Model comparison
Gemini 2.5 Flash vs Gemini 2.0 Flash
- Input
- $0.30 / 1M tokens (text / image / video); $1.00 / 1M tokens (audio)
- Output
- $2.50 / 1M tokens (includes thinking tokens)
- Context
- 1M
- Released
- 2025-04-17
- Input
- $0.10 / 1M tokens (text, image, or video); $0.70 / 1M tokens for audio
- Output
- $0.40 / 1M tokens
- Context
- 1,048,576 tokens (1M)
- Released
- 2025-02-05
Gemini 2.5 Flash scores higher on 2 of the 2 benchmarks both models report; Gemini 2.0 Flash is cheaper on input tokens ($0.1 vs $0.3 per 1M, 3×); Gemini 2.0 Flash has the larger context window (1.048576M vs 1M).
Specs and pricing side by side
| Spec | Gemini 2.5 Flash | Gemini 2.0 Flash |
|---|---|---|
| Maker | Googlesame | |
| Released | 2025-04-17 | 2025-02-05 |
| Context window | 1M | 1,048,576 tokens (1M) |
| Max output | 64K | 8,192 tokens |
| Input price | $0.30 / 1M tokens (text / image / video); $1.00 / 1M tokens (audio) | $0.10 / 1M tokens (text, image, or video); $0.70 / 1M tokens for audio |
| Output price | $2.50 / 1M tokens (includes thinking tokens) | $0.40 / 1M tokens |
| Parameters | not published | Undisclosed — Google never published the parameter count |
| License | Proprietary | Proprietary (Google) — closed source, served only via API |
| Weights | API only | API onlysame |
| Modalities | Text, Vision, Audio, Video, PDF | text input, image input, audio input, video input, text output |
| Knowledge cutoff | January 2025 | August 2024 |
Benchmarks both models report
| Benchmark | Gemini 2.5 Flash | Gemini 2.0 Flash |
|---|---|---|
| Global MMLU | 88.4% | 83.4% |
| MMMU | 79.7% | 70.7% |
Scores are as published by each maker or its cited source; harness, reasoning effort and date can differ between rows, so treat small gaps as ties. Sources are listed on each model page.
Which one should you pick?
Pick Gemini 2.5 Flash if…
- You care about Global MMLU, MMMU (it scores higher on 2 shared benchmarks).
- You need Text / Vision / Audio / Video / PDF input, which Gemini 2.0 Flash lacks.
- Your use case is: high-volume chat, summarization, and extraction where cost and latency matter.
Pick Gemini 2.0 Flash if…
- Cost matters: input tokens cost 3× less ($0.1 vs $0.3 per 1M).
- You need the longer context (1.048576M vs 1M).
- You need text input / image input / audio input / video input / text output input, which Gemini 2.5 Flash lacks.
- Your use case is: high-volume, cost-sensitive text generation, summarization, and classification.
FAQ
Which is better, Gemini 2.5 Flash or Gemini 2.0 Flash?
Gemini 2.5 Flash scores higher on 2 of the 2 benchmarks both models report; Gemini 2.0 Flash is cheaper on input tokens ($0.1 vs $0.3 per 1M, 3×); Gemini 2.0 Flash has the larger context window (1.048576M vs 1M). The better pick depends on whether you value benchmark scores, price per token, context length or openness for your workload.
How much cheaper is Gemini 2.0 Flash?
Gemini 2.5 Flash: $0.30 / 1M tokens (text / image / video); $1.00 / 1M tokens (audio) input, $2.50 / 1M tokens (includes thinking tokens) output. Gemini 2.0 Flash: $0.10 / 1M tokens (text, image, or video); $0.70 / 1M tokens for audio input, $0.40 / 1M tokens output (list API prices as published by each maker).
What are the context windows of Gemini 2.5 Flash and Gemini 2.0 Flash?
Gemini 2.5 Flash offers 1M with up to 64K output; Gemini 2.0 Flash offers 1,048,576 tokens (1M) with up to 8,192 tokens output.
Is Gemini 2.5 Flash newer than Gemini 2.0 Flash?
Gemini 2.5 Flash was released 2025-04-17; Gemini 2.0 Flash was released 2025-02-05.