claude-haiku-5-5 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, claude-haiku-5-5 costs $0.15 per million blended tokens on a 2,000-in / 300-out call against $1.14 for gemini-3.8-flash, 86.7% less. With the static prefix cached both drop further: $0.22 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
- claude-haiku-5-5 by 86.7% (computed)
- claude-haiku-5-5 blended $/1M
- $0.15 (computed)
- gemini-3.8-flash blended $/1M
- $1.14 (computed)
- Input $/1M
- $0.10 vs $0.75
- Output $/1M
- $0.50 vs $3.75
- Cached input $/1M
- $0.010 vs $0.075
- Cache discount
- 90% vs 90% (computed)
- Monthly at 100k calls
- $35 vs $263 (computed)
- Saved per 1M calls
- $2,275 (computed)
- Providers
- anthropic vs gemini
- Lifecycle
- active, no retirement announced vs active, no retirement announced
- Parity floor for routing
- 99.8% (shadow-eval breaker)
claude-haiku-5-5 vs gemini-3.8-flash: list prices and the same workload on both (USD, table 2026-10-26)
| Metric | claude-haiku-5-5 | gemini-3.8-flash | Delta |
|---|---|---|---|
| Provider · tier | anthropic · fast | gemini · fast | different providers |
| Input $/1M | $0.10 | $0.75 | 86.7% gap |
| Output $/1M | $0.50 | $3.75 | 86.7% gap |
| Cached input $/1M | $0.010 | $0.075 | 90% / 90% off input |
| Cache write $/1M | $0.125 | no surcharge | |
| Minimum cacheable prefix | 512 tokens | 1024 tokens | |
| Effective blended $/1M (2,000 in / 300 out) | $0.15 | $1.14 | claude-haiku-5-5 86.7% less |
| Per call | $0.00035 | $0.00262 | $0.00227 |
| Per month at 100k calls | $35 | $263 | $228 |
| …with the 1,500-token prefix cached | $22 | $161 | $140 |
| Long-context threshold | 100,000 tokens ($0.50 in / $2.50 out above) | single tier | |
| Processing tiers | speed: fast 2x | standard only | |
| Lifecycle | active, no retirement announced | active, no retirement announced | |
| Cheaper sibling (cascade target) | — | gemini-3.5-flash-lite | |
| TokenZero cascade recommendation | none (cascade stays within one provider; cross-provider moves only on failover) | $2,275 saved per 1M calls if every call moved; $910 at a 40% simple-prompt share | 99.8% parity floor, breaker on |
Use either model through TokenZero
ANTHROPIC_BASE_URL=https://tokenzero.sh
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, claude-haiku-5-5 or gemini-3.8-flash?
claude-haiku-5-5. At list prices as of 2026-10-26 it costs $0.15 per million blended tokens versus $1.14 for gemini-3.8-flash, a 86.7% gap on a 2,000-input / 300-output call. Per month at 100,000 calls that is $35 versus $263.
How much does prompt caching change the claude-haiku-5-5 vs gemini-3.8-flash gap?
Cached input costs $0.010 on claude-haiku-5-5 and $0.075 on gemini-3.8-flash per million. With a 1,500-token static prefix cached, 100,000 calls cost $22 and $161 respectively; TokenZero's formatter places the breakpoints and sets prompt_cache_key automatically.
Can TokenZero route gemini-3.8-flash traffic to claude-haiku-5-5 safely?
Not automatically: cascade routing stays inside one provider so the request shape, tools and keys are unchanged. Cross-provider moves happen only on failover when you name the fallback model and key. Use the calculator to price a manual migration of the workload.
Is claude-haiku-5-5 or gemini-3.8-flash being retired?
claude-haiku-5-5: 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 claude-haiku-5-5 and gemini-3.8-flash