API model string
gemini-1.5-flash (retired — use gemini-2.5-flash)Context window
1M tokens (retired)
Max output not published (retired)
- Knowledge cutoff
- not published
- Released
- 2024
- Modalities
- text, image in; text out (retired model)
Last verified July 10, 2026
Rate limits by tier
Gemini 1.5 Flash is shut down — the limits below describe its successor Gemini 2.5 Flash (gemini-2.5-flash), which is the correct migration target. All limits are project-specific and shown in the AI Studio console; Google no longer publishes a universal RPM/TPM table.
| Tier | Requirements | RPM | TPM | RPD | Concurrent | Notes |
|---|---|---|---|---|---|---|
| Free (AI Studio) — Gemini 2.5 Flash | Google account; no credit card required | not published (project-specific) | not published | ~1,500 (approximate; verify in AI Studio console) | not published | Free tier available on Gemini 2.5 Flash. Rate limits are project-specific and not guaranteed. Data may be used to improve Google products. |
| PAYG — Gemini 2.5 Flash | Google Cloud billing account linked to project | not published (project-specific, shown in AI Studio) | not published | not published | not published | $0.30 in / $2.50 out per MTok (raised July 2, 2026). No long-context surcharge — flat rate across all context lengths. |
| Batch API — Gemini 2.5 Flash | Google Cloud billing account | async (results within 24h) | not published | not published | not published | 50% off: $0.15 in / $1.25 out per MTok. |
| Gemini 1.5 Flash (retired) | n/a | n/a | n/a | n/a | n/a | No longer available. API calls to gemini-1.5-flash return model-not-found errors. Gemini 2.0 Flash-Lite was also shut down June 1, 2026. |
Swipe the table sideways to see every limit column.
- 1.Gemini 1.5 Flash is no longer on Google's pricing page and returns model-not-found errors. Gemini 2.0 Flash was also shut down June 1, 2026.
- 2.Gemini 2.5 Flash limits are project-specific. The ~1,500 RPD figure on the free tier is approximate and not guaranteed by Google docs.
- 3.All limits described are for Gemini 2.5 Flash (the successor). No Gemini 1.5 Flash limits are applicable or published.
Limits verified against the Google docs, July 10, 2026.
Token pricing
What you pay per million tokens (USD). Input and output are billed separately.
Input
$0.30
per 1M tokens
Output
$2.50
per 1M tokens
Cached input
$0.03
per 1M cached
Batch discount
−50%
on batch jobs
- Pricing shown is for Gemini 2.5 Flash (the successor). Gemini 1.5 Flash pricing is not published (retired).
- Prices raised July 2, 2026.
- Thinking tokens bill at the output rate ($2.50/MTok). Disable thinking for tasks not requiring step-by-step reasoning.
- No long-context surcharge on Gemini 2.5 Flash — flat pricing across the full 1M context window.
- Gemini 2.0 Flash-Lite pricing is not published (also shut down June 1, 2026).
Side-project (Gemini 2.5 Flash after migration)
$4.00
per month
Assumptions
5M input tokens / 1M output tokens per month
5M × $0.30/1M + 1M × $2.50/1M = $1.50 + $2.50
High-volume processing with 70% cache hit (Gemini 2.5 Flash)
$36.66
per month
Assumptions
60M input tokens / 12M output tokens per month; 42M served from cache
(18M × $0.30 + 42M × $0.03)/1M + 12M × $2.50/1M = $5.40 + $1.26 + $30.00
Enterprise scale (Gemini 2.5 Flash)
$320
per month
Assumptions
400M input tokens / 80M output tokens per month
400M × $0.30/1M + 80M × $2.50/1M = $120 + $200
Run your own numbers
Drag your real monthly token volumes and watch the bill update live — priced against rival models at the same usage.
Estimated gemini-1.5-flash (retired — use gemini-2.5-flash) spend
$22/mo
Input: $9.00
Output: $13
30M in × $0.300 + 5M out × $2.50 = $22
Same volume, priced across models
- Gemma 3Cheapest$1.60
- gemini-1.5-flash (retired — use gemini-2.5-flash)This model$22
- Gemini 2.5 Pro$88
- Claude 4 Sonnet$110
Rivals priced at their published input/output rates for the same monthly volumes. Prompt caching is model-specific, so it is applied to gemini-1.5-flash (retired — use gemini-2.5-flash) only. Estimates for comparison; real bills vary with request shape and long-context surcharges.
gemini-1.5-flash (retired — use gemini-2.5-flash) vs the alternatives
Gemini 1.5 Flash is retired. This comparison covers Gemini 2.5 Flash — its successor — against current alternatives.
