BerriAI/litellm · error · ValueError
TogetherAI API key is required, please set 'TOGETHERAI_API_K
Error message
TogetherAI API key is required, please set 'TOGETHERAI_API_KEY' in your environment
What it means
Credential resolution guard for Together AI rerank: no API key came from the call, optional params, litellm globals, or the TOGETHERAI_API_KEY environment variable, so the rerank request cannot be authenticated.
Source
Thrown at litellm/rerank_api/main.py:278
api_base=api_base,
_is_async=_is_async,
headers=headers or litellm.headers or {},
client=client,
model_response=model_response,
litellm_params=rerank_litellm_params,
)
elif _custom_llm_provider == litellm.LlmProviders.TOGETHER_AI:
# Implement Together AI rerank logic
api_key = (
dynamic_api_key
or optional_params.api_key
or litellm.togetherai_api_key
or get_secret("TOGETHERAI_API_KEY")
or litellm.api_key
)
if api_key is None:
raise ValueError("TogetherAI API key is required, please set 'TOGETHERAI_API_KEY' in your environment")
response = together_rerank.rerank(
model=model,
query=query,
documents=documents,
top_n=top_n,
rank_fields=rank_fields,
return_documents=return_documents,
max_chunks_per_doc=max_chunks_per_doc,
api_key=api_key,
_is_async=_is_async,
)
elif _custom_llm_provider == litellm.LlmProviders.JINA_AI:
if dynamic_api_key is None:
raise ValueError("Jina AI API key is required, please set 'JINA_AI_API_KEY' in your environment")
api_base = (
dynamic_api_base or optional_params.api_base or litellm.api_base or get_secret("BEDROCK_API_BASE")View on GitHub (pinned to 77b7c6c40c)
Solutions
- Set TOGETHERAI_API_KEY in your environment.
Defensive patterns
Strategy: validation
When it happens
Trigger: Thrown at litellm/rerank_api/main.py:278 when the library encounters an invalid state.
Common situations: See trigger scenarios.
AI-assisted analysis of BerriAI/litellm@77b7c6c40c (2026-08-18).
Data as JSON: /api/errors/9e3c9dd8d738d192.
Report an issue: GitHub.