AI21 の Jamba 1.5 Mini は、超低遅延のリアルタイム対話、高速ルーティング、大量リクエスト処理向けに設計されたAIモデルです。256K のコンテキストウィンドウ、毎秒 120 トークンの生成速度、知能指数 39/100（1Mトークンあたり入力$0.2・出力$0.4）を実現しています。
Technical Specifications
- Provider
- AI21
- Category
- open-source
- Release Date
- 2024-08
- Batch API Discount
- 50% off async batch
- Consumer Subscription
- Free / Self-Hosted
- Reasoning Effort Control
- Fixed
- Structured Outputs
- Yes
- Output Modalities
- text
- Official Documentation
- Visit Official Docs ↗
Data Privacy, Licensing & Deployment Governance
Official Provider Release Intelligence, API Quotas & Agentic Specs
- Official API Model ID (SDK String)
- jamba-1-5-mini
- Supported SDK & API Protocol
- OpenAI-Compatible REST / vLLM / SGLang / HuggingFace TGI
- Lifecycle & Deprecation Status
- Legacy Stable (Upgrade path available in AI21 lineup)
- Production Rate Limits (RPM & TPM)
- Unlimited (Hardware-bound on self-hosted GPU) / 10,000 RPM Cloud · Unlimited local throughput / 10M+ TPM Managed Cloud
- Long-Context Pricing Tier (>128K / >200K)
- Flat rate ($0.2/1M in) across full 256K window
- Prompt Cache Write & TTL Policy
- Cached input at $0.05/1M tokens
- Computer Use & Browser GUI Agent
- API / CLI Tool-Use & DOM Agent ready (no raw pixel desktop click loop)
- MCP & Parallel Tool Calling
- Native MCP Client/Server ready · Parallel function calling · 100% Strict JSON Schema
- Web Search Grounding & Code Sandbox
- Supported via external Tavily/Exa Search & E2B/Docker Sandbox tools
- Fine-Tuning & Distillation Support
- Full Weights SFT, LoRA, QLoRA, DPO & GRPO RL (Unsloth / Axolotl / Llama-Factory)
- Multimodal Tokenization Billing
- Text BPE (~4 chars/token)
- Weights Precision & Quantization
- BF16 / FP16, FP8 Dynamic, INT4 AWQ / GPTQ, GGUF (Q4_K_M / Q8_0)
- Minimum GPU VRAM Requirement
- 32 GB VRAM (4-bit Quantized) · 112 GB VRAM (Native BF16)
- Supported Inference Engines
- vLLM, SGLang, Ollama, llama.cpp, TensorRT-LLM, HuggingFace TGI
- System Card & Safety Framework
- Open-Weights System Card + Customizable Guardrail Layer (Llama Guard / ShieldGemma)
- Enterprise Compliance (SOC2 / HIPAA / ZDR)
- 100% Air-Gapped On-Premises / Private VPC · Full HIPAA, GDPR & SOC2 Control
Jamba 1.5 Mini Cost, Context, Hardware & API Integration
Pay-as-you-go API is cheaper for this volume (saves $6.50/mo vs $20 flat plan).
Break-even point: ~741 requests/day equals $20/month.
Same Monthly Workload Cost Across Popular Reference Models
Live Prompt Paste Tokenizer & Cost Counter
Paste real system instructions, JSON schemas, or code to measure BPE token counts across tokenizers.
Hybrid Prompt Routing Cascade Simulator
Route routine queries to a fast lightweight model ($0.15/1M) and escalate only complex reasoning turns to Jamba 1.5 Mini:
Benchmark Scores & 6-Axis Capability Radar
- SWE-bench Verified
- 35.8%
- GPQA Diamond
- 44.2%
- MMLU-Pro
- 64%
- HumanEval
- 82%
- Humanity's Last Exam
- 4.8%
- Terminal-Bench
- 21.5%
- SciCode
- 22.8%
- LiveCodeBench
- 37.5%
- AIME
- 45%
- Long-Context Reasoning
- 72%
- Chatbot Arena Elo
- 1242pts
Strengths
- 256K のコンテキストウィンドウと最大 4K トークンの出力容量（SWE-bench Verified 35.8% · GPQA Diamond 44.2%）
- 毎秒 120 トークンの高速スループットと、初回トークン到達時間（TTFT）わずか 340ms の低遅延
- オープンウェイトモデル (52B (12B ))として vLLM・SGLang・Ollama を用いた自社GPUでのローカル運用が可能
Limitations & Trade-offs
- 非量子化のフル精度でローカル推論を行うには十分なGPU VRAM容量が必要です
- 極めて高度な専門科学の証明問題では、上位の大型推論特化モデルの方がより深い洞察を提供する場合があります
Editorial Assessment
知能指数 39/100、256K コンテキスト、毎秒 120 トークンの速度を兼ね備えた Jamba 1.5 Mini は、AI21 のラインナップにおいて非常に実用性の高い主力モデルです。
Best for: 超低遅延のリアルタイム対話、高速ルーティング、大量リクエスト処理、エンタープライズRAG基盤、スケーラブルな本番API統合に最適。
Compare Jamba 1.5 Mini
Frequently Asked Questions about Jamba 1.5 Mini
How much does the Jamba 1.5 Mini API cost per 1M tokens?+
Jamba 1.5 Mini by AI21 is priced at $0.2 per 1M input tokens and $0.4 per 1M output tokens. With prompt caching enabled, cached input tokens cost $0.05 per 1M tokens, and asynchronous Batch API requests receive a 50% discount.
