This model was retired on 2026-10-20. The pricing below is the last-known rate, kept for migration reference.
Gemini 2.5 FlashDeprecated
VisionTool useReasoningAudioPrompt cachingStructured outputWeb search
Context
1M
Max output
1M
Serving providers
8
Cheapest input
$0.15 /1M
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
Benchmarks
independent evaluations · source: Artificial AnalysisSpeed & latency
Output speed
208 t/s
tokens / second
Time to first token
0.46s
latency
Headline indices
Intelligence Index
20.3
of 100
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| CritPt | 1% | default | — | |||||||||||||
| ||||||||||||||||
| GPQA Diamond | 79% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| Humanity's Last Exam | 12% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| IFBench | 50% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| LiveCodeBench | 70% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| Long-Context Reasoning | 66% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| Mlcr Overall | 0.1 | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| MMLU-Pro | 83% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| MMMU-Pro | 69% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| Omniscience | -29.8 | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| Omniscience Accuracy | 0.3 | default | — | |||||||||||||
| ||||||||||||||||
| Omniscience Non Hallucination | 0.2 | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| SciCode | 39% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| TerminalBench Hard | 14% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| τ²-bench | 32% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
Pricing by serving provider
last-known · per 1M tokens · click a provider to expand| Serving provider | Input /1M | Output /1M | Endpoints | |||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| OCI | $0.15 | $0.60 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
| DeepInfra | $0.30 | $2.50 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
| Vertex AI | $0.30 | $2.50 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
| $0.30 | $2.50 | 1 | ||||||||||||||||||||||
| ||||||||||||||||||||||||
| Vercel AI Gateway | $0.30 | $2.50 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
| OpenRouter | $0.30 | $2.50 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
| Databricks | $0.30 | $2.50 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
| Replicate | $2.50 | $2.50 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
Price history
input + output $/1M since we started tracking Input Output
Input down 50% since first tracked
Cost calculator
estimate your monthly spend on this model$78
estimated / month
Model IDs
copy the exact identifier for your platformoci/google.gemini-2.5-flashdeepinfra/google/gemini-2.5-flashgemini-2.5-flashgemini/gemini-2.5-flashvercel_ai_gateway/google/gemini-2.5-flashgoogle/gemini-2.5-flashdatabricks/databricks-gemini-2-5-flashreplicate/google/gemini-2.5-flash
Frequently asked questions
Gemini 2.5 Flash pricing, context and availabilityIs Gemini 2.5 Flash still available?
Gemini 2.5 Flash was retired on 2026-10-20. The pricing on this page is the last-known rate, kept for migration reference.
How much did Gemini 2.5 Flash cost?
Gemini 2.5 Flash's last-known pricing, before it was retired on 2026-10-20, was $0.15 per 1M input tokens and $0.60 per 1M output tokens.
What was the context window of Gemini 2.5 Flash?
Gemini 2.5 Flash had a 1M token context window and could return up to 1M output tokens.
What could Gemini 2.5 Flash do?
Gemini 2.5 Flash supported image input (vision), tool use, reasoning, audio input, prompt caching, structured output and web search.
Other Google models
compare pricing across the Google lineupPopular comparisons
head-to-head pages featuring Gemini 2.5 Flash
Gemini 2.5 Flash vs GPT-4o Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI