Processing or generating 2,500 words (approximately 3,333 tokens) with AI21 Jamba 1.5 Large ranges from $0.001667 (cached input) to $0.0267 (full generation).
You send 2,500 words as prompt context, documentation, or background knowledge.
AI21 Jamba 1.5 Large drafts a complete 2,500 words article, chapter, or code module.
2,000 words input prompt + 500 words output reply.
| Model | Provider | Input Cost (2,500 words) | Cached Input Cost | Output Cost (2,500 words) | Context Limit |
|---|---|---|---|---|---|
| AI21 Jamba 1.5 Large (Current) | ai21 | $0.006666 | $0.001667 | $0.0267 | 256,000 |
| GPT-5.6 Sol | openai | $0.016 | $0.0016 | $0.096 | 1,050,000 |
| GPT-5.6 Cyber | openai | $0.04 | $0.004 | $0.24 | 1,050,000 |
| GPT-5.5 Standard | openai | $0.016 | $0.0016 | $0.096 | 512,000 |
| GPT-5.5 Pro | openai | $0.096 | $0.0096 | $0.576 | 512,000 |
| o3-pro (Frontier Reasoning) | openai | $0.064 | $0.0064 | $0.256 | 1,000,000 |
For AI21 Jamba 1.5 Large (tiktoken_cl100k tokenizer), 2,500 words is approximately 3,333 tokens (an average ratio of 1.33 tokens per word in English). Code, technical vocabulary, and non-English scripts will have higher token densities.
Sending 2,500 words as input costs $0.006666 (or $0.001667 with prompt caching). Generating 2,500 words as output costs $0.0267. Output tokens are more expensive because autoregressive token generation requires significantly more computation per token.
Yes! If your input text is part of a repeated context, prompt caching saves 50% to 90% (costing $0.001667). For non-urgent asynchronous batch processing, 24-hour batch queues provide a flat 50% discount across all tokens (costing $0.003333 for input, $0.0133 for output).
At an average human reading speed of 250 words per minute, 2,500 words takes approximately 10 minutes to read. In contrast, AI21 Jamba 1.5 Large can process or generate this text in seconds.