// AI Platform Drift
Google Gemma 4 26B A4B pricing reduced 25% on OpenRouter
OpenRouter model catalogue · published 2026-09-25 14:33 UTC
WHAT CHANGEDOpenRouter reduced pricing for google/gemma-4-26b-a4b-it by 25%: prompt tokens from $0.00000009 to $0.0000000675 per token, completion tokens from $0.0000003 to $0.000000225 per token.
WHY IT MATTERSIf you route requests through OpenRouter to this model, your per-token costs dropped by a quarter. Existing cost projections and budgets for workloads using this model are now overstated.
WHAT TO DOReforecast spend for any workload calling google/gemma-4-26b-a4b-it through OpenRouter, and update budget holders with the revised numbers.
Model-reported confidence 95% (not measured accuracy)
Primary source ↗
written by anthropic/claude-sonnet-4.5
Show the reasoning — raw diff, triage verdict, confidence
RAW DIFF
id: google/gemma-4-26b-a4b-it name: Google: Gemma 4 26B A4B -pricing.prompt: 0.00000009 -pricing.completion: 0.0000003 +pricing.prompt: 0.0000000675 +pricing.completion: 0.000000225 context_length: 262144 top_provider.max_completion_tokens: 235929
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 | Pricing for an active model decreased materially. Teams budgeting or comparing costs need to know. |
| signals | pricing.prompt decreased 25% (0.00000009 → 0.0000000675) · pricing.completion decreased 25% (0.0000003 → 0.000000225) · price change on active model in catalogue |
| suppression | — |
| triage model | anthropic/claude-haiku-4.5 ($0.00000) |
| writer model | anthropic/claude-sonnet-4.5 ($0.00000) |