AI21 LabsReleased on Aug 22, 2024

Jamba 1.5 Large: API Pricing, Context Window & Benchmarks

Jamba 1.5 Large is a language model from AI21 Labs, released in August 2024.

State-of-the-art hybrid SSM-Transformer instruction following foundation model, offering superior long context handling, speed, and quality.

Input
Text
Output
Text

Jamba 1.5 Large benchmarks

Rankings

Quality Tracker

Jamba 1.5 Large Performance Across Datasets

Scores sourced from the model's scorecard, paper, or official blog posts

LLM Stats Logollm-stats.com - Tue Jul 28 2026
Notice missing or incorrect data?

Jamba 1.5 Large pricing

Providers

Jamba 1.5 Large starts at $2.00 per million input tokens and $8.00 per million output tokens via Bedrock. See all 2 providers below with their per-token pricing, latency, throughput, and modality support.

ProviderInput $/MOutput $/MContext in / outTTFT p50 / p95 sOutput avg / p5 c/sSuccess 7dModalities in / out
Bedrock logoBedrock
$2.00$8.00256.0K/256.0K
/0.50
100/
/
Google logoGoogle
$2.00$8.00256.0K/256.0K
/0.30
42/
/

Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests. Success is calculated from completed versus failed requests over the trailing seven days.

Loading chart...
Loading chart...
Loading chart...

Jamba 1.5 Large model size

Jamba 1.5 Large has 398 billion parameters. See how it compares to other models in the same parameter range.

Parameters
398B
Frontier (200B+)
398B
1B7B70B405B

Jamba 1.5 Large context window

Input and output token limits for Jamba 1.5 Large, plus how it ranks on long-context understanding.

InputOutput
256Ktokens
256Ktokens
385 pages of text
256K
8K128K1M

Jamba 1.5 Large API

Available from the model provider

Jamba 1.5 Large has an official provider API. It is not currently routed through the LLM Stats gateway.

Read the official API documentation

Jamba 1.5 Large latency

Jamba 1.5 Large time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.

Jamba 1.5 Large examples

Recent arena outputs from Jamba 1.5 Large, picked from the highest-ranked matchups.

Jamba 1.5 Large license

Jamba 1.5 Large is released under the Jamba Open Model License license, which restricts commercial use, has 398.0B parameters, has a knowledge cutoff of March 2024.

License
Jamba Open Model License
Non-commercial
Parameters
398.0B
Knowledge cutoff
March 2024

Jamba 1.5 Large resources

Official sources for Jamba 1.5 Large: api documentation, official launch post, model weights.

Jamba 1.5 Large vs other models

The most-compared alternatives to Jamba 1.5 Large are Gemini 1.5 Flash, Qwen3 VL 4B Thinking, Phi 4 Mini. Open any pair side-by-side for benchmarks, pricing, context, and latency.

Models like Jamba 1.5 Large

Models ranked just above and below Jamba 1.5 Large by LLM Stats score.

 

Gemini 1.5 Flash

Score pending
 

Qwen3 VL 4B Thinking

Score pending
 

Phi 4 Mini

Score pending
 

Grok-1.5

Score pending
 

Phi-3.5-MoE-instruct

Score pending
 

Mistral Small 3.1 24B Base

Score pending

FAQ

Common questions about Jamba 1.5 Large.

When was Jamba 1.5 Large released?

Jamba 1.5 Large was released on August 22, 2024 by AI21 Labs. This is the official Jamba 1.5 Large release date tracked on LLM Stats.

How much does Jamba 1.5 Large cost?

Jamba 1.5 Large pricing starts at $2.00 per million input tokens and $8.00 per million output tokens via Bedrock, the lowest price among tracked providers.

Is Jamba 1.5 Large available via API?

Yes, Jamba 1.5 Large is available via API. See the official documentation for authentication and endpoint details. It is served by 2 providers tracked on LLM Stats.

How big is Jamba 1.5 Large?

Jamba 1.5 Large has 398 billion parameters. It ships as an open-weight model, so you can download and run it on your own hardware.

Who created Jamba 1.5 Large?

Jamba 1.5 Large was created by AI21 Labs.

What is the license for Jamba 1.5 Large?

Jamba 1.5 Large is released under the Jamba Open Model License license. This is an open-source / open-weight license that permits self-hosting.

What is the knowledge cutoff date for Jamba 1.5 Large?

Jamba 1.5 Large has a knowledge cutoff of March 2024, meaning it was trained on data up to that point and may not know about events after it.

What is Jamba 1.5 Large latency?

Jamba 1.5 Large p95 time to first token is 0.30 seconds via Google over the trailing 7 days. Lower time to first token means the model begins responding sooner for chat, agents and API workloads.

Where can I use Jamba 1.5 Large?

Jamba 1.5 Large is available through 2 providers including Bedrock, Google.

Where is the Jamba 1.5 Large paper or technical report?

Jamba 1.5 Large has a paper or technical report available at https://www.ai21.com/blog/announcing-jamba-model-family. Use that source for architecture, training, release and evaluation details.

What models should I compare Jamba 1.5 Large against?

Common Jamba 1.5 Large comparisons include Jamba 1.5 Large vs Gemini 1.5 Flash, Jamba 1.5 Large vs Qwen3 VL 4B Thinking, Jamba 1.5 Large vs Phi 4 Mini. Compare them side by side for benchmark scores, pricing, context window, latency and API availability.