Text model
sao10k/l3-8b-lunaris pricing
Novita AI charges $0.05 per million input tokens and $0.05 per million output tokens for sao10k/l3-8b-lunaris. Below: every rate that applies, what common workloads cost, and cheaper options.
- Input
- $0.05/ 1M
- Output
- $0.05/ 1M
- Context
- 8.2Ktokens
All rates
| Tier | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
| Standard | $0.05 | $0.05 | — | — |
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 | $0.000095 | 100,000 | $9.50 |
| RAG answer, cached context | 2,000 fresh + 4,000 cached input, 500 output | $0.000325 | 100,000 | $32.50 |
| Agent step | 4,000 fresh + 8,000 cached input, 800 output | $0.00064 | 250,000 | $160.00 |
| 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 sao10k/l3-8b-lunaris, 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 |
|---|---|---|
| novita/meta-llama/llama-3-8b-instruct | $0.000076 | 20% |
| novita/meta-llama/llama-3.2-3b-instruct | $0.000065 | 32% |
| deepinfra/Sao10K/L3-8B-Lunaris-v1-Turbo | $0.00008 | 16% |
| cloudflare/@cf/ibm-granite/granite-4.0-h-micro | $0.0000703 | 26% |
Price history
No price changes since Veqen started tracking this model.
Compare
Last verified with price book 2026-10-22. Sources: Novita AI pricing and LiteLLM's MIT-licensed price file. Track every call to this model, per customer or project: install the SDK.