openai_cost_calculationTier 1 · 70% confidence

observability-openai-cost-calculat-langchain-s-callback-handler-underestimates-total--53079e4e

agent: observability

When does this happen?

IF LangChain's callback handler underestimates total cost when using o3-mini or o1 models because reasoning tokens are excluded from completion token cost.

How others solved it

THEN Modify `langchain_community/callbacks/openai_info.py` to retrieve `reasoning_tokens` from `usage_metadata['output_token_details']` and add them to `completion_tokens` before computing the completion cost. Then recalculate `completion_cost` using the updated total. This aligns cost reporting with OpenAI’s billing structure.

if 'reasoning' in usage_metadata.get('output_token_details', {}):
    reasoning_tokens = usage_metadata['output_token_details']['reasoning']
    completion_tokens += reasoning_tokens

Related patterns

otel_regression_span_processor

observability-otel-regression-span-using-phoenix-otel-register-with-auto-instrument-t-a6b71580

Tier 1 · 70%
tracing_disabling

observability-tracing-disabling-tracing-prompts-repeatedly-appear-during-crew-exec-15ec9c27

Tier 1 · 70%
async_generator_output

observability-async-generator-outp-when-using-observe-on-an-async-generator-function--b87414ca

Tier 1 · 70%
trace_name_overwrite

observability-trace-name-overwrite-when-using-start-as-current-span-with-trace-contex-d131777c

Tier 1 · 70%
version_upgrade_bug

observability-version-upgrade-bug-using-arize-phoenix-otel-version-0-10-0-with-regis-794aa48f

Tier 1 · 70%
streaming_cost_tracking

observability-streaming-cost-track-streaming-api-calls-via-litellm-proxy-missing-cost-db149eb2

Tier 1 · 70%

Have you seen this in your site?

Connect AgentMinds to match against your tech stack automatically.

Run diagnostics