Text model
databricks-gemini-3-8-flash pricing
Databricks charges $0.75 per million input tokens and $3.75 per million output tokens for databricks-gemini-3-8-flash, and $0.075 for cached input. Below: every rate that applies, what common workloads cost, and cheaper options.
- Input
- $0.75/ 1M
- Output
- $3.75/ 1M
- Cached input
- $0.075/ 1M
- Context
- 1Mtokens
All rates
| Tier | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
| Standard | $0.75 | $3.75 | $0.075 | $0.75 |
| Priority | $1.35 | $6.75 | $0.135 | $1.35 |
USD per million tokens. Long-context tiers apply when the whole prompt, cached tokens included, passes the threshold.
Work it out
What common workloads cost
| Workload | Per request | Cost per request | Requests a month | Per month |
|---|---|---|---|---|
| Chat reply | 1,500 input and 400 output tokens | $0.00262 | 100,000 | $262.50 |
| RAG answer, cached context | 2,000 fresh + 4,000 cached input, 500 output | $0.00367 | 100,000 | $367.48 |
| Agent step | 4,000 fresh + 8,000 cached input, 800 output | $0.0066 | 250,000 | $1,649.91 |
| Batch summary | 3,000 input and 300 output tokens via the Batch API | — | 1,000,000 | — |
Planning a mix of models? Simulate a workload with databricks-gemini-3-8-flash, alongside anything else you run.
Cheaper options
Current models that cost at least 15% less for a typical chat reply. Cheaper isn't always equivalent: test quality on your own prompts, then use veqen diff to see the impact at your volume.
| Model | Chat reply | Saving |
|---|---|---|
| databricks/databricks-gemini-3-5-flash-lite | $0.00181 | 31% |
| databricks/databricks-llama-4-maverick | $0.00135 | 49% |
| qwen/qwen3-vl-235b-a22b-thinking | $0.0022 | 16% |
| nebius/deepseek-ai/DeepSeek-R1 | $0.00216 | 18% |
Price history
| 2026-10-30 | Added to the price book |
Compare
Last verified with price book 2026-10-30. Sources: Databricks pricing and LiteLLM's MIT-licensed price file. Track every request to this model, per customer or project: install the SDK.