gemini-3.1-pro vs gemini-3.8-flash
Fourteen priced metrics for the same 2,000-in / 300-out call, with and without provider caching, and what TokenZero's cascade would do with the pair.
At list prices as of 2026-10-26, gemini-3.8-flash costs $1.14 per million blended tokens on a 2,000-in / 300-out call against $3.30 for gemini-3.1-pro, 65.5% less. With the static prefix cached both drop further: $4.90 versus $1.61 per thousand calls. TokenZero routes only prompts its classifier scores simple and holds a 99.8% parity floor.
· Source: provider list prices verified in pricing table 2026-10-26; costs computed by the same code that signs TokenZero receipts
At a glance
- Cheaper per blended token
- gemini-3.8-flash by 65.5% (computed)
- gemini-3.1-pro blended $/1M
- $3.30 (computed)
- gemini-3.8-flash blended $/1M
- $1.14 (computed)
- Input $/1M
- $2.00 vs $0.75
- Output $/1M
- $12.00 vs $3.75
- Cached input $/1M
- $0.200 vs $0.075
- Cache discount
- 90% vs 90% (computed)
- Monthly at 100k calls
- $760 vs $263 (computed)
- Saved per 1M calls
- $4,975 (computed)
- Providers
- gemini vs gemini
- Lifecycle
- active, no retirement announced vs active, no retirement announced
- Parity floor for routing
- 99.8% (shadow-eval breaker)
gemini-3.1-pro vs gemini-3.8-flash: list prices and the same workload on both (USD, table 2026-10-26)
| Metric | gemini-3.1-pro | gemini-3.8-flash | Delta |
|---|---|---|---|
| Provider · tier | gemini · frontier | gemini · fast | same provider |
| Input $/1M | $2.00 | $0.75 | 62.5% gap |
| Output $/1M | $12.00 | $3.75 | 68.8% gap |
| Cached input $/1M | $0.200 | $0.075 | 90% / 90% off input |
| Cache write $/1M | no surcharge | no surcharge | |
| Minimum cacheable prefix | 1024 tokens | 1024 tokens | |
| Effective blended $/1M (2,000 in / 300 out) | $3.30 | $1.14 | gemini-3.8-flash 65.5% less |
| Per call | $0.00760 | $0.00262 | $0.00498 |
| Per month at 100k calls | $760 | $263 | $498 |
| …with the 1,500-token prefix cached | $490 | $161 | $329 |
| Long-context threshold | 200,000 tokens ($4.00 in / $18.00 out above) | single tier | |
| Processing tiers | standard only | standard only | |
| Lifecycle | active, no retirement announced | active, no retirement announced | |
| Cheaper sibling (cascade target) | gemini-3.8-flash | gemini-3.5-flash-lite | |
| TokenZero cascade recommendation | gemini-3.1-pro → gemini-3.8-flash | $4,975 saved per 1M calls if every call moved; $1,990 at a 40% simple-prompt share | 99.8% parity floor, breaker on |
Use either model through TokenZero
GOOGLE_GEMINI_BASE_URL=https://tokenzero.sh
# keep your own keys; cache formatting on, routing advisory, signed receipt per callFree up to $500/month of routed spend; paid plans take 15% of verified savings with a 3x-ROI-or-$0 rule.
What is not on this page
Third-party quality scores (coding ELO, extraction accuracy, reasoning benchmarks) and per-model latency are not shown because TokenZero does not measure them; the numbers above are prices and the arithmetic on them. The latency benchmark shows what the gateway does measure.
Questions people ask
Which is cheaper, gemini-3.1-pro or gemini-3.8-flash?
gemini-3.8-flash. At list prices as of 2026-10-26 it costs $1.14 per million blended tokens versus $3.30 for gemini-3.1-pro, a 65.5% gap on a 2,000-input / 300-output call. Per month at 100,000 calls that is $263 versus $760.
How much does prompt caching change the gemini-3.1-pro vs gemini-3.8-flash gap?
Cached input costs $0.200 on gemini-3.1-pro and $0.075 on gemini-3.8-flash per million. With a 1,500-token static prefix cached, 100,000 calls cost $490 and $161 respectively; TokenZero's formatter places the breakpoints and sets prompt_cache_key automatically.
Can TokenZero route gemini-3.1-pro traffic to gemini-3.8-flash safely?
Yes, within gemini: with X-TokenZero-Cascade: auto the classifier scores each prompt and only simple ones move; shadow evaluation re-runs a sample on gemini-3.1-pro and a pair below 99.8% parity is auto-disabled. Moving every call would save $4,975 per million calls; at a 40% simple share it is $1,990.
Is gemini-3.1-pro or gemini-3.8-flash being retired?
gemini-3.1-pro: active, no retirement announced. gemini-3.8-flash: active, no retirement announced. TokenZero audits flag retired ids and the gateway warns in X-TokenZero-Warning with the provider's replacement.
Related
Price your own workload on gemini-3.1-pro and gemini-3.8-flash