Google · Gemini 2.5 · Mid
Gemini 2.5 Flash pricing and limits
Google's price-performance thinking model with a 1M context window and a configurable thinking budget. One of the cheapest ways to run long-context work.
| Line | Tokens | Rate / 1M | Cost |
|---|---|---|---|
| Input, uncached | 8,000 | $0.30 | $0.00240 |
| Input, cache read | 12,000 | $0.075 | $0.00090 |
| Output | 800 | $2.50 | $0.00200 |
- Input / 1M
- $0.30
- Output / 1M
- $2.50
- Cached / 1M
- $0.075
- Cache write / 1M
- n/a
- Blended 3:1
- $0.85
- Context
- 1M
What drives Gemini 2.5 Flash cost
Thinking tokens are billed as output, and Flash lets you set a thinking budget per request, including zero. Leaving the default on for simple tasks is the most common source of avoidable spend.
Implicit caching discounts repeated prefixes automatically. Because input is cheap and the context is large, the risk shifts to prompt growth: an agent that never trims history keeps paying for an ever longer prompt.
Cost of a typical call
Take a RAG answer with 20,000 input tokens, 12,000 of them served from cache, and 800 output tokens. At Gemini 2.5 Flash list prices ($0.30 input, $0.075 cached input, $2.50 output per 1M) one call costs $0.00530, against $0.00800 with no cache hits. At 400,000 calls a month that is $2,120, or $3,200 uncached.
Blended at a 3:1 input to output ratio, Gemini 2.5 Flash costs $0.85 per 1M tokens. Routing the same call to the fallback in the policy below, Gemini 2.5 Flash-Lite, costs $0.00142, 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 against three alternatives
The same RAG answer priced on GPT-5 mini, Claude Haiku 4.5, DeepSeek V3.2 (chat). 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 this guide
$0.00530 per call
$2,650 / mo
baseline
GPT-5 mini
$0.00390 per call
$1,950 / mo
-26% vs Gemini 2.5 Flash
Claude Haiku 4.5
$0.0132 per call
$6,600 / mo
+149% vs Gemini 2.5 Flash
DeepSeek V3.2 (chat)
$0.00291 per call
$1,456 / mo
-45% vs Gemini 2.5 Flash
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 requests per day, raised by tier on the Gemini API; Vertex AI quotas are per region. Free tier limits are low and intended for testing.
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
Set the thinking budget explicitly per feature and enforce a per-tenant output token ceiling, so a prompt that triggers long thinking cannot run unbounded.
Token velocity breakers matter for Flash because it is fast: a loop can issue many calls per second before any dashboard updates.
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-pro
match:
model: gemini-2.5-flash
tier: pro # from X-PalmSouq-Tier
budgets:
monthly_usd: 120 # per tenant
soft_cap_pct: 80 # webhook to your app
on_hard_cap: fallback # or: block (HTTP 429)
fallback:
- gemini-2.5-flash-lite
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: 15
max_reasoning_tokens: 4000 # per request
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 2.5 Flash-Lite ($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
High-volume agents, RAG over large corpora and summarization. A strong fallback target for Gemini 2.5 Pro and for other providers' frontier models.
Provider documentation: ai.google.dev/gemini-api/docs
Gemini 2.5 Flash pricing questions
How much does Gemini 2.5 Flash cost per million tokens?
At list price Gemini 2.5 Flash costs $0.30 per 1M input tokens and $2.50 per 1M output tokens, with cached input at $0.075 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 support prompt caching?
Yes. Cached input is billed at $0.075 per 1M tokens against $0.30 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 rate limits?
Per-project RPM, TPM and requests per day, raised by tier on the Gemini API; Vertex AI quotas are per region. Free tier limits are low and intended for testing. 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 agent loops?
Set the thinking budget explicitly per feature and enforce a per-tenant output token ceiling, so a prompt that triggers long thinking cannot run unbounded. The sample policy on this page enables all four PALM SOUQ heuristics with a max step cap of 15 and falls back to Gemini 2.5 Flash-Lite at the hard cap.
Is there a batch discount for Gemini 2.5 Flash?
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 spend per customer.
Point your Google client at gateway.palmsouqltd.com, pass X-PalmSouq-Tenant, and every Gemini 2.5 Flash token is attributed, capped and protected by circuit breakers.
14-day free production trial · 100k requests included · no card required