Model pricing
CodeLlama 70B pricing
CodeLlama 70B by Anyscale costs
CodeLlama 70B pricing
per 1M input tokens andCodeLlama 70B pricing
per 1M output tokens (cached input not recorded, batch input not recorded) as of 2026-10-31. A 1,000-input/500-output request costs $0.0015. The lowest-cost alternative with at least this context window and the same recorded reasoning category is lfm-2.2-6b at $0.01/$0.02; capability equivalence is not guaranteed.Notes
Code generation
Key pricing facts
| Fact | Value |
|---|---|
| Input / 1M tokens | $1 |
| Output / 1M tokens | $1 |
| Cached input / 1M | Not recorded |
| Batch input / output / 1M | Not recorded |
| Context window | 16,384 |
| Provider | Anyscale |
| Last verified | No model-specific verification date recorded |
| Snapshot updated | 2026-10-31 |
Last updated: · Source: No official provider pricing URL recorded · Methodology
Frequently asked questions
What does CodeLlama 70B cost per million tokens?
Input costs $1 and output costs $1 per million tokens. The 1,000-input/500-output example costs $0.0015, before discounts, taxes, hidden reasoning tokens or context-tier surcharges.
Does CodeLlama 70B have cached or batch pricing?
Cached input: not separately recorded. Batch: not recorded in this dataset. Eligibility and cache-write charges depend on the provider; these discounts are not automatically stacked.
What is a cheaper alternative to CodeLlama 70B?
lfm-2.2-6b costs $0.01 input and $0.02 output per million tokens. This comparison matches context capacity and reasoning category, not benchmark quality. Test your workload before replacing a model.
How often are these prices verified?
The live pricing table synchronizes stored model records daily; public file snapshots update when the site is rebuilt. Synchronization is not independent provider verification. Snapshot updated 2026-10-31. No model-specific verification date is recorded; the snapshot date must not be interpreted as an official provider verification.