Model Library
AI21 LabsReleased March 6, 2025Jamba 1.6 Mini
AI21 Labs · Released March 6, 2025
Intelligence score
3
At a glance
- Intelligence
- 3
- Speed
- 180.2tokens/sec
- Latency
- 1.06stime to first token
- Input price
- $0.20per 1M tokens
- Output price
- $0.40per 1M tokens
- Context window
- 260Ktokens
- Parameters
- 52billions
Summary
Comparison summary
Jamba 1.6 Mini scores 3 (estimated) on the Artificial Analysis Intelligence Index, placing it at the lower end among other open weight non-reasoning models of similar size (median: 7). Jamba 1.6 Mini generates output at 180.2 tokens per second (based on AI21 Labs's API), which is well above average compared to other open weight non-reasoning models of similar size (median: 81.5 t/s). Jamba 1.6 Mini costs $0.20 per 1M input tokens (very competitive, median: $0.53) and $0.40 per 1M output tokens (very competitive, median: $1.05), based on AI21 Labs's API.
Specifications
Technical specifications
| Model name | Jamba 1.6 Mini |
|---|---|
| Provider | AI21 Labs |
| Release date | March 6, 2025 |
| Intelligence score | 3 |
| Speed | 180.2 tokens/sec |
| Latency (TTFT) | 1.06s |
| Input price | $0.20 / 1M tokens |
| Output price | $0.40 / 1M tokens |
| Context window | 260,000 tokens |
| Parameters | 52B |
| 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-mini |
Pricing
Token prices
Price per 1M tokens
Jamba 1.6 Mini, as listed in the catalog record
- Input$0.20
- Output$0.40
| Token type | Price per 1M |
|---|---|
| Input | $0.20 |
| Output | $0.40 |
Model Intelligence legacy profile: jamba-1-6-mini
FAQ · 20
Frequently asked questions
Jamba 1.6 Mini was released on March 6, 2025.
Jamba 1.6 Mini was created by AI21 Labs.
Jamba 1.6 Mini scores 3 (estimated) on the Artificial Analysis Intelligence Index, placing it at the lower end among other open weight non-reasoning models of similar size (median: 7).
Jamba 1.6 Mini generates output at 180.2 tokens per second (based on AI21 Labs's API), which is well above average compared to other open weight non-reasoning models of similar size (median: 81.5 t/s).
Jamba 1.6 Mini has a time to first token (TTFT) of 1.06s (based on AI21 Labs's API), which is very competitive compared to other open weight non-reasoning models of similar size (median: 1.59s).
Jamba 1.6 Mini costs $0.20 per 1M input tokens (very competitive, median: $0.53) and $0.40 per 1M output tokens (very competitive, median: $1.05), based on AI21 Labs's API.
Jamba 1.6 Mini costs $0.20 per 1M input tokens and $0.40 per 1M output tokens (based on AI21 Labs's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.22 per 1M tokens. Pricing may vary by provider.
No, Jamba 1.6 Mini is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
Jamba 1.6 Mini supports text input.
Jamba 1.6 Mini supports text output.
No, Jamba 1.6 Mini does not support image input. It can only process text.
No, Jamba 1.6 Mini is not multimodal. It only supports text input.
Jamba 1.6 Mini 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 Mini is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Jamba 1.6 Mini has 52 billion parameters (12 billion active).
Jamba 1.6 Mini is a Mixture of Experts (MoE) model with 52 billion total parameters, but only 12 billion active parameters are used during inference.
Jamba 1.6 Mini is released under the Jamba Open Model License Agreement license. This license allows commercial use.
Jamba 1.6 Mini achieves a score of 3 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, Jamba 1.6 Mini is available via API through 1 provider.
Jamba 1.6 Mini is available through 1 API provider.