AI21 Labs model product
Jamba 1.5 Large
State-of-the-art hybrid SSM-Transformer instruction following foundation model, offering superior long context handling, speed, and quality.
Updated Aug 12, 2026. Default version: Jamba 1.5 Large
LLMBoard score2.7Jamba 1.5 Large
Coverage80%8 benchmark families
Context window256KTokens
Official input priceN/AOfficial price unavailable
Jamba 1.5 Large Specifications
Technical details for the model's default version.
- Version
- Jamba 1.5 Large
- Released
- Aug 22, 2024
- Knowledge cutoff
- Mar 5, 2024
- Parameters
- 398B
- Context window
- 256K
- Max output
- 256K
- Inputs
- text
- Outputs
- text
- Open weights
- No
- License
- Jamba Open Model License
Jamba 1.5 Large Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Jamba 1.5 Large Benchmark Results
Benchmark scores for Jamba 1.5 Large.
| ARC-C | 93.0% | 07 | 34 | 81.8% | C | |
| Wild Bench | 48.5% | 07 | 8 | 14.3% | C | |
| TruthfulQA | 58.3% | 09 | 18 | 52.9% | C | |
| Arena Hard | 65.4% | 12 | 26 | 56.0% | C | |
| GSM8k | 87.0% | 33 | 48 | 31.9% | C | |
| MMLU | 81.2% | 53 | 100 | 47.5% | C | |
| MMLU-Pro | 53.5% | 110 | 129 | 14.8% | C | |
| GPQA | 36.9% | 210 | 234 | 10.3% | C |
Jamba 1.5 Large Arena Results
Preference and agent-evaluation results for the default version.
| text style control | overall | 263 | 1289.3 | 8,662 | N/A | |
| text | overall | 268 | 1237.2 | 8,662 | N/A |
Jamba 1.5 Large Runtime Performance
Provider-specific output speed and catalog latency for Jamba 1.5 Large. Runtime does not affect the capability score.
| Bedrock | 100 tok/s | 0.5 s | 256K | 256K | |
| 42 tok/s | 0.3 s | 256K | 256K |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Jamba 1.5 Large Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- N/A
- Tracked offerings
- 0
No provider prices
The default version has no current input or output token prices.
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Jamba 1.5 Large Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
| Jamba 1.5 Large | 2.7 | 398B | 256K | 256K | No | Jamba Open Model License |
What is Jamba 1.5 Large?
Key information about Jamba 1.5 Large and its available data.
State-of-the-art hybrid SSM-Transformer instruction following foundation model, offering superior long context handling, speed, and quality.
Data as of 2026-08-11.
Jamba 1.5 Large vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to Jamba 1.5 Large
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
AL
Jamba 1.5 Mini
AI21 Labs
AC
Qwen3.5 2B
Alibaba Cloud / Qwen Team
NV
Llama 3.1 Nemotron 70B
NVIDIA
AN
Claude Sonnet 3
Anthropic
GO
Google
Gemini Diffusion
MA
Codestral 22B
Mistral AI
FAQ
Common questions about Jamba 1.5 Large.
When was Jamba 1.5 Large released?
Jamba 1.5 Large's default version was released on Aug 22, 2024.
How much does Jamba 1.5 Large cost?
No official standard PAYG price is currently available for Jamba 1.5 Large.
Who created Jamba 1.5 Large?
Jamba 1.5 Large was created by AI21 Labs.
What is the context window for Jamba 1.5 Large?
The default version has a 256K token context window.
Is Jamba 1.5 Large open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer Jamba 1.5 Large?
No provider offering is currently linked to the default version.
What models should I compare Jamba 1.5 Large with?
Nearby ranked alternatives include Claude Sonnet 3, Llama 3.1 Nemotron 70B, Qwen3.5 2B.