* fix(gemini): use JSON instead of form-data for image edit requests
Gemini's image edit API expects JSON body, not multipart/form-data.
The handler was sending form-encoded data which caused 400 errors:
"Invalid JSON payload received. Unexpected token."
Changes:
- Add use_multipart_form_data() method to BaseImageEditConfig (default True)
- Modify image_edit_handler to use json= when use_multipart_form_data() is False
- Override use_multipart_form_data() in GeminiImageEditConfig to return False
* test(gemini): add test for use_multipart_form_data
Claude 3.7 Sonnet's default max_output_tokens is 64000, not 128000.
The 128K output limit requires the beta header 'output-128k-2025-02-19'.
This fixes the integration test failure where requests with max_tokens=128000
were being rejected by the Anthropic API.
Fixes test_multiturn_tool_calls in test_anthropic_responses_api.py
* fix(unified_guardrails.py): send all chunks on completion of final stream
* feat(generic_guardrail_api.py): handle tool call response on streaming LLM responses
* fix(anthropic/chat/guardrail_translation): initial commit adding anthropic tool response streaming guardrails
enables guardrail checks on tool response from llm's to work via `/v1/messages`
* feat(anthropic/): working guardrail checks on tool response from LLMs
ensures guardrail checks on anthropic /v1/messages works as expected
* feat(responses/guardrail_translation): support tool call response guardrails on streaming for /v1/responses
ensures complete coverage of tool call responses
* refactor(openai.py): refactor to use consistent pydantic model for responses api tool response on streaming
enables non-openai model tool call response to work correctly with guardrail checks on /v1/responses
* test: update tests
* fix: fix linting error
* fix: fix failing tests
* fix: fix import errors
* fix(openai/chat/guardrail_transformation): fix final chunk returned on streaming
* fix(anthropic): use dynamic max_tokens based on model
When users don't specify max_tokens in requests to Anthropic models,
LiteLLM now uses the correct max_output_tokens value from the model
pricing JSON instead of a hardcoded 4096.
This fixes truncated responses for Claude 3.5+ models which support
higher output limits (8192 for Claude 3.5, 128k for Claude 3.7, etc.)
Fixes#8835
* fix(anthropic): restore env var support for backwards compatibility
Keep DEFAULT_ANTHROPIC_CHAT_MAX_TOKENS as fallback when model is not
found in JSON, allowing users to configure via environment variable.
Add direct Stability AI REST API support for image generation endpoints.
This enables using Stability's SD3, SD3.5, and Stable Image models via
LiteLLM's OpenAI-compatible interface.
Changes:
- Add STABILITY provider to LlmProviders enum
- Create StabilityImageGenerationConfig with multipart/form-data support
- Add OpenAI size to Stability aspect_ratio mapping
- Register provider in ProviderConfigManager
- Add 9 Stability models to model_prices_and_context_window.json
- Add documentation at docs/providers/stability.md
- Add 25 unit tests
Supported models:
- stability/sd3, sd3-large, sd3-large-turbo, sd3-medium
- stability/sd3.5-large, sd3.5-large-turbo, sd3.5-medium
- stability/stable-image-ultra, stable-image-core
Fixes#15337
Perplexity API returns pre-calculated costs in `usage.cost.total_cost`
that include the `request_cost` (fixed per-request fee). LiteLLM was
ignoring this and calculating costs manually, resulting in ~27x
underreporting (e.g., $0.0002 vs actual $0.006).
Changes:
- Use `usage.cost.total_cost` from Perplexity response when available
- Fall back to manual calculation if cost object not present
- Add tests for both behaviors
Add support for the 'xhigh' reasoning effort level on all gpt-5.2 model
variants, not just gpt-5.2-pro. This enables deeper reasoning capabilities
for the base gpt-5.2 model.
Changes:
- Add is_model_gpt_5_2_model() method to detect gpt-5.2 variants
- Update xhigh validation to allow gpt-5.2 models
- Update documentation with gpt-5.2 reasoning_effort support
- Update tests to reflect new behavior
Moved speechConfig from RequestBody to GenerationConfig TypedDict so that
TTS configuration survives the filtering in _transform_request_body().
This fixes the 400 INVALID_ARGUMENT error when using Gemini TTS models
(gemini-2.5-flash-tts, gemini-2.5-flash-preview-tts, etc.) with both
vertex_ai and gemini providers.
Fixes: speechConfig was being created correctly in map_openai_params()
but then filtered out because GenerationConfig.__annotations__.keys()
didn't include it.
Tested with both preview and non-preview TTS model names and both
vertex_ai and gemini providers.
This fix addresses two issues with Anthropic web search streaming:
1. Fix trailing {} in tool call arguments
- web_search_tool_result blocks have input_json_delta events that were
incorrectly emitted as tool calls
- Added current_content_block_type tracking to only emit tool calls for
tool_use and server_tool_use blocks
2. Capture web_search_tool_result for multi-turn
- The web_search_tool_result content comes ALL AT ONCE in content_block_start
- Now captured in provider_specific_fields.web_search_results
- stream_chunk_builder combines these for final message
- Allows multi-turn conversations to work with streaming web search
Add support for the Bedrock Converse API serviceTier parameter to allow
specifying processing tier (priority, default, or flex).
Changes:
- Add ServiceTierBlock type in litellm/types/llms/bedrock.py
- Add serviceTier to CommonRequestObject
- Add serviceTier to get_config_blocks() in AmazonConverseConfig
- Add comprehensive tests for serviceTier functionality
- Add documentation for serviceTier usage
This allows users to configure service tier via:
- litellm_params in proxy config
- optional_params in SDK calls
* fix(azure_ai): Remove unsupported params from Azure AI Anthropic requests
Azure AI Anthropic endpoint rejects max_retries and stream_options parameters
with "Extra inputs are not permitted" error. These are LiteLLM-internal
parameters that should not be sent to the API.
Fixes 400 Bad Request error when using azure_ai/claude-sonnet-4-5 and other
Azure AI Anthropic models.
* test(azure_ai): Add test for unsupported params removal in Azure AI Anthropic
Verifies that max_retries, stream_options, and extra_body are properly
removed from the request before sending to Azure AI Anthropic endpoint.
- Extract web_search_tool_result blocks in extract_response_content()
- Store web_search_results in provider_specific_fields for round-trip
- Detect srvtoolu_ prefix to reconstruct as server_tool_use (not tool_use)
- Add corresponding web_search_tool_result after server_tool_use blocks
This ensures multi-turn conversations with Anthropic web search + custom
tools work correctly without Anthropic expecting tool_result for server-
side tool executions.
* feat(voyage): add rerank API support
Add support for Voyage AI rerank models (rerank-2.5, rerank-2.5-lite,
rerank-2, rerank-2-lite) to the LiteLLM rerank API.
Changes:
- Add VoyageRerankConfig transformation class
- Register voyage provider in rerank_api/main.py
- Add voyage case in utils.py get_provider_rerank_config
- Add rerank-2.5 and rerank-2.5-lite models to pricing JSON
- Add unit tests for transformation logic
- Update documentation for voyage.md and rerank.md
Usage:
```python
from litellm import rerank
response = rerank(
model="voyage/rerank-2.5",
query="What is the capital of France?",
documents=["Paris is...", "London is..."],
top_n=3,
)
```
* refactor(voyage): simplify rerank transformation code
Remove verbose docstrings to align with other providers (jina_ai pattern).
No functional changes - 168 lines vs 169 for jina_ai.
* fix(voyage): remove incorrect input_cost_per_query from rerank models
Voyage AI charges per token, not per query. The input_cost_per_query
field was incorrectly set to the same value as input_cost_per_token
in the existing rerank-2 and rerank-2-lite models.
Removes input_cost_per_query from all Voyage rerank models:
- voyage/rerank-2
- voyage/rerank-2-lite
- voyage/rerank-2.5
- voyage/rerank-2.5-lite
Pricing source: https://docs.voyageai.com/docs/pricing
The 'user' parameter was being ignored when using responses API models
(e.g., model="openai/responses/gpt-4.1") because the model name check
in get_supported_openai_params() didn't account for the "responses/" prefix.
Fix: Normalize the model name by stripping "responses/" prefix before
checking if the model is in the list of supported OpenAI models.
This is a minimal, non-breaking change that:
- Adds 2 lines of code in gpt_transformation.py
- Only affects the parameter support check, not the model variable itself
- Includes unit and integration tests
* refactor: remove api-key conversion logic for Azure Anthropic
Co-authored-by: Erdem Halil <erdemhalil@users.noreply.github.com>
* fix(passthrough): pass custom_llm_provider to completion_cost for Azure AI Anthropic
The passthrough logging for Anthropic was failing when using Azure AI Anthropic
because the completion_cost function was not receiving the custom_llm_provider
parameter, causing it to fail with "LLM Provider NOT provided" error.
This fix:
- Retrieves custom_llm_provider from logging_obj.model_call_details
- Prepends provider prefix to model name for cost calculation
- Passes both formatted model and custom_llm_provider to completion_cost
- Centralizes provider prefix logic in _create_anthropic_response_logging_payload
This ensures cost calculation works correctly for Azure AI Anthropic requests
with models like azure_ai/claude-sonnet-4-5_gb_20250929.
Co-authored-by: Erdem Halil <erdemhalil@users.noreply.github.com>
* test: add unit tests for Azure AI Anthropic fixes
- Add tests for custom_llm_provider cost calculation in passthrough logging
- Add tests for ProviderConfigManager returning AzureAnthropicMessagesConfig
- Update existing tests to reflect removal of api-key to x-api-key conversion
Co-authored-by: Erdem Halil <erdemhalil@users.noreply.github.com>
---------
Co-authored-by: Erdem Halil <erdemhalil@users.noreply.github.com>
Fixes#17473 - Anthropic streaming fails with JSONDecodeError when
network fragmentation causes SSE data to arrive in partial chunks.
Changes:
- Add accumulated_json buffer and chunk_type to ModelResponseIterator
- Add _handle_accumulated_json_chunk() to accumulate partial JSON
- Add _parse_sse_data() to handle both complete and partial chunks
- Modify __next__ and __anext__ to use accumulation logic
- Add unit tests for partial chunk handling
