Retrieve Message Batch results changedapi/beta/messages/batches/results
Nearest release: v2.1.247, published under an hour before this site recorded the change. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.
Recorded here
Lines+19added
Lines−3removed
From line
22
where the diff opens
First seen
14 Aug 2026
this site's first read of the page
Recorded edits26to this page, all time
The whole hunk
from line 22, old and new numbered
/
from line 22
2222
2323 - `string`
2424
25 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 31 more`
25 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 38 more`
2626
2727 - `"message-batches-2024-09-24"`
2828
from line 92
9292
9393 - `"mid-conversation-tool-changes-2026-07-01"`
9494
95 - `"compact-2026-01-12"`
96
97 - `"computer-use-2025-11-24"`
98
99 - `"mcp-tunnels-2026-06-22"`
100
101 - `"structured-outputs-2025-11-13"`
102
103 - `"task-budgets-2026-03-13"`
104
105 - `"thinking-display-updates-2026-08-18"`
106
107 - `"ce-user-management-2026-07-13"`
108
95109## Returns
96110
97111- `BetaMessageBatchIndividualResponse object`
from line 1541
15271541
15281542 Per-iteration token usage breakdown.
15291543
1530 Each entry represents one sampling iteration, with its own input/output token counts and cache statistics. This allows you to:
1544 Each entry represents one sampling iteration, with its own input/output token counts and cache statistics, discriminated by `type`. For `message` entries (model sampling iterations, such as the turns of a server-side tool use loop), this allows you to:
15311545
15321546 - Determine which iterations exceeded long context thresholds (>=200k tokens)
1533 - Calculate the true context window size from the last iteration
1547 - Calculate the context window size from the last `message` entry
15341548 - Understand token accumulation across server-side tool use loops
1549
1550 A `compaction` entry reports the token usage of the compaction operation itself — the server-side request that summarizes the context being closed — NOT the size of the context that was compacted away, and its token counts can be much smaller than that closed context (for example, a compaction that closes a ~200k-token context can report only a few thousand tokens). Do not derive the context window size from a `compaction` entry, even when it is the last entry. A `compaction` entry's tokens are not included in the top-level `usage` fields. When an input-token trigger is in effect (the default — 150,000 tokens unless configured otherwise), each `compaction` entry closes a context that had reached at least that threshold, though the context can exceed it by the final iteration's output and tool results.
15351551
15361552 - `BetaMessageIterationUsage object`
15371553
No line in this hunk matches that.