Jamba 1.6 Large
Intelligence
10.6
#427/520
Coding
—
Math
—
Speed
51 tok/s
TTFT: 705.00s
Pricing
$2.00 / $8.00
per 1M tokens (in/out)
Jamba 1.6 Large is AI21 Labs’ offering for advanced natural language processing tasks. It processes at 51.436 tokens per second and is priced at $2 per million input tokens and $8 per million output tokens, targeting professional users.
When to Use Jamba 1.6 Large
✓ Best For
- Text generation and completion
- Natural language understanding
- Conversational AI applications
✗ Not Ideal For
- Users requiring high-speed processing for real-time applications
- Tasks needing advanced mathematical computations
How Jamba 1.6 Large Compares
Intelligence Index · Higher is better
Allen Institute for AINous ResearchAI21 LabsAlibabaLiquid AI
Benchmark Profile
Output Speed · tok/s
AlibabaAI21 LabsMistralZ AI
Intelligence · Coding · Math
Intelligence
Coding
Math
All Benchmark Scores (8)
| Benchmark | Score | |
|---|---|---|
| Intelligence Index | 10.6 | |
| MMLU-Pro | 565% | |
| GPQA | 387% | |
| LiveCodeBench | 172% | |
| HLE | 4% | |
| SciCode | 18.4% | |
| AIME | 4.7% | |
| MATH 500 | 58% |
Data: Artificial Analysis · Updated: April 2, 2026
Frequently Asked Questions (15)
When was Jamba 1.6 Large released?
Jamba 1.6 Large was released on March 6, 2025.
Who created Jamba 1.6 Large?
Jamba 1.6 Large was created by AI21 Labs.
How intelligent is Jamba 1.6 Large?
Jamba 1.6 Large scores 11 (estimated) on the Artificial Analysis Intelligence Index, placing it at the lower end among other open weight non-reasoning models of similar size (median: 22).
How fast is Jamba 1.6 Large?
Jamba 1.6 Large generates output at 59.8 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: 47.2 t/s).
What is the latency of Jamba 1.6 Large?
Jamba 1.6 Large has a time to first token (TTFT) of 1.39s (based on AI21 Labs's API), which is very competitive compared to other open weight non-reasoning models of similar size (median: 1.95s).
How much does Jamba 1.6 Large cost?
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: $2.33), based on AI21 Labs's API.
What is Jamba 1.6 Large API pricing?
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 (3:1 input to output ratio), this is $3.50 per 1M tokens. Pricing may vary by provider.
How verbose is Jamba 1.6 Large?
When evaluated on the Intelligence Index, Jamba 1.6 Large generated 980k output tokens, which is very competitive compared to other open weight non-reasoning models of similar size (median: 8.1M).
Is Jamba 1.6 Large a reasoning model?
No, Jamba 1.6 Large is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
What input modalities does Jamba 1.6 Large support?
Jamba 1.6 Large supports text input.
What output modalities does Jamba 1.6 Large support?
Jamba 1.6 Large supports text output.
Can Jamba 1.6 Large process images?
No, Jamba 1.6 Large does not support image input. It can only process text.
Is Jamba 1.6 Large multimodal?
No, Jamba 1.6 Large is not multimodal. It only supports text input.
What is the context window of Jamba 1.6 Large?
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.
Is Jamba 1.6 Large open source?
Yes, Jamba 1.6 Large is open weights. The model weights are publicly available and can be downloaded for self-hosting.
