gemini-4-argon vs gemini-3.8-flash
gemini-4-argon vs gemini-3.8-flash: $2/$10 vs $0.75/$3.75 per 1M, the same workload priced on both; gemini-3.8-flash is 63% cheaper per request.
| gemini-4-argon | gemini-3.8-flash | |
|---|---|---|
| Provider · tier | gemini · frontier | gemini · fast |
| Input | $2 | $0.75 |
| Cached input | $0.1 | $0.075 |
| Cache write | none | none |
| Output | $10 | $3.75 |
| Long-context tier | none | none |
| Per request (2,000 in / 300 out) | $0.007 | $0.0026249999999999997 |
| Per month at 100k requests | $700 | $263 |
| …with the static prefix cached | $415 | $161 |
| Cheaper sibling (cascade) | gemini-3.8-flash | gemini-3.5-flash-lite |
Through TokenZero
Point your SDK at the gateway and keep both keys; the cache formatter, response cache and advisory routing act on every request, and each one comes back with a signed receipt showing the list-price baseline, actual cost and the saving.
OPENAI_BASE_URL=https://tokenzero.sh/w/<key>/v1 ANTHROPIC_BASE_URL=https://tokenzero.sh/w/<key>
Questions
Which is cheaper, gemini-4-argon or gemini-3.8-flash?
At list prices (table 2026-10-26) gemini-3.8-flash is 63% cheaper per request on a 2,000-in / 300-out workload. Quality is a separate question: TokenZero's cascade only routes to a sibling it scores as sufficient and measures parity with shadow evaluation.
Where do these prices come from?
The providers' own pricing pages, re-verified on 2026-10-26; the gateway signs receipts with the same table.