Jamba Large 1.7
AI21 · released Jul 2, 2025 · ai21labs/AI21-Jamba-Large-1.7
- Type
- Open weightsCustom licence
- Params
- 399B
- Context
- 256K
about 192K words of context · download allowed, licence restricts use
Our take
Written Aug 3, 2026Jamba Large 1.7 is a 398.6-billion-parameter text model from AI21 with a 256,000-token request limit and a custom restricted licence. It has broad benchmark coverage with stable measurements, though only two hosts carry it and at identical rates.
Pick this for long-context text tasks that need a quarter-million tokens in one request, or for coding workloads where its measured coding score is the strongest of its six tracked categories. Use it when you are comfortable with AI21's own hosting at 34 tokens per second. Skip it if you need price competition between providers, a permissive licence, or strong mathematics performance — its maths score trails its coding score by a wide margin.
The case for it
- Broad benchmark coverage with stable, reproducible measurement: six Arena benchmarks measured twice within two days, all within 0.1% score drift.
- Largest measured context window in this data set, at 256,000 tokens.
- Coding benchmark is the strongest of its six measured categories, ahead of its next-best by a 67.3-point margin.
The case against it
- Mathematics is the weakest of its six measured categories, trailing its coding score by a 67.3-point gap.
- No price competition between its two hosts, which charge identical rates.
- Restricted licence limits commercial flexibility — not Apache, MIT, or standard commercial terms.
How good is it?
IntelligencePuzzles, maths, exam questions
Arena Text (overall)128th of 143 · 1289.2
CodingWriting and fixing code on its own
Arena Coding129th of 143 · 1312.2
Arena Coding is the only board that has scored it for this.
AgenticPlanning, calling tools, staying on task
Nobody we watch has scored Jamba Large 1.7 for this. We would take the rating from Arena Agent (IPS).
WritingWe do not rate this
Two boards come close and neither tests writing: Arena Creative Writing asks people which of two replies they prefer, and LiveBench Language tests whether a model understood a passage. So we show where Jamba Large 1.7 placed and give it no mark out of five.
These tests check whether a model follows instructions — a precondition for all the work above, but not a measure of how well that work is done, which is why they get no rating.
Every published score for this model6 scoresEvery figure we hold, from 6 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Can you run it yourself?
- Fits in memory
- weights load entirely on the card
- Spills to system RAM
- some weights offload; much slower
- Too large
- will not load even with offload
- est
- size is calculated; the verdict could change by 10%
GeForce RTX 4090 · 24 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Apple M1 Pro (16-core GPU) · 32 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Comfortable fit
Apple M3 Ultra (80-core GPU) · 512 GB
Room to spare. 123.2 GB spare means a 10% error in the size would not change the answer.
Memory use by level
Against a 24 GB card.
All 3 sizes here are calculated, not measured. We hold no measured file for this model, so each size comes from the parameter count and every verdict above inherits that uncertainty.
Check against your own machine → · All 71 devices, with every size →
Or rent it from someone else
Cheapest of 2 live listings. Picked at the widest standard context we hold, within one quantisation slice, so the numbers beside it are a price one host actually charges.
- per 1M tokens
- $2.00 in / $8.00 out
- Context served
- 256K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $2.00 / $8.00 | 256K | not measured | Unknown | Unknown | Unknown |
| AI21fp8 | $2.00 / $8.00 | 256K | 53 tok/s | No | Yesunknown period | Unknown |
Across the 2 listings we hold: 1 say they do not train on prompts, 0 say they do and 1 do not say. 0 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouter | ✓ | ✓ | ✗ |
| AI21fp8 | ✓ | ✓ | ✗ |
Tool calling: 2 of 2 listings say yes. JSON output: 2 of 2 listings say yes. Strict schema: 0 of 2 listings say yes, 2 say no.
When we formed this view
Dates behind this page
Prices last checked 6h ago
What we do not know about this model yet
- We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 2 listings do not say whether they train on prompts.
- We hold no cached-input rate for any of its listings.
Licence and identifiers
What the licence allowsCustom licence, what it allows commercially, and the identifiers you need to pull this model — its Hugging Face repo, our slug and a machine-readable card.
Licence
Custom licence
This model ships custom license terms that don't map to a known template. We haven't parsed them, so commercial use, redistribution and derivatives are unverified — review the original terms before shipping.
Identifiers
- Hugging Face
- ai21labs/AI21-Jamba-Large-1.7
- Modality record
- text->text
- Catalogue slug
- ai21-jamba-large-1-7