Text model
databricks-gpt-5-6-luna pricing
Databricks charges $1.00 per million input tokens and $6.00 per million output tokens for databricks-gpt-5-6-luna, and $0.10 for cached input. Below: every rate that applies, what common workloads cost, and cheaper options.
- Input
- $1.00/ 1M
- Output
- $6.00/ 1M
- Cached input
- $0.10/ 1M
- Context
- 922Ktokens
All rates
| Tier | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
| Standard | $1.00 | $6.00 | $0.10 | $1.25 |
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 | $0.0039 | 100,000 | $390.00 |
| RAG answer, cached context | 2,000 fresh + 4,000 cached input, 500 output | $0.0054 | 100,000 | $540.01 |
| Agent step | 4,000 fresh + 8,000 cached input, 800 output | $0.0096 | 250,000 | $2,400.08 |
| 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-5-6-luna, 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-inkling | $0.00312 | 20% |
| databricks/databricks-gpt-5-4-mini | $0.00292 | 25% |
| together/thinkingmachines/Inkling | $0.00312 | 20% |
| novita/qwen/qwen3-vl-235b-a22b-thinking | $0.00305 | 22% |
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.