Text model
databricks-gpt-6-1-terra pricing
Databricks charges $1.00 per million input tokens and $5.00 per million output tokens for databricks-gpt-6-1-terra, and $0.05 for cached input. Below: every rate that applies, what common workloads cost, and cheaper options.
- Input
- $1.00/ 1M
- Output
- $5.00/ 1M
- Cached input
- $0.05/ 1M
- Context
- 922Ktokens
All rates
| Tier | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
| Standard | $1.00 | $5.00 | $0.05 | $1.25 |
| Standard, prompts over 272K tokens | $2.00 | $7.50 | $0.10 | $2.50 |
| Priority | $2.00 | $10.00 | $0.10 | $2.50 |
| Priority, prompts over 272K tokens | $4.00 | $15.00 | $0.20 | $5.00 |
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 | $0.0035 | 100,000 | $350.00 |
| RAG answer, cached context | 2,000 fresh + 4,000 cached input, 500 output | $0.0047 | 100,000 | $470.00 |
| Agent step | 4,000 fresh + 8,000 cached input, 800 output | $0.0084 | 250,000 | $2,099.99 |
| 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-gpt-6-1-terra, 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-gpt-5-4-mini | $0.00292 | 16% |
| databricks/databricks-gemini-3-6-flash | $0.00262 | 25% |
| deepinfra/zai-org/GLM-5.1 | $0.00298 | 15% |
| openai/gpt-5.4-mini | $0.00293 | 16% |
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.