| Aspect | gemini-1.5-flash (retired — use gemini-2.5-flash) | Gemini 2.5 Pro | Gemma 3 | Claude 4 Sonnet |
|---|---|---|---|---|
| Input $/MTok | $0.30 (Gemini 2.5 Flash) | $1.25 (Gemini 2.5 Pro) | $0.040 (Gemma 3 4B hosted) | $2.00 (Claude 4 Sonnet intro) |
| Output $/MTok | $2.50 (Gemini 2.5 Flash) | $10.00 (Gemini 2.5 Pro) | $0.080 (Gemma 3 4B) | $10.00 (Claude 4 Sonnet intro) |
| Context window | 1M tokens | 1M+ (Gemini 2.5 Pro) | 131K (Gemma 3) | 1M (Claude 4 Sonnet) |
| Long-context surcharge | None (flat pricing) | Yes >200K (whole prompt, Gemini 2.5 Pro) | None (Gemma 3) | None (Claude 4 Sonnet) |
| Free tier | Yes (~1,500 RPD approximate) | None (Gemini 2.5 Pro — paid only since Apr 2026) | Yes (Gemma 3 AI Studio) | None (Claude 4 Sonnet) |
| Batch discount | 50% | 50% (Gemini 2.5 Pro) | 50% (Gemma 3 hosted) | 50% (Claude 4 Sonnet) |
Swipe the table sideways to see every model.
Hitting a 429? The playbook
The exact errors you'll see
429 Too Many RequestsRESOURCE_EXHAUSTEDQuota exceeded for quota metric 'generate_requests_per_minute'models/gemini-1.5-flash is not found for API version v1betaWhy it happens & how to fix it
API calls still using the retired gemini-1.5-flash model string
Update your API call to use gemini-2.5-flash. This is typically a one-line change in your configuration or environment variable. The gemini-1.5-flash string returns a model-not-found error, not a rate limit error — but it often surfaces as a 429 in some SDK wrappers.
Free-tier daily limit (~1,500 RPD) reached on Gemini 2.5 Flash
Add a Google Cloud billing account to upgrade to PAYG. Alternatively, spread requests across the 24h window. The free-tier RPD is approximate and not guaranteed.
RPM exceeded on Gemini 2.5 Flash after migration
Implement exponential backoff and request queuing. View your current RPM quota in AI Studio and submit a quota increase request via Google Cloud Console → IAM & Admin → Quotas.
Project-level quota cap
Request a quota increase in Google Cloud Console → IAM & Admin → Quotas → Generative Language API. Provide expected volume and use case. Typical response time: 1–5 business days.
Retry strategy
After migrating to gemini-2.5-flash: implement exponential backoff per Google AI docs. Start with a 1-second delay, double on each retry, cap at 64 seconds, add ±20% jitter. Honor the Retry-After header when present. Official Google client libraries (google-generativeai, @google/generative-ai) handle retries automatically.
1// retry.ts — Gemini 2.5 Flash with exponential backoff (post-migration from 1.5 Flash)2const API_KEY = process.env.GOOGLE_AI_API_KEY!;3// KEY CHANGE: gemini-1.5-flash → gemini-2.5-flash4const BASE_URL = "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent";56async function generateWithRetry(7 prompt: string,8 maxRetries = 59): Promise<string> {10 let delay = 1000; // ms11 for (let attempt = 0; attempt <= maxRetries; attempt++) {12 const res = await fetch(`${BASE_URL}?key=${API_KEY}`, {13 method: "POST",14 headers: { "Content-Type": "application/json" },15 body: JSON.stringify({16 contents: [{ parts: [{ text: prompt }] }]17 })18 });1920 if (res.ok) {21 const data = await res.json();22 return data.candidates[0].content.parts[0].text;23 }2425 if (res.status === 429 && attempt < maxRetries) {26 const retryAfter = res.headers.get("Retry-After");27 const wait = retryAfter28 ? parseInt(retryAfter, 10) * 100029 : delay * (1 + Math.random() * 0.4 - 0.2);30 console.warn(`429 — retrying in ${Math.round(wait / 1000)}s (attempt ${attempt + 1})`);31 await new Promise((r) => setTimeout(r, wait));32 delay = Math.min(delay * 2, 64000);33 continue;34 }3536 throw new Error(`Gemini API error ${res.status}: ${await res.text()}`);37 }38 throw new Error("Max retries exceeded");39}How to raise your limits
The ladder from the starter tier to enterprise — what each rung takes, and what it unlocks.
Migrate model string first
Minutes (code change)Replace gemini-1.5-flash with gemini-2.5-flash in your code, environment variables, or configuration. Gemini 2.0 Flash users also need to update (gemini-2.0-flash-lite shut down June 1, 2026).
