Gemini 2.5 Flash API pricing
8 providers serve Gemini 2.5 Flash. Gemini 2.5 Flash is a proprietary API model, up to 1049K context. Prices below are per 1M tokens, cheapest input first.
Refreshed 2026-08-23 · list prices from provider APIs| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context | |
|---|---|---|---|---|---|
| Oracle OCI | $0.150 | $0.600output floor | - | 1049K | Use |
| Databricks | $0.300 | $2.50 | - | 1049K | Use |
| DeepInfra | $0.300 | $2.50 | - | 1000K | Use |
| Google Vertex AI | $0.300 | $2.50 | $0.030 | 1049K | Use |
| Google Gemini API | $0.300 | $2.50 | $0.030 | 1049K | Use |
| OpenRouter | $0.300 | $2.50 | - | 1049K | Use |
| Vercel AI Gateway | $0.300 | $2.50 | - | 1000K | Use |
| Replicate | $2.50 | $2.50 | - | - | Use |
The cheapest way to run Gemini 2.5 Flash
On an illustrative 70M-input / 30M-output monthly workload, today's lowest listed cost is roughly $28.50/month, at Oracle OCI. Input-heavy, output-heavy and cache-heavy workloads can produce different winners. Use the live mix calculator below rather than combining floors from two different providers. It is API-only, so the table above is your full set of options. Run your own numbers in the breakeven calculator, or read the breakeven math.
Your actual monthly cost
Cache read uses the listed cache rate where available; otherwise it falls back to normal input price. Batch, write-cache, volume and negotiated discounts are excluded.
Related models
| Model | Cheapest in $/1M | Cheapest out $/1M | Providers |
|---|---|---|---|
| Gemini 2.5 Pro | $1.25 | $10.00 | 7 |
| Gemini-3-Pro | $2.00 | $12.00 | 6 |
| Gemini 3 Flash Preview | $0.500 | $3.00 | 5 |
| Gemini 3.1 Flash Lite | $0.250 | $1.50 | 4 |
| Gemini 3.1 Pro Preview | $2.00 | $12.00 | 4 |
| Gemini-2.0-Flash-001 | $0.100 | $0.400 | 4 |
FAQ
What is the cheapest API for Gemini 2.5 Flash?
As of 2026-08-23, the lowest input price for Gemini 2.5 Flash is Oracle OCI at $0.150 per 1M input tokens. The lowest output price is Oracle OCI at $0.600 per 1M output tokens. The cheapest provider for a real workload depends on its input/output mix. The next-lowest input price is Databricks at $0.300, a 100% difference.
← All models · GPU rental prices · Breakeven calculator · Get this data as JSON