AI21 Labs · Official-source model record
AI21-Jamba-Mini-1.7
Jamba
Publisher-sourced inventory. Specifications come from official documentation and model cards. “Not documented” means we have no verified value. This inventory is separate from our editorial reviews.
Coverage & sources ↗Current catalog answers
What to know about AI21-Jamba-Mini-1.7
AI-compiled from linked model documentation. This is a catalog reference, not an independent performance review. Catalog checked October 23, 2026.
Which AI21-Jamba-Mini-1.7 does this page describe?
AI21-Jamba-Mini-1.7 is a model record from AI21 Labs in the Jamba family. Source
A separate version identifier is not documented in this record; the model name alone does not establish which snapshot a service runs.
How can you access AI21-Jamba-Mini-1.7?
The catalog documents API and Open weights access for AI21-Jamba-Mini-1.7. Source
As of the catalog check, this version was marked deprecated. Source Check the linked lifecycle information before starting a new integration.
For API use, confirm the exact model identifier, your account and region, and the endpoint's current limits in the linked documentation. An API listing does not establish access through a consumer subscription.
Open weights means the model weights are distributed for use under their stated terms. It does not establish a hosted API, an open-source license, or a hardware requirement. This record documents API access separately.
What are AI21-Jamba-Mini-1.7's context and output limits?
The publisher reports the context window as 256K tokens. Source We retain the publisher's notation and qualifiers; no exact token count or hosted serving allowance is inferred from it.
A separate maximum-output value is not established in this record. The context or input figure should not be used as an output allowance.
Context, input and output limits describe different constraints. Do not add the figures together to infer a larger window. Check the endpoint's accounting for conversation history, system instructions, tools, media and generated tokens; a documented maximum is not a guarantee of answer quality or a measured usable capacity.
What dates are documented for AI21-Jamba-Mini-1.7?
Knowledge cutoff: August 22, 2024. Source This labels the documented knowledge boundary; it is not a promise that every earlier fact is known or correct. The source labels this “- Knowledge cutoff date: August 22nd, 2024.”
Retrieval or web tools can supply newer information at run time. That does not change the model's recorded training or knowledge dates, and this record does not establish that a particular endpoint includes those tools.
What license is recorded for AI21-Jamba-Mini-1.7?
The recorded license label is jamba-open-model-license. Source
Read the linked license and associated use terms for this exact version before redistribution, commercial deployment or fine-tuning. A label alone does not establish every permission, restriction or obligation, and it does not determine the terms of a separate hosted service.
What distinguishes AI21-Jamba-Mini-1.7?
These details come from the linked publisher material for this model. Reported capabilities and training descriptions are publisher statements, not independent test results.
- Hybrid architecture
- Joint Attention and Mamba hybrid with a documented 256K context window; 1.7 emphasizes grounding and instruction following. Source
- Supported languages
- Supports English, Spanish, French, Portuguese, Italian, Dutch, German, Arabic and Hebrew. Source
- Deployment requirements
- The default BF16/vLLM setup supports 200K-token prompts on 2×80GB A100 GPUs; the card describes additional GPUs for the full 256K context. Source
What is documented about the AI21-Jamba-Mini-1.7 checkpoint?
This evidence refers to ai21labs/AI21-Jamba-Mini-1.7 at recorded revision e8986f3aa2e7ce119329cde6120238f8802f92cb, checked October 23, 2026. Repository metadata
Safetensors metadata records 51,570,323,328 stored parameters. This is a stored-weight count, not necessarily the number activated per token, a download size or a GPU-memory requirement. Repository metadata
Recorded architecture class: JambaForCausalLM. Repository metadata
Repository access gate: auto. This records the repository's gate setting when checked; licensing and use terms still apply. Repository metadata
Read the retrieved model card for setup and qualifications. Model card
Keep the exact version in view
Other Jamba models from AI21 Labs.
These are separate records in the same publisher family. A shared family name does not establish equal capabilities or interchangeable licenses.
AI21-Jamba-Large-1.7
API · Open weights · 256,000 context tokens
AI21-Jamba2-3B
Open weights · 256,000 context tokens
AI21-Jamba2-Mini
API · Open weights · 256,000 context tokens
AI21-Jamba-Large-1.5
API · Open weights
AI21-Jamba-Large-1.6
API · Open weights
AI21-Jamba-Mini-1.5
API · Open weights
The documented record
Specifications, with their sources.
A missing value remains unknown. Input limits, output limits and the total context window are separate measurements.
- Publisher
- AI21 LabsSource ↗
- Family
- JambaSource ↗
- Version
- Not documented
- Availability
- DeprecatedSource ↗
- Access
- API · Open weightsSource ↗
- Inputs
- Not documented
- Outputs
- Not documented
- Context window
- 256K tokensSource ↗
- Maximum input
- Not documented
- Maximum output
- Not documented
- Knowledge cutoff
- Aug 22, 2024- Knowledge cutoff date: August 22nd, 2024 · day precisionSource ↗
- Training-data cutoff
- Not documented
- Training completed
- Not documented
- Release date
- Not documented
- License
- jamba-open-model-licenseSource ↗
- Input price / 1M tokens
- Not documented
- Output price / 1M tokens
- Not documented
Read this with the numbers.
Official publisher model repository; listed status confirms a catalog entry, not a verified hosted API service. The model card could not be retrieved anonymously; only public publisher metadata was used. Remaining fields need verification. API lifecycle is separate from downloadable weights. The shared vendor overview gives inconsistent knowledge/training recency statements, so no family-wide cutoff is copied into this version. Publisher repository evidence (2026-10-23): Published architecture metadata: JambaForCausalLM. Published safetensors metadata counts 51,570,323,328 stored parameters; this is not an active-parameter count for mixture-of-experts models. Repository access metadata is auto; access gating does not establish license permissions.
Model identifiers and aliases 2
ai21labs/AI21-Jamba-Mini-1.7jamba-mini-1.7-2025-08
Follow the evidence
Official sources.
- Jamba foundation models ↗docs.ai21.com
- AI21-Jamba-Mini-1.7 — official model card ↗huggingface.co
- AI21-Jamba-Mini-1.7: official publisher repository metadata ↗huggingface.co
- AI21-Jamba-Mini-1.7: publisher model card at pinned revision ↗huggingface.co