Unlocks: Access to the current Flash-tier model; eliminates model-not-found errors immediately.
Free (AI Studio) on Gemini 2.5 Flash
ImmediateSign in at aistudio.google.com with a Google account. No credit card needed.
Unlocks: ~1,500 RPD (approximate). Sufficient for development and low-volume testing.
PAYG
Minutes after billing enabledGoogle Cloud Console → create or link a billing account → associate with your AI Studio project.
Unlocks: $0.30/$2.50 per MTok, higher project quotas, data not used for training.
Higher RPM / TPM
1–5 business daysGoogle Cloud Console → IAM & Admin → Quotas → Generative Language API → Request increase.
Unlocks: Custom per-project RPM and TPM limits.
Enterprise
NegotiatedContact Google Cloud Sales at cloud.google.com/contact.
Unlocks: Dedicated capacity, SLAs, committed-use discounts.
Cut your token spend
Update the model string first
Eliminates all model-not-found errors immediatelyThe single highest-impact change: replace gemini-1.5-flash (or gemini-2.0-flash-lite) with gemini-2.5-flash in every place the model is referenced. No other API changes are required for basic migration.
Context caching on 2.5 Flash
−90% input cost on repeated prefixesCache reads on Gemini 2.5 Flash cost $0.03/MTok — 10% of the standard $0.30 input rate. For pipelines with shared system prompts or document prefixes, caching delivers significant savings immediately after migration.
No long-context surcharge on Flash
Zero cost penalty on full 1M contextGemini 2.5 Flash charges flat pricing at all context lengths. You can use the full 1M window without the 2× input cost surcharge that Gemini 2.5 Pro applies above 200K tokens.
Batch API for async workloads
−50% cost on all tokensUse the Batch API for non-realtime processing: document classification, bulk extraction, overnight jobs. Rates: $0.15/$1.25 per MTok. Results within 24h.
Disable thinking for simple tasks
2–5× reduction in output token volumeThinking tokens on Gemini 2.5 Flash bill at the output rate ($2.50/MTok) and can significantly expand response size. Disable thinking for classification, extraction, and simple Q&A tasks.
Frequently asked questions
Does Gemini 1.5 Flash still work?
No. Gemini 1.5 Flash has been shut down and is no longer available via the Google AI API. Calls to gemini-1.5-flash return a model-not-found error. The correct replacement is gemini-2.5-flash, which typically requires only a one-line model string change.
What replaced Gemini 1.5 Flash?
Gemini 2.5 Flash (api_name: gemini-2.5-flash) is the current Flash-tier model. It has the same 1M context window, a free tier (~1,500 RPD approximate), PAYG pricing at $0.30/$2.50 per MTok (raised July 2, 2026), and no long-context surcharge. Gemini 2.0 Flash-Lite was also shut down June 1, 2026 — not a valid migration target.
How do I migrate from Gemini 1.5 Flash to Gemini 2.5 Flash?
In most cases: change the model string from gemini-1.5-flash to gemini-2.5-flash in your API call or environment variable. The request/response format is compatible. Test in a staging environment first and verify that any system prompts still perform as expected, since model behavior may differ between generations.
What is the Gemini 2.5 Flash rate limit?
Google no longer publishes a universal RPM or TPM table. Limits are project-specific and shown in your AI Studio console. The free tier has approximately 1,500 requests per day (not guaranteed). PAYG users see higher limits in their project dashboard. To increase limits, submit a quota increase request via Google Cloud Console → IAM & Admin → Quotas.
Is Gemini 2.5 Flash free?
Yes — there is a free tier via AI Studio with approximately 1,500 requests per day (not a hard published limit). For production, upgrade to PAYG at $0.30/$2.50 per MTok with no minimum spend or subscription fee.
Gemini 1.5 Flash vs Gemini 2.5 Flash pricing?
Gemini 1.5 Flash pricing is no longer published (model is retired). Gemini 2.5 Flash is priced at $0.30 input / $2.50 output per MTok (as of July 2, 2026). Context cache reads cost $0.03/MTok. Batch API offers 50% off: $0.15/$1.25 per MTok.
Can RapidDev help me migrate from Gemini 1.5 Flash?
Yes. RapidDev can audit your existing API calls, handle the model string migration, and optimise caching and batching to reduce Gemini 2.5 Flash costs. Reach out at rapidevelopers.com/contact for a free scoping call.
We build AI apps that don't hit rate limits
- Retry, backoff & caching built in
- Multi-provider fallback routing
- Fixed price, you own the code
30-min call. No commitment.