A
Jamba Large 1.7OPEN
Jamba Large 1.7 (Ai21): live API pricing, context window and the best open-source alternatives, tracked daily by olud.ai.
Prices update automatically — checked hourly against provider list prices.
Benchmarks & performance
Independent benchmark scores for Jamba Large 1.7, measured by Artificial Analysis. Higher is better.
About this model
Jamba Large 1.7 is an open-weight AI model by Ai21. You can download and self-host it for free; the prices below are hosted-API list prices, tracked hourly, for when you prefer convenience over self-hosting.
Frequently asked questions
What is Jamba Large 1.7?
Jamba Large 1.7 is an AI language model from Ai21. It is open-weight: you can download it and run it on your own hardware, for free. It scores 5.3 on the Artificial Analysis intelligence index.
Is Jamba Large 1.7 free?
The weights are free and open — you can self-host Jamba Large 1.7 and pay nothing per token. If you prefer a hosted API, list prices are $2 per million input tokens and $8 per million output tokens.
What is Jamba Large 1.7 good at?
Independent benchmarks from Artificial Analysis give it GPQA 39%, MMLU-Pro 57.7%, Humanity's Last Exam 3.8%, Long Context Reasoning 17.3%, LiveCodeBench 18.1%, SciCode 18.8%, MATH-500 60%, AIME 5.7%, AIME 2025 2.3%, IFBench 35.2%, τ²-Bench 13.5%, Terminal-Bench Hard 2.3%. It is particularly used for mathematical reasoning.
How fast is Jamba Large 1.7?
It generates about 56.4 tokens per second, with a median 0.87s delay before the first token. Measured independently by Artificial Analysis.
Can I self-host Jamba Large 1.7?
Yes. Jamba Large 1.7 has open weights, so you can download it and run it on your own GPU or server with tools like Ollama, vLLM or llama.cpp — with no per-token cost.