// AI Platform Drift
Claude Sonnet 5.5 batch variant added at $1/1M prompt tokens
OpenRouter model catalogue · published 2026-09-28 23:01 UTC
WHAT CHANGEDOpenRouter added anthropic/claude-sonnet-5.5:batch with pricing of $0.000001 per prompt token ($1 per 1M tokens) and $0.000005 per completion token ($5 per 1M tokens). Context window is 1M tokens, max completion is 128k tokens.
WHY IT MATTERSBatch processing typically offers lower latency requirements and cost savings over synchronous calls. If you are running high-volume Claude Sonnet 5.5 workloads that can tolerate asynchronous processing, this variant may reduce your API costs.
WHAT TO DOCheck your current Claude Sonnet 5.5 usage volume and latency requirements. If you process requests that can wait for batch completion, test the :batch endpoint to measure actual cost savings against your workload.
Model-reported confidence 85% (not measured accuracy)
Primary source ↗
written by anthropic/claude-sonnet-4.5
Show the reasoning — raw diff, triage verdict, confidence
RAW DIFF
+id: anthropic/claude-sonnet-5.5:batch +name: Anthropic: Claude Sonnet 5.5 (batch) +pricing.prompt: 0.000001 +pricing.completion: 0.000005 +context_length: 1000000 +top_provider.max_completion_tokens: 128000
HOW IT WAS JUDGED
Triage signals below are model-reported assertions, preserved verbatim; they are not independent arithmetic verification.
| triage verdict | MATERIAL at 0.95, needed 0.5 |
|---|---|
| triage reasoning | New model entry with pricing and limits affects platform availability and cost planning for engineers. |
| signals | new model added to catalogue · pricing introduced (prompt and completion rates) · context window specified (1M tokens) · completion token limit specified (128k) · batch variant of existing model |
| suppression | — |
| triage model | anthropic/claude-haiku-4.5 ($0.00000) |
| writer model | anthropic/claude-sonnet-4.5 ($0.00000) |