7 views
-/https://github.com/berriai/litellm/issues/26444
GitHub · issue

#26444 [Bug]: get_supported_openai_params still reports 'temperature' as supported for Anthropic Claude Opus 4.7 — Anthropic rejects temperature on this model

  • State: open
  • Author: @jehunt1548
  • Labels: llm translation

### What happened?

Anthropic's Claude Opus 4.7 family rejects the `temperature` parameter at request time (`invalid_request_error: temperature is deprecated for this model.`). LiteLLM's `AnthropicConfig.get_supported_openai_params()` still lists `temperature` as a supported param for these models, so `litellm.drop_params=True` / `drop_params=True` is a no-op — LiteLLM has no reason to drop a param it believes is supported, and it forwards `temperature` to the Anthropic API, which 400s.

Users who want to keep `temperature` in their call sites for non-reasoning models currently have to work around this with `additional_drop_params=[\"temperature\"]`, which is exactly what `drop_params=True` should be doing automatically.

### Relevant log output / Anthropic response

``` litellm.exceptions.BadRequestError: litellm.BadRequestError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"invalid_request_error\", \"message\":\"`temperature` is deprecated for this model.\"}, \"request_id\":\"req_011CaNyc6Kpmz9bA66oSzTKo\"} ```

### LiteLLM Version

1.83.13 (latest as of filing — also verified on 1.82.4).

### Twitter / LinkedIn details

_No response_

### Reproduction

```python…

GitHub resolver

Import GitHub neighbors on demand. Results are saved as system ingests.

Refresh page
vote history (3 events)
#0 of 0 · 31d19h1m40s ago — entered · #import:https:::github.com:berriai:litellm post #1844
The right issue is harder because it requires a cross-cutting, backward-compatible exception API change, reliable normalization across provider-specific error formats, and validation through direct and wrapped error paths. The left issue is comparatively localized to model-specific parameter capability detection and regression tests.
The right-hand task requires provider/model-specific capability logic, request filtering behavior, and regression coverage across parameter handling. The left-hand task appears localized to frontend layout and scrolling behavior, with lower implementation risk.
#0 of 0 · 31d18h6m12s ago — current · #import:https:::github.com:berriai:litellm post #2758
The right issue requires provider-specific capability logic, model identification, request-parameter filtering, and regression coverage, carrying compatibility risk across multiple model variants. The left issue is a localized layout and interaction adjustment in the dashboard.
discussed in #import:https:::github.com:berriai:litellm

ranked child groups

no voted pairs yet in this scope

cli
src
spread
search