Text model
databricks-meta-llama-3-1-8b-instruct pricing
Databricks charges $0.15 per million input tokens and $0.45 per million output tokens for databricks-meta-llama-3-1-8b-instruct, and $0.15 for cached input. Below: every rate that applies, what common workloads cost, and cheaper options.
- Input
- $0.15/ 1M
- Output
- $0.45/ 1M
- Cached input
- $0.15/ 1M
- Context
- 200Ktokens
All rates
| Tier | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
| Standard | $0.15 | $0.45 | $0.15 | $0.15 |
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 call | Cost per call | Calls a month | Per month |
|---|---|---|---|---|
| Chat reply | 1,500 input and 400 output tokens | $0.000405 | 100,000 | $40.50 |
| RAG answer, cached context | 2,000 fresh + 4,000 cached input, 500 output | $0.00113 | 100,000 | $112.51 |
| Agent step | 4,000 fresh + 8,000 cached input, 800 output | $0.00216 | 250,000 | $540.04 |
| 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-meta-llama-3-1-8b-instruct, 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-deepseek-v4-flash-0731 | $0.000322 | 20% |
| databricks/databricks-gpt-5-nano | $0.000235 | 42% |
| cloudflare/@cf/meta/llama-3.2-11b-vision-instruct | $0.000343 | 15% |
| deepinfra/meta-llama/Llama-Guard-4-12B | $0.000342 | 16% |
Price history
No price changes since Veqen started tracking this model.
Compare
Last verified with price book 2026-10-22. Sources: Databricks pricing and LiteLLM's MIT-licensed price file. Track every call to this model, per customer or project: install the SDK.