This model is deprecated. We still benchmark its performance, but less often: every 18 hours instead of every 6.
AI21 Labs has launched a newer release, Jamba 1.6 Large. We suggest considering it instead.
Jamba 1.5 Large API Provider Benchmarking & Analysis
This analysis is intended to support you in choosing the best API provider of Jamba 1.5 Large for your use-case.
Lowest Time per Task
Time per Intelligence Index task (minutes)
Total 1 provider
Lowest Cost per Task
Cost per Intelligence Index task
Total 1 provider
Jamba 1.5 Large is available through Amazon.
Please see the models page for Jamba 1.5 Large for details of the model and its intelligence compared to other models.
Pricing
Cost per Intelligence Index Task: Jamba 1.5 Large
Pricing: Cache Hit, Input, and Output: Jamba 1.5 Large
Output Speed vs. Cost per Task: Jamba 1.5 Large
Speed
Average of the single-request and multi-turn agentic workloads measured
Output Speed: Jamba 1.5 Large
Latency
Average of the single-request and multi-turn agentic workloads measured
Time to First Answer Token: Jamba 1.5 Large
Reliability
Share of requests the endpoint failed, across all the single-request and multi-turn agentic workloads measured
Endpoint Error Rate: Jamba 1.5 Large
Key Comparison Metrics & API Features
Frequently Asked Questions
Common questions about Jamba 1.5 Large providers
Jamba 1.5 Large is available through 1 API provider: Amazon. Each provider offers different performance characteristics and pricing.
Jamba 1.5 Large is currently available through 1 API provider that we benchmark and track.
The most affordable provider for Jamba 1.5 Large by blended price is Amazon ($2.60 per 1M tokens). Blended price uses a 7:2:1 cache hit/input/output token ratio.
The provider with the lowest input token pricing for Jamba 1.5 Large is Amazon ($2.00 per 1M input tokens).
The provider with the lowest output token pricing for Jamba 1.5 Large is Amazon ($8.00 per 1M output tokens).
The only provider of Jamba 1.5 Large supports function calling (tool use).
When choosing a provider for Jamba 1.5 Large, consider: time per task (how quickly the provider completes an Intelligence Index task), latency (for interactive applications requiring quick first responses), pricing (for cost-sensitive workloads), and API features like JSON mode or function calling.
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.
For information about Jamba 1.5 Large's intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview