Deprecated on Oct 2, 2026. 8 providers still list it at the prices below.
Context
1M
Max output
1M
Serving providers
8
Cheapest input
$0.15 /1M
On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
Benchmarks
independent evaluations · source: Artificial AnalysisSpeed & latency
Output speed
206 t/s
tokens / second
Time to first token
0.47s
latency
Headline indices
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 | 65% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| Mlcr OverallFrozen Sep 9, 2026 | 0.1 | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| MMLU-ProFrozen Aug 18, 2026 | 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 | — | |||||||||||||
| ||||||||||||||||
| SciCodeArtificial Analysis did not report this score in its latest run on Oct 14, 2026 | 39% | — | — | |||||||||||||
| ||||||||||||||||
| TerminalBench Hard | 14% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| τ²-bench | 32% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
Artificial Analysis last published scores for this benchmark on Sep 9, 2026. Scores here are frozen at that date, and models released since are not on it.
Artificial Analysis last published scores for this benchmark on Aug 18, 2026. Scores here are frozen at that date, and models released since are not on it.
Pricing by serving provider
standard tier · per 1M tokens · click a provider to expandInput pricing runs from $0.15 to $0.30 per 1M tokens across 8 providers, so the dearest route costs 100% more than the cheapest for the same model.
| Serving provider | Input /1M | Output /1M | Endpoints | |||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| OCICheapest | $0.15 | $0.60 | 1 | |||||||||||||||||
Standardoci/google.gemini-2.5-flash
| ||||||||||||||||||||
| DeepInfra | $0.30 | $2.50 | 1 | |||||||||||||||||
Standarddeepinfra/google/gemini-2.5-flash
| ||||||||||||||||||||
| $0.30 | $2.50 | 1 | ||||||||||||||||||
Standardgemini/gemini-2.5-flash
| ||||||||||||||||||||
| OpenRouter | $0.30 | $2.50 | 1 | |||||||||||||||||
Standardgoogle/gemini-2.5-flash
| ||||||||||||||||||||
| Replicate | $0.30 | $2.50 | 1 | |||||||||||||||||
Standardreplicate/google/gemini-2.5-flash
| ||||||||||||||||||||
| VercelVercel reseller quote | $0.30 | $2.50 | 1 | |||||||||||||||||
Standardgoogle/gemini-2.5-flash
| ||||||||||||||||||||
| Vertex AI Language Models | $0.30 | $2.50 | 1 | |||||||||||||||||
Standardgemini-2.5-flash
| ||||||||||||||||||||
| Databricks | $0.30 | $2.50 | 1 | |||||||||||||||||
Standarddatabricks/databricks-gemini-2-5-flash
| ||||||||||||||||||||
| Vercel is dearest at $0.54 / $4.50 | ||||||||||||||||||||
Price history
listed seller prices, input and output per 1M tokens 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-flashgoogle/gemini-2.5-flash:batchgoogle/gemini-2.5-flashdeepinfra/google/gemini-2.5-flashgoogle/gemini-2.5-flashgemini-2.5-flashgoogle/gemini-2.5-flashgemini/gemini-2.5-flashreplicate/google/gemini-2.5-flashdatabricks/databricks-gemini-2-5-flashgoogle/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 deprecated on 2026-10-02, but 8 serving providers still list it.
How much does Gemini 2.5 Flash cost?
Gemini 2.5 Flash costs $0.15 per 1M input tokens from OCI, and $0.60 per 1M output tokens from OCI. Across 8 serving providers, input prices range from $0.15 to $0.30 per 1M tokens.
What is the context window of Gemini 2.5 Flash?
Gemini 2.5 Flash accepts up to 1M tokens of context and can return up to 1M output tokens.
Which providers serve Gemini 2.5 Flash?
Gemini 2.5 Flash is available from 8 serving providers, each with its own pricing and model ID. OCI is currently the cheapest.
What can Gemini 2.5 Flash do?
Gemini 2.5 Flash supports image input (vision), tool use, reasoning, audio input, prompt caching, structured output and web search.
Other Google models
compare pricing across the Google lineupGemma 4 31B$0.09/1M · 13 providersGemma 4 26B A4B $0.07/1M · 10 providersGemma 3 27B$0.08/1M · 8 providersGemini 3.7 Flash$0.75/1M · 7 providersGemini 2.5 Pro$1.25/1M · 7 providersGemini 3.5 Flash$1.50/1M · 7 providersGemini 3.1 Flash Lite$0.25/1M · 6 providersGemini 3.5 Flash Lite$0.30/1M · 6 providers
Popular comparisons
head-to-head pages featuring Gemini 2.5 Flash
Gemini 2.5 Flash vs GPT-4o Listed prices from LiteLLM, OpenRouter and Vercel · last checked Oct 14, 2026
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI