- Remove 20 deprecated/unavailable Groq models from registry
- Add groq/meta-llama/llama-guard-4-12b (new safety model)
- Add supports_vision to Llama 4 models (maverick, scout)
- Update Groq documentation with current model list
- Clean up test file references to deprecated models
Fixes#18043
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
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
Add newly released Mistral coding models:
- mistral/codestral-2508: 256K context, $0.30/$0.90 per M tokens
- mistral/devstral-2512: 256K context, $0.40/$2.00 per M tokens
- mistral/labs-devstral-small-2512: 256K context, $0.10/$0.30 per M tokens
* 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
* Add Amazon Nova as a first party provider
* Added new provider folder under llms/ to outline the openai supported params
* Updated supported endpoints on the documnetation
When Gemini image generation models return `text_tokens=0` with `image_tokens > 0`,
the cost calculator was assuming no token breakdown existed and treating all
completion tokens as text tokens, resulting in ~10x underestimation of costs.
Changes:
- Fix cost calculation logic to respect token breakdown when image/audio/reasoning
tokens are present, even if text_tokens=0
- Add `output_cost_per_image_token` pricing for gemini-3-pro-image-preview models
- Add test case reproducing the issue
- Add documentation explaining image token pricing
Fixes#17410
Add support for OpenAI's gpt-5.1-codex-max model, their most intelligent
coding model optimized for long-horizon agentic coding tasks.
- 400k context window, 128k max output tokens
- $1.25/1M input, $10/1M output, $0.125/1M cached input
- Only available via /v1/responses endpoint
- Supports vision, function calling, reasoning, prompt caching
Fixes issue where LiteLLM used the json_tool_call workaround for all Groq
models, even those that support native json_schema (e.g., gpt-oss-120b,
llama-4, kimi-k2). This caused errors when users passed their own tools
alongside structured outputs.
Changes:
- Check `supports_response_schema()` before using the workaround
- Only use json_tool_call workaround for models without native support
- Add clear error message when using workaround with user-provided tools
- Update model config to set `supports_response_schema: false` for models
that don't support native json_schema
- Add unit tests for structured output handling
