Jamba Instruct: Intelligence, Performance & Price Analysis
Analysis of AI21 Labs's Jamba Instruct and comparison to other AI models across key metrics including quality, price, performance (tokens per second & time to first token), context window & more. Click on any model to compare API providers for that model. For more details including relating to our methodology, see our FAQs.
Base version (Jamba v0.1) is open-source, but this instruct-tuned variant is API-only with no direct model release available
Comparison Summary
Intelligence:
Jamba Instruct is of lower intelligence compared to average, with Artificial Analysis Intelligence Index of 15.
Price:Speed:Latency:Context Window:Jamba Instruct has a smaller context windows than average, with a context window of 260k tokens.
Highlights
Intelligence
Artificial Analysis Intelligence Index; Higher is better
Loading chart...
Speed
Output Tokens per Second; Higher is better
Loading chart...
Price
USD per 1M Tokens; Lower is better
Loading chart...
Parallel Queries:
Prompt Length:
Jamba Instruct Model Details
Comparisons to Jamba Instruct
- Jamba Instruct
gpt-oss-120B (high)- gpt-oss-20B (high)
- GPT-4.1
- GPT-5 (high)
- GPT-5 (minimal)
- o3
Llama 4 Maverick
Gemini 2.5 Pro- Gemini 2.5 Flash (Reasoning)
Claude 4 Sonnet Thinking
Magistral Small
DeepSeek V3.1 (Non-reasoning)- DeepSeek R1 0528
- DeepSeek V3.1 (Reasoning)
Grok 4
Solar Pro 2 (Reasoning)
MiniMax M1 80k
Llama Nemotron Super 49B v1.5 (Reasoning)
Kimi K2
EXAONE 4.0 32B (Reasoning)
GLM-4.5
Qwen3 235B 2507 (Reasoning)
Further details
R1 1776
Nova Premier
Phi-4
Granite 3.3 Instruct 8B
Reka Flash 3
DeepHermes 3 - Llama-3.1 8B Preview
Aya Expanse 32B
OpenChat 3.5 (1210)
LFM 40B
DBRX Instruct
Llama 3.1 Tulu3 405B
Arctic Instruct
Yi-Large