Jamba 1.5 Mini
Jamba 1.5 Mini is the world's first production-grade Mamba-based model, combining SSM and Transformer architectures for a 256K context window and high efficiency. It works with 9 languages and can handle various writing and analysis tasks as well as or better than similar small models. This model uses less computer memory and works faster with longer texts than previous designs. Read their announcement to learn more.
- Input / output price
- $0.20 / $0.40 per 1M
- Context
- 256K tokens
- Released
- Aug 22, 2024
Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
Providers
One provider serves this model, priced per 1M tokens after gateway discounts.
| Provider | Input | Output |
|---|---|---|
ConcentrateRetiring concentrate/jamba-1-5-mini | $0.20/M | $0.40/M |
Pricing
USD per 1M tokens on Concentrate, after gateway discounts.
- Input
- $0.20 per 1M
- Output
- $0.40 per 1M
Cost by volume
Total cost from 0 to 1T tokens.
Throughput and latency
30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.
Output speed
Higher is better1.4tokens/sacross providers
Response latency
Lower is better0.7sacross providers
Benchmarks
9 published scores from 2 sources, each linked to where it was published.
Published scores
| Benchmark | Score | Source | Published |
|---|---|---|---|
| BFCLhuggingface.co | 80.6% | huggingface.co | Aug 22, 2024 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| ARC-Challengehuggingface.co | 85.7% | huggingface.co | Aug 22, 2024 |
| GPQAhuggingface.co | 32.3% | huggingface.co | Aug 22, 2024 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| GSM8Khuggingface.co | 75.8% | huggingface.co | Aug 22, 2024 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| MMLUhuggingface.co | 69.7% | huggingface.co | Aug 22, 2024 |
| MMLU-Prohuggingface.co | 42.5% | huggingface.co | Aug 22, 2024 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| ArenaHardhuggingface.co | 46.1% | huggingface.co | Aug 22, 2024 |
| LMArena EloLMArena | 1240 Elo · #178 of 187 | LMArena | Nov 18, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| TruthfulQAhuggingface.co | 54.1% | huggingface.co | Aug 22, 2024 |
Apps
Use Jamba 1.5 Mini in the tools you already run. Each guide points the app at the Respan gateway.
Setup guides for more apps are in the integration docs.
Jamba 1.5 Mini FAQ
Short answers, built from the data on this page.
Jamba 1.5 Mini is a model from AI21 Labs, released on Aug 22, 2024. Jamba 1.5 Mini is the world's first production-grade Mamba-based model, combining SSM and Transformer architectures for a 256K context window and high efficiency. It works with 9 languages and can handle various writing and analysis tasks as well as or better than similar small models. This model uses less computer memory and works faster with longer texts than previous designs. Read their announcement to learn more.
On the Respan gateway, Jamba 1.5 Mini costs $0.20 per 1M input tokens and $0.40 per 1M output tokens on Concentrate, after gateway discounts.
Jamba 1.5 Mini is served by Concentrate.
Jamba 1.5 Mini accepts up to 256K tokens of context.
Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "jamba-1.5-mini". To set it up with a coding agent, copy the agent setup prompt at the top of this page.
Jamba 1.5 Mini has 9 published benchmark scores, including BFCL 80.6%, ARC-Challenge 85.7%, and GSM8K 75.8%. Each score links to where it was published; the data is collected by Respan.
Certified where it counts.
Built to meet the security and privacy standards that enterprise and healthcare teams require.
ISO 27001
The internationally recognized standard for information security management.
SOC 2
Secure, compliant management of your data across all of our systems.
GDPR
Operated under GDPR, the world's strictest standard for data privacy.
HIPAA
HIPAA compliant, with a BAA available for healthcare teams.