# Jamba Mini vs Llama-3.1-70B-Instruct - AI Model Comparison

- Page: https://opencode.ai/data/compare/ai21/jamba-mini/meta/llama-3-1-70b-instruct

|  | Jamba Mini | Llama-3.1-70B-Instruct |
| --- | --- | --- |
| Lab | AI21 | Meta |
| Context window | 256K | 128K |
| Max output | 4.1K | 4.1K |
| Input modalities | text | text |
| Reasoning | No | No |
| Tool calling | Yes | Yes |
| Open weights | Yes | Yes |
| Release date | 2026-01-01 | 2024-07-23 |
| Input price per 1M tokens | $0.20 | $0.00 |
| Output price per 1M tokens | $0.40 | $0.00 |
| Cached input price per 1M tokens | - | - |
| OpenCode tokens: past 2 months | - | - |
| Share of all tokens | - | - |
| Rank by tokens last week | - | - |
| Unique users | - | - |
| Weekly retention | - | - |

Model pages: [Jamba Mini](https://opencode.ai/data/ai21/jamba-mini.md), [Llama-3.1-70B-Instruct](https://opencode.ai/data/meta/llama-3-1-70b-instruct.md)

## Methodology

- Updates: Aggregated every hour. Days and weeks use UTC.
- Tokens: Input, output, reasoning, and cached tokens for each request.
- Users and sessions: Approximate counts of distinct users and OpenCode sessions.
- Cost: Session cost is the average cost per OpenCode session. Token prices are list prices from the OpenCode model catalog.
- Retention: The share of a model's users in one week who use it again the next week.
- Citation: Cite OpenCode Data (opencode.ai/data) with the update time shown at the top of the page.