Jamba Instruct
Jamba Instruct is AI21 Labs's language model with a 256K context window and up to 8K output tokens, available from 2 providers, starting at $0.5 / 1M input and $0.7 / 1M output. An instruction-tuned variant of AI21's Jamba hybrid SSM-Transformer model, optimized for following complex user directives.
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Pricing by Provider
US Dollar ($)
Per 1M tokens
| Provider | Standard | |
|---|---|---|
| Input $ / 1M | Output $ / 1M | |
| $0.5 | $0.7 | |
| $0.5 | $0.7 | |
Cost Calculator
US Dollar ($)
Preset:
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Jamba 1.7 Large | 256K | $2.00 | $8.00 | Available | |
| Jamba 1.5 Large | 256K | $2.00 | $8.00 | Deprecating | |
| Jamba 1.5 Mini | 256K | $0.200 | $0.400 | Deprecating | |
| Jamba 1.6 Large | — | 256K | $2.00 | $8.00 | Available |
| Jamba 1.7 Mini | — | 256K | $0.200 | $0.400 | Available |
| Jamba 1.6 Mini | — | 256K | $0.200 | $0.400 | Available |
| Jamba 1.5 | — | 256K | $0.200 | $0.400 | Available |
| Jamba Instruct | — | 256K | $0.500 | $0.700 | Current |
| Jamba Reasoning 3B | — | — | — | — | Available |