Google · Gemini 2.5 · Small
Gemini 2.5 Flash-Lite pricing and limits
The lowest-cost Gemini 2.5 model, built for throughput. Thinking is off by default, which keeps per-call cost close to visible tokens.
| Line | Tokens | Rate / 1M | Cost |
|---|---|---|---|
| Input, uncached | 1,000 | $0.10 | $0.00010 |
| Input, cache read | 1,500 | $0.025 | $0.00004 |
| Output | 100 | $0.40 | $0.00004 |
- Input / 1M
- $0.10
- Output / 1M
- $0.40
- Cached / 1M
- $0.025
- Cache write / 1M
- n/a
- Blended 3:1
- $0.18
- Context
- 1M
What drives Gemini 2.5 Flash-Lite cost
At this price the bill is driven almost entirely by volume. Classification and routing pipelines can make tens of millions of calls a month, so a small change to prompt length has an outsized effect on the total.
Implicit caching discounts repeated prefixes, and the 1M context window means you can afford to include long reference material when needed. Turning thinking on raises output cost and should be a per-feature decision.
Cost of a typical call
Take a routing call with 2,500 input tokens, 1,500 of them served from cache, and 100 output tokens. At Gemini 2.5 Flash-Lite list prices ($0.10 input, $0.025 cached input, $0.40 output per 1M) one call costs $0.00018, against $0.00029 with no cache hits. At 5,000,000 calls a month that is $888, or $1,450 uncached.
Blended at a 3:1 input to output ratio, Gemini 2.5 Flash-Lite costs $0.18 per 1M tokens. Routing the same call to the fallback in the policy below, Gemini 2.0 Flash, costs $0.00018, which is what a tenant pays you in COGS once they cross the hard cap and PALM SOUQ downgrades instead of blocking.
Cost comparison
Gemini 2.5 Flash-Lite against three alternatives
The same routing call priced on GPT-5 nano, GPT-4.1 nano, Amazon Nova Lite. Move the sliders to match your traffic; models without a cache-read rate bill every input token in full.
Benchmark quality per task before switching. A cheaper model that needs more steps or longer outputs can cost more per finished task than its rate suggests, which is why PALM SOUQ reports cost per feature, not only per token.
Gemini 2.5 Flash-Lite this guide
$0.00018 per call
$888 / mo
baseline
GPT-5 nano
$0.00010 per call
$488 / mo
-45% vs Gemini 2.5 Flash-Lite
GPT-4.1 nano
$0.00018 per call
$888 / mo
+0% vs Gemini 2.5 Flash-Lite
Amazon Nova Lite
$0.00011 per call
$533 / mo
-40% vs Gemini 2.5 Flash-Lite
List prices from the PALM SOUQ LLM Price Index, computed per call as uncached input + cache reads + output. Reasoning tokens count as output on reasoning models.
Rate limits by usage tier
Per-project RPM, TPM and daily request limits by tier. High-volume workloads should plan for quota increases ahead of launches.
Exact limits vary by account tier and change over time, so we do not reprint them here. Check the limits page for your own account in the Google documentation at ai.google.dev/gemini-api/docs. PALM SOUQ enforces your own per-tenant limits in front of the provider's, so a single customer cannot consume the shared allowance that every other tenant depends on.
Circuit-breaker best practices
Use per-tenant request quotas rather than dollar caps alone. At this price a loop costs little per call but can exhaust project quotas and cause 429s for every other tenant.
A token velocity ceiling per tenant protects shared quota from a single noisy customer.
When a breaker trips, the gateway answers in under 50 ms with HTTP 429 and X-PalmSouq-Reason: circuit_breaker_triggered, before the request reaches Google. Your agent framework sees a normal rate-limit response and stops, and the audit log records which heuristic fired and for which tenant.
# palmsouq.policy.yaml
policy: gemini-2-5-flash-lite-free
match:
model: gemini-2.5-flash-lite
tier: free # from X-PalmSouq-Tier
budgets:
monthly_usd: 10 # per tenant
soft_cap_pct: 80 # webhook to your app
on_hard_cap: fallback # or: block (HTTP 429)
fallback:
- gemini-2.0-flash
breakers:
tool_thrashing: { identical_calls: 3, window_steps: 8 }
token_velocity: { max_tokens_per_s: 50000, window_s: 10 }
semantic_echo: { repeats: 3 }
max_steps: 5
cache:
meter_reads: true- budgetsPer-tenant monthly dollar cap with an 80% soft-cap webhook, keyed by X-PalmSouq-Tenant.
- fallbackAt the hard cap, requests reroute to Gemini 2.0 Flash ($0.18 blended per 1M) instead of failing.
- breakersAll four loop heuristics on, evaluated in the request path with under 5 ms added latency.
Where it fits
Routing, intent detection, tagging and lightweight extraction at very high volume. Also a useful final fallback tier.
Provider documentation: ai.google.dev/gemini-api/docs
Gemini 2.5 Flash-Lite pricing questions
How much does Gemini 2.5 Flash-Lite cost per million tokens?
At list price Gemini 2.5 Flash-Lite costs $0.10 per 1M input tokens and $0.40 per 1M output tokens, with cached input at $0.025 per 1M. Prices were last reviewed in the PALM SOUQ LLM Price Index and are for the standard tier and shortest context band.
Does Gemini 2.5 Flash-Lite support prompt caching?
Yes. Cached input is billed at $0.025 per 1M tokens against $0.10 for uncached input. PALM SOUQ records cached tokens per tenant from the provider's usage data, so cache savings show up in each customer's COGS.
What are the Gemini 2.5 Flash-Lite rate limits?
Per-project RPM, TPM and daily request limits by tier. High-volume workloads should plan for quota increases ahead of launches. For your account's exact numbers, see the Google documentation at ai.google.dev/gemini-api/docs.
How do I stop runaway Gemini 2.5 Flash-Lite agent loops?
Use per-tenant request quotas rather than dollar caps alone. At this price a loop costs little per call but can exhaust project quotas and cause 429s for every other tenant. The sample policy on this page enables all four PALM SOUQ heuristics with a max step cap of 5 and falls back to Gemini 2.0 Flash at the hard cap.
Is there a batch discount for Gemini 2.5 Flash-Lite?
50% off through Gemini Batch Mode for asynchronous jobs. Batch traffic suits evaluations, backfills and nightly enrichment jobs that do not need a real-time answer.
Govern Gemini 2.5 Flash-Lite spend per customer.
Point your Google client at gateway.palmsouqltd.com, pass X-PalmSouq-Tenant, and every Gemini 2.5 Flash-Lite token is attributed, capped and protected by circuit breakers.
14-day free production trial · 100k requests included · no card required