Capabilities
7-day heat trend
+7.6%Pricing breakdown
Typical 3:1 output-to-input mix, per 1M tokens
Estimated monthly cost by workload
Market position
- Cheaper than 7% of tracked models
- Faster than 84% of tracked models
- Efficiency rank: #1008 of 1105
Best suited for
General-purpose text generation, chat, summarization and content workloads where broad capability and low cost matter most.
About jamba-large
Jamba Large is the stable AI21 hosted alias for the current higher-capability Jamba Large 1.7 API line.
jamba-large is a Text model from AI21 (US). HotON.ai tracks it at $2.00 per 1M input tokens and $8.00 per 1M output tokens, with a 256K-token context window, ~166 tokens/sec throughput and 99.4% availability. Its composite efficiency score is 87/100 at an estimated $0.008 per successful task.
Compare jamba-large
Related market news
Frequently asked questions
How much does jamba-large cost per 1M tokens?+
jamba-large is tracked at $2.00 per 1M input tokens and $8.00 per 1M output tokens. A typical 3:1 output-to-input workload blends to roughly $6.50 per 1M tokens. Figures are illustrative demo data.
What is jamba-large best for?+
General-purpose text generation, chat, summarization and content workloads where broad capability and low cost matter most.
How fast is jamba-large?+
jamba-large delivers about 166 tokens/sec with 99.4% tracked availability, suitable for latency-sensitive, real-time applications.
Is jamba-large cheaper than other AI models?+
Within the HotON.ai tracked set, jamba-large is cheaper than 7% of models on input price and ranks #1008 of 1105 by overall efficiency.
Related models
Pricing is real (via the TestKey catalog, updated daily). Quality (Arena Elo) is real where the model is ranked on LMArena. Speed, availability and efficiency are modeled estimates.