Should I use a $20/month subscription or the Jamba 1.5 Mini pay-as-you-go API?+
A flat $20/month consumer subscription is predictable for daily interactive chat and manual coding. However, if you are building software, running automated workflows, or sending low-to-moderate volume with prompt caching enabled, the pay-as-you-go API is typically far more cost-effective and offers higher rate limits without manual UI caps.
How many words and pages fit in Jamba 1.5 Mini's context window?+
Jamba 1.5 Mini features a 256K tokens context window, which equals approximately 192,000 English words or ~512 standard single-spaced pages in a single prompt. Its maximum output generation per turn is 4,096 tokens.
Can I run Jamba 1.5 Mini locally on my own GPU (Open Weights)?+
Yes, Jamba 1.5 Mini (52B (12B active)) releases open weights that can be self-hosted locally or on private cloud GPUs using vLLM, Ollama, SGLang, or llama.cpp.
Does AI21 train on data sent to the Jamba 1.5 Mini API, and is commercial use allowed?+
100% Isolated when self-hosted on private GPUs or VPC. License tier: Open-Weights Research & Commercial License. Full commercial ownership of generated outputs. Supported deployment channels include: Self-Hosted GPU (vLLM / Ollama), Private VPC, or Managed Serverless API.
How does Jamba 1.5 Mini perform on coding and reasoning benchmarks?+
Jamba 1.5 Mini achieves a composite Intelligence Index of 39/100, scoring 35.8% on SWE-bench Verified, 44.2% on GPQA Diamond, 64% on MMLU-Pro, and 1242 pts on Chatbot Arena Elo.
What is Jamba 1.5 Mini best used for?+
Jamba 1.5 Mini is best suited for: 超低遅延のリアルタイム対話、高速ルーティング、大量リクエスト処理、エンタープライズRAG基盤、スケーラブルな本番API統合に最適。. Assessment: 知能指数 39/100、256K コンテキスト、毎秒 120 トークンの速度を兼ね備えた Jamba 1.5 Mini は、AI21 のラインナップにおいて非常に実用性の高い主力モデルです。
AI21 Family Lineage, Routing Tiers & Upgrade Path
Step down to a lighter sibling for high-volume routing or step up to AI21's flagship reasoning tier:
AI Glossary & Architecture Concepts
View full glossary →Key machine learning concepts and benchmarks relevant to Jamba 1.5 Mini:
The basic unit of text that a language model processes, typically representing about 3 to 4 English characters or roughly 0.75 words. For example, the sentence "Artificial intelligence is fast" breaks down into about 5 tokens.
A standardized evaluation suite used to objectively measure and rank an AI model's capabilities across specific tasks — such as SWE-bench Verified for software engineering, AIME for competitive math, or MMLU for general knowledge.
The maximum number of tokens a model can consider at once — both the input it reads and the output it writes. A 1,000,000-token context window can hold roughly 750,000 English words in a single request.
The ability of a language model to recognize when an external capability is needed and output structured JSON arguments to invoke external APIs, databases, or terminal commands. The runtime executes the tool and passes results back to the model.
An open standard created by Anthropic that allows AI applications and agents to connect seamlessly to local filesystems, development environments, and third-party APIs via standardized server interfaces.
A cost and latency optimization where inference providers store pre-computed attention states for repeated prompt prefixes. Reusing cached tokens typically slashes API input costs by 50% to 90% and cuts TTFT substantially.
Benchmark scores, token prices, and rate limits evolve rapidly as AI labs release model updates. Always verify current specifications and pricing on the official provider documentation.