Gemini 2.5 Flash-Lite
Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents
Shogo Agent Index
UnrankedNot ranked yet: 0 agentic benchmarks measured, and we need at least 2 plus an overall capability score. It will be ranked as results are published.
Agentic coding
16
estimated
Long-horizon autonomy
26
estimated
Knowledge-work agents
15
estimated
Computer use
5
estimated
Security & context learning
14
estimated
Price
- Input
- $0.070/M
- Output
- $0.28/M
- Cache read
- —/M
- 3:1 blend
- $0.12/M
- Agent-effective
- $0.080/M
Cheapest host for agents: Google AI Studio at $0.020/M.
Agent-effective = 20 input tokens per output token, 85% cache hits. Why.
Agentic benchmarks
| Benchmark | Score | Normalised | Index weight | Harness / source |
|---|---|---|---|---|
| SWE-bench Verified | est. | 8% | predicted 47 | |
| Terminal-Bench 2.0 | est. | 8% | predicted 6 | |
| DeepSWE | est. | 6% | predicted 8 | |
| FrontierSWE | est. | 5% | predicted 1 | |
| CursorBench | est. | 4% | predicted 16 | |
| GSO-Bench | est. | 4% | predicted 1 | |
| METR Time Horizons | est. | 10% | predicted 47 | |
| Vending-Bench 2 | est. | 6% | predicted 1 | |
| PostTrainBench | est. | 4% | predicted 10 | |
| APEX-Agents | est. | 8% | predicted 9 | |
| GDPval | est. | 7% | predicted 15 | |
| Remote Labor Index | est. | 5% | predicted 0 | |
| DeepResearch Bench | est. | 5% | predicted 40 | |
| OSWorld 2.0 | est. | 6% | predicted 0 | |
| OSWorld | est. | 4% | predicted 12 | |
| Cybench | est. | 5% | predicted 16 | |
| CL-bench | est. | 5% | predicted 12 |
Other benchmarks
API hosts
Live prices and uptime for every host serving Gemini 2.5 Flash-Lite via OpenRouter.
| Host | Input | Output | Cache read | Agent $/M | Uptime 24h | Quant |
|---|---|---|---|---|---|---|
| Google AI Studio | $0.050 | $0.20 | $0.005 | $0.020 | 100.0% | — |
| Google AI Studio | $0.10 | $0.40 | $0.010 | $0.040 | 100.0% | — |
| Google AI Studio | $0.18 | $0.72 | $0.018 | $0.070 | 71.8% | — |