AI21 Labs: Models Intelligence, Performance & Price

AI21 Labs
AI21 Labs

Analysis of AI21 Labs's models across key metrics including quality, price, output speed, latency, context window & more. This analysis is intended to support you in choosing the best model provided by AI21 Labs for your use-case.

Most Intelligent

Updated
#1
Jamba 1.7 Large
Jamba 1.7 Large
5
#2
Jamba 1.6 Large
Jamba 1.6 Large
5
#3
Jamba 1.6 Mini
Jamba 1.6 Mini
3

Intelligence index

Total 3 models

Fastest

#1
Jamba 1.6 Mini
Jamba 1.6 Mini
183 t/s
#2
Jamba 1.7 Large
Jamba 1.7 Large
57 t/s
#3
Jamba 1.6 Large
Jamba 1.6 Large
54 t/s

Output speed

Total 3 models

Lowest Price

#1
Jamba 1.6 Mini
Jamba 1.6 Mini
$0.22
#2
Jamba 1.7 Large
Jamba 1.7 Large
$2.60
#3
Jamba 1.6 Large
Jamba 1.6 Large
$2.60

Blended price (per 1M tokens)

Total 3 models

AI21 Labs offers 3 models, each with different intelligence, performance, and pricing characteristics. Below is a comparison of the key metrics across models.

  • For intelligence, the top models on AI21 Labs are Jamba 1.7 Large (5), Jamba 1.6 Large (5), Jamba 1.6 Mini (3).
  • For output speed, the fastest models are Jamba 1.6 Mini (183 t/s), Jamba 1.7 Large (57 t/s), Jamba 1.6 Large (54 t/s).
  • For latency, Jamba 1.6 Mini (0.82s), Jamba 1.7 Large (1.39s), Jamba 1.6 Large (1.43s) offer the lowest time to first answer token.
  • For pricing, Jamba 1.6 Mini ($0.22), Jamba 1.7 Large ($2.60), Jamba 1.6 Large ($2.60) offer the lowest blended prices per 1M tokens.
  • For context window size, Jamba 1.7 Large (256k), Jamba 1.6 Large (256k), Jamba 1.6 Mini (256k) support the largest context windows on AI21 Labs.
  • Jamba 1.6 Mini offers both the fastest output and best pricing, making it attractive for throughput-sensitive and cost-conscious applications. Jamba 1.7 Large leads in intelligence for tasks that require the highest quality.

Highlights

Updated

Intelligence

Artificial Analysis Intelligence Index · Higher is better

Speed

Output tokens per second · Higher is better

Price

USD per 1M tokens (blended) · Lower is better

Intelligence Evaluations

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR
Estimate (independent evaluation forthcoming)
Reasoning models are indicated by a lightbulb icon

Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Intelligence Evaluations

Intelligence evaluations measured independently by Artificial Analysis · Higher is better
GDPval-AA v2

Agentic real-world work tasks, (Elo-500)/2000

No data available
𝜏³-Banking

Agentic tool use

No data available
Terminal-Bench v2.1

Agentic coding & terminal use

No data available
SciCode

Coding

Humanity's Last Exam

Reasoning & knowledge

GPQA Diamond

Scientific reasoning

CritPt

Physics reasoning

AA-Omniscience Accuracy

Knowledge

AA-Omniscience Non-Hallucination Rate

1 - hallucination rate

AA-LCR

Long context reasoning

AA-BriefcaseNew

Agentic knowledge work, Elo

No data available
AutomationBench-AANew

Agentic SaaS workflows

No data available
Harvey LAB-AANew

Legal agentic work, criterion pass rate

No data available
EnterpriseOps-Gym-AANew

Agentic business operations

No data available
IFBench

Instruction following

APEX-Agents-AA

Long-horizon agentic tasks

No data available
ITBench-AA

Kubernetes incident root-cause analysis

No data available
MMMU-Pro

Visual reasoning

No data available
Reasoning models are indicated by a lightbulb icon.

While model intelligence generally translates across use cases, specific evaluations may be more relevant for certain use cases.

Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Intelligence vs. Price

Blended at 7:2:1 (cache-input-output) · USD per 1M tokens (blended)
Most attractive quadrant
Reasoning models are indicated by a lightbulb icon.

While higher intelligence models are typically more expensive, they do not all follow the same price-quality curve.

Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Price per token, shown in USD per million tokens. Price is a blend of cache hit, input, and output token prices using the selected ratio (default 7:2:1 cache-input-output).

The blended cache price shown here uses cache hit price only. Other caching costs differ by provider:

  • Anthropic: charges a separate cache write fee, with different rates for 5-minute and 1-hour TTLs (1-hour TTL is more expensive).
  • Google (Vertex/Gemini): charges a per-hour cache storage fee in addition to cache hit pricing. Some providers also use tiered pricing for prompts above 200K tokens.
  • OpenAI, DeepSeek, others: typically charge only cache hit pricing with no write or storage fee.

See Prompt Caching for the full breakdown.

Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).

Context Window

Context Window

Context window: tokens limit · Higher is better
Reasoning models are indicated by a lightbulb icon

Larger context windows are relevant to RAG (Retrieval Augmented Generation) LLM workflows which typically involve reasoning and information retrieval of large amounts of data.

Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).

Pricing

Intelligence vs. Price

Blended at 7:2:1 (cache-input-output) · USD per 1M tokens (blended)
Most attractive quadrant
Reasoning models are indicated by a lightbulb icon.

While higher intelligence models are typically more expensive, they do not all follow the same price-quality curve.

Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Price per token, shown in USD per million tokens. Price is a blend of cache hit, input, and output token prices using the selected ratio (default 7:2:1 cache-input-output).

The blended cache price shown here uses cache hit price only. Other caching costs differ by provider:

  • Anthropic: charges a separate cache write fee, with different rates for 5-minute and 1-hour TTLs (1-hour TTL is more expensive).
  • Google (Vertex/Gemini): charges a per-hour cache storage fee in addition to cache hit pricing. Some providers also use tiered pricing for prompts above 200K tokens.
  • OpenAI, DeepSeek, others: typically charge only cache hit pricing with no write or storage fee.

See Prompt Caching for the full breakdown.

Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).

Performance Summary

Output Speed vs. Price

Output speed: output tokens per second · USD per 1M tokens (blended)
Most attractive quadrant
Reasoning models are indicated by a lightbulb icon.

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Price per token, shown in USD per million tokens. Price is a blend of cache hit, input, and output token prices using the selected ratio (default 7:2:1 cache-input-output).

Speed

Measured by Output Speed (tokens per second)

Output Speed

Output tokens per second · Higher is better
Reasoning models are indicated by a lightbulb icon

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).

Latency

Measured by Time (seconds) to First Token

Latency: Time To First Token

Seconds to first token received · Lower is better
Reasoning models are indicated by a lightbulb icon

Time to first token received, in seconds, after API request sent. For reasoning models which share reasoning tokens, this will be the first reasoning token. For models which do not support streaming, this represents time to receive the completion.

Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).

End-to-End Response Time

Seconds to output 500 tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed

End-to-End Response Time vs. Price

End-to-end response time: end-to-end seconds to output 500 tokens · USD per 1M tokens (blended)
Most attractive quadrant

Price per token, shown in USD per million tokens. Price is a blend of cache hit, input, and output token prices using the selected ratio (default 7:2:1 cache-input-output).

Seconds to receive a 500 token response. Key components:

  • Input time: Time to receive the first response token
  • Thinking time (only for reasoning models): Time reasoning models spend outputting tokens to reason prior to providing an answer. Amount of tokens based on the average reasoning tokens across a diverse set of 60 prompts (methodology details).
  • Answer time: Time to generate 500 output tokens, based on output speed

Figures represent median (P50) measurement over the past 72 hours to reflect sustained changes in performance.

Further Analysis
AI21 Labs logo
Jamba 1.7 Large
256k
Open
5*
$2.60
59
1.44
9.98
--
Model
Provider
AI21 Labs logo
Jamba 1.6 Large
256k
Open
5*
$2.60
55
1.43
10.57
--
Model
Provider
AI21 Labs logo
Jamba 1.6 Mini
256k
Open
3*
$0.22
183
0.81
3.54
--
Model
Provider

Key definitions

Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Time to first token received, in seconds, after API request sent. For reasoning models which share reasoning tokens, this will be the first reasoning token. For models which do not support streaming, this represents time to receive the completion.

Price per token, shown in USD per million tokens. Price is a blend of cache hit, input, and output token prices using the selected ratio (default 7:2:1 cache-input-output).

Price per token generated by the model (received from the API), represented as USD per million Tokens.

Price per token included in the request/message sent to the API, represented as USD per million Tokens.

Metrics are 'live' and are based on the past 72 hours of measurements, measurements are taken 8 times a day for single requests and 2 times per day for parallel requests.

Frequently Asked Questions

Common questions about AI21 Labs

AI21 Labs offers 3 models that we track: Jamba 1.7 Large, Jamba 1.6 Large, and Jamba 1.6 Mini.

The most intelligent model available on AI21 Labs is Jamba 1.7 Large with an Intelligence Index score of 5.

The fastest model on AI21 Labs by output speed is Jamba 1.6 Mini at 183.1 tokens per second.

The model with the lowest time to first answer token on AI21 Labs is Jamba 1.6 Mini at 0.82s. Lower latency means faster initial response time.

The most affordable model on AI21 Labs by blended price is Jamba 1.6 Mini at $0.22 per 1M tokens (7:2:1 cache hit/input/output ratio).

Prices on AI21 Labs vary up to 12x across models, from $0.22 per 1M tokens for Jamba 1.6 Mini to $2.60 per 1M tokens for Jamba 1.6 Large.

2 of 3 models on AI21 Labs support JSON mode for structured output.

Yes, all 3 models on AI21 Labs support function calling (tool use).

Yes, all 3 models on AI21 Labs are open weight models.

Yes, provider performance can vary over time due to infrastructure changes, load balancing, and updates. We continuously benchmark all providers and display historical performance trends in the "Over Time" charts.

When choosing a model on AI21 Labs, consider: intelligence (for quality-sensitive tasks), output speed (for throughput-intensive tasks), latency (for interactive applications requiring quick first responses), pricing (for cost-sensitive workloads), and features like context window size, JSON mode, or function calling support.