Model Library
AI21 LabsReleased March 6, 2025Jamba 1.6 Large
AI21 Labs · Released March 6, 2025
Intelligence score
5
At a glance
- Intelligence
- 5
- Speed
- 58.2tokens/sec
- Latency
- 1.73stime to first token
- Input price
- $2.00per 1M tokens
- Output price
- $8.00per 1M tokens
- Context window
- 260Ktokens
- Parameters
- 398billions
Summary
Comparison summary
Jamba 1.6 Large scores 5 (estimated) on the Artificial Analysis Intelligence Index, placing it at the lower end among other open weight non-reasoning models of similar size (median: 17). Jamba 1.6 Large generates output at 58.2 tokens per second (based on AI21 Labs's API), which is below average compared to other open weight non-reasoning models of similar size (median: 58.3 t/s). Jamba 1.6 Large costs $2.00 per 1M input tokens (at the higher end, median: $0.60) and $8.00 per 1M output tokens (at the higher end, median: $2.40), based on AI21 Labs's API.
Specifications
Technical specifications
| Model name | Jamba 1.6 Large |
|---|---|
| Provider | AI21 Labs |
| Release date | March 6, 2025 |
| Intelligence score | 5 |
| Speed | 58.2 tokens/sec |
| Latency (TTFT) | 1.73s |
| Input price | $2.00 / 1M tokens |
| Output price | $8.00 / 1M tokens |
| Context window | 260,000 tokens |
| Parameters | 398B |
| Reasoning | No |
| Input modalities | text |
| Output modalities | — |
| Open weights | Yes |
| License | Jamba Open Model License Agreement |
| API availability | — |
| Source | Model Intelligence legacy profile: jamba-1-6-large |
Pricing
Token prices
Price per 1M tokens
Jamba 1.6 Large, as listed in the catalog record
- Input$2.00
- Output$8.00
| Token type | Price per 1M |
|---|---|
| Input | $2.00 |
| Output | $8.00 |
Model Intelligence legacy profile: jamba-1-6-large
FAQ · 20
Frequently asked questions
Jamba 1.6 Large was released on March 6, 2025.
Jamba 1.6 Large was created by AI21 Labs.
Jamba 1.6 Large scores 5 (estimated) on the Artificial Analysis Intelligence Index, placing it at the lower end among other open weight non-reasoning models of similar size (median: 17).
Jamba 1.6 Large generates output at 58.2 tokens per second (based on AI21 Labs's API), which is below average compared to other open weight non-reasoning models of similar size (median: 58.3 t/s).
Jamba 1.6 Large has a time to first token (TTFT) of 1.73s (based on AI21 Labs's API), which is better than average compared to other open weight non-reasoning models of similar size (median: 2.33s).
Jamba 1.6 Large costs $2.00 per 1M input tokens (at the higher end, median: $0.60) and $8.00 per 1M output tokens (at the higher end, median: $2.40), based on AI21 Labs's API.
Jamba 1.6 Large costs $2.00 per 1M input tokens and $8.00 per 1M output tokens (based on AI21 Labs's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $2.60 per 1M tokens. Pricing may vary by provider.
No, Jamba 1.6 Large is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
Jamba 1.6 Large supports text input.
Jamba 1.6 Large supports text output.
No, Jamba 1.6 Large does not support image input. It can only process text.
No, Jamba 1.6 Large is not multimodal. It only supports text input.
Jamba 1.6 Large has a context window of 260k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, Jamba 1.6 Large is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Jamba 1.6 Large has 398 billion parameters (94 billion active).
Jamba 1.6 Large is a Mixture of Experts (MoE) model with 398 billion total parameters, but only 94 billion active parameters are used during inference.
Jamba 1.6 Large is released under the Jamba Open Model License Agreement license. This license allows commercial use.
Jamba 1.6 Large achieves a score of 5 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, Jamba 1.6 Large is available via API through 1 provider.
Jamba 1.6 Large is available through 1 API provider.