` string, nullable
    - `vertex_location` string, nullable
    - `vertex_credentials` union
      - string
      - object
    - `region_name` string, nullable
    - `gcs_bucket_name` string, nullable
    - `aws_access_key_id` string, nullable
    - `aws_secret_access_key` string, nullable
    - `aws_session_token` string, nullable
    - `aws_region_name` string, nullable
    - `aws_session_name` string, nullable
    - `aws_profile_name` string, nullable
    - `aws_role_name` string, nullable
    - `aws_web_identity_token` string, nullable
    - `aws_sts_endpoint` string, nullable
    - `aws_external_id` string, nullable
    - `aws_bedrock_runtime_endpoint` string, nullable
    - `aws_bedrock_project_id` string, nullable
    - `s3_bucket_name` string, nullable
    - `s3_region_name` string, nullable
    - `s3_encryption_key_id` string, nullable
    - `aws_batch_role_arn` string, nullable
    - `s3_output_bucket_name` string, nullable
    - `bedrock_tags` unknown[], nullable
      - unknown
    - `watsonx_region_name` string, nullable
    - `custom_llm_provider` string, nullable
    - `rust` boolean, nullable
    - `tpm` integer, nullable
    - `rpm` integer, nullable
    - `itpm` integer, nullable
    - `otpm` integer, nullable
    - `timeout` union
      - number
      - string
    - `stream_timeout` union
      - number
      - string
    - `max_retries` integer, nullable
    - `organization` string, nullable
    - `configurable_clientside_auth_params` union[], nullable
      - union
        - string
        - ConfigurableClientsideParamsCustomAuthInput
          - `api_base` string, required
    - `litellm_credential_name` string, nullable
    - `litellm_trace_id` string, nullable
    - `max_file_size_mb` number, nullable
    - `default_api_key_tpm_limit` integer, nullable
    - `default_api_key_rpm_limit` integer, nullable
    - `max_budget` number, nullable
    - `budget_duration` string, nullable
    - `keepalive_seconds` number, nullable
    - `allow_client_keepalive_override` boolean, nullable
    - `use_in_pass_through` boolean, nullable
    - `use_litellm_proxy` boolean, nullable
    - `use_chat_completions_api` boolean, nullable
    - `use_xai_oauth` boolean, nullable — Use stored xAI OAuth credentials when no xAI API key is configured.
    - `merge_reasoning_content_in_choices` boolean, nullable
    - `model_info` object, nullable
    - `mock_response` union
      - string
      - ModelResponse
        - `id` string, required
        - `created` integer, required
        - `model` string, nullable
        - `object` string, required
        - `system_fingerprint` string, nullable
        - `choices` Choices[], required
          - `finish_reason` 'stop' | 'content_filter' | 'function_call' | 'tool_calls' | 'length' | 'guardrail_intervened' | 'eos' | 'finish_reason_unspecified' | 'malformed_function_call', required
          - `index` integer, required
          - `message` Message, required
            - `content` string, nullable, required
            - `role` 'assistant' | 'user' | 'system' | 'tool' | 'function', required
            - `tool_calls` union[], nullable, required
              - …
            - `function_call` FunctionCall, required
              - …
            - `audio` ChatCompletionAudioResponse
              - …
            - `images` ImageURLListItem[], nullable
              - …
            - `reasoning_content` string, nullable
            - `thinking_blocks` union[], nullable
              - …
            - `reasoning_items` ChatCompletionReasoningItem[], nullable
              - …
            - `provider_specific_fields` object, nullable
            - `annotations` ChatCompletionAnnotation[], nullable
              - …
          - `logprobs` union
            - ChoiceLogprobs
              - …
            - unknown
          - `provider_specific_fields` object, nullable
      - unknown
    - `tags` string[], nullable
    - `tag_regex` string[], nullable
    - `auto_router_config_path` string, nullable
    - `auto_router_config` string, nullable
    - `auto_router_default_model` string, nullable
    - `auto_router_embedding_model` string, nullable
    - `auto_router_max_input_chars` integer, nullable
    - `auto_router_routing_compression` string, nullable
    - `auto_router_model_compression` string, nullable
    - `complexity_router_config` object, nullable
    - `complexity_router_default_model` string, nullable
    - `adaptive_router_default_model` string, nullable
    - `adaptive_router_config` object, nullable
    - `quality_router_config` object, nullable
    - `quality_router_default_model` string, nullable
    - `vector_store_id` string, nullable
    - `milvus_text_field` string, nullable
    - `milvus_db_name` string, nullable
    - `milvus_partition_names` string[], nullable
    - `valkey_host` string, nullable
    - `valkey_port` integer, nullable
    - `valkey_password` string, nullable
    - `valkey_ssl` boolean, nullable
    - `valkey_text_field` string, nullable
    - `valkey_embedding_field` string, nullable
    - `model` string, nullable
  - `model_info` ModelInfo
    - `input_cost_per_token` number, nullable
    - `output_cost_per_token` number, nullable
    - `input_cost_per_character` number, nullable
    - `output_cost_per_character` number, nullable
    - `cache_read_input_token_cost` number, nullable
    - `cache_creation_input_token_cost` number, nullable
    - `tiered_pricing` object[], nullable
    - `id` string, nullable, required
    - `db_model` boolean
    - `updated_at` string, date-time, nullable
    - `updated_by` string, nullable
    - `created_at` string, date-time, nullable
    - `created_by` string, nullable
    - `base_model` string, nullable
    - `tier` 'free' | 'paid', nullable
    - `team_id` string, nullable
    - `team_public_model_name` string, nullable
    - `blocked` boolean, nullable
    - `ptu_count` integer, nullable
    - `cost_per_ptu_per_hour` number, nullable
    - `ptu_effective_from` string, date-time, nullable
    - `ptu_effective_to` string, date-time, nullable
    - `allow_fail_open` boolean, nullable
    - `enable_tag_filtering` boolean, nullable
    - `internal_router_model` boolean, nullable
  - `blocked` boolean, nullable

## Response `200`

Successful Response

- unknown

## Other responses

- `422` — Validation Error

## Changes

- **2026-09-18** `082b5fabd909` — 1 breaking, 89 info
  - the `litellm_params/anyOf[subschema #1: updateLiteLLMParams]/mock_response/anyOf[subschema #2: ModelResponse]/choices/items/message/tool_calls/anyOf[subschema #1]/items/` request property type changed from `object` to no type
  - added the new optional request property `blocked`
  - added the new optional request property `litellm_params/anyOf[subschema #1: updateLiteLLMParams]/allow_client_keepalive_override`
  - added the new optional request property `litellm_params/anyOf[subschema #1: updateLiteLLMParams]/annotation_cost_per_page`
  - …86 more

[Change history](https://skmtc.dev/flock/apis/litellm-api/changes/model/:model_id/update/patch.md)

---

[API](https://skmtc.dev/flock/apis/litellm-api.md) · [All operations](https://skmtc.dev/flock/apis/litellm-api/llms.txt) · [OpenAPI document](https://skmtc.dev/flock/apis/litellm-api/revisions/3b2b241e4b0b?raw)