alto-velocidad codificación specialist desarrollado para autónomo test generación, terminal herramienta bucles, y rápido refactorización un través de 256K contexto.
Technical Specifications
- Provider
- Cohere
- Category
- open-source
- Release Date
- 2026-06
- Batch API Discount
- 50% off async batch
- Consumer Subscription
- Free / Self-Hosted
- Reasoning Effort Control
- Configurable (Low / Med / High)
- 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)
- north-mini-code
- Supported SDK & API Protocol
- OpenAI-Compatible REST / vLLM / SGLang / HuggingFace TGI
- Lifecycle & Deprecation Status
- Active GA (Guaranteed support through 2028+)
- 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 $0.04/1M 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
- 12 GB VRAM (4-bit Quantized) · 43 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
North Mini Code Cost, Context, Hardware & API Integration
Pay-as-you-go API is cheaper for this volume (saves $3.80/mo vs $20 flat plan).
Break-even point: ~617 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 North Mini Code:
Benchmark Scores & 6-Axis Capability Radar
- SWE-bench Verified
- 45%
- GPQA Diamond
- 55%
- MMLU-Pro
- 78%
- HumanEval
- 90%
- Terminal-Bench
- 40%
- AIME
- 68%
- Long-Context Reasoning
- 80%
- Chatbot Arena Elo
- 1320pts
Strengths
- Snappy 125 tokens/sec generación velocidad optimizado para IDE autocomplete y diffs
- Expansive 256K ventana de contexto para ingesting completo multifarchivo software projects
- de pesos abiertos bajo permissive license para offline propietario code development
Limitations & Trade-offs
- Trails larger 100B+ modelos en bleeding-perimetral competitivo programación
- texto-solo sin nativo visual UI mockup comprensión
Editorial Assessment
de Cohere dedicado codificación companion bringing rápido, confiable code síntesis un desarrolladores.
Best for: desarrollador IDE copilots, automatizado unit test suites, y rápido terminal CLI codificación agentes
Compare North Mini Code
Frequently Asked Questions about North Mini Code
How much does the North Mini Code API cost per 1M tokens?+
North Mini Code by Cohere is priced at $0.2 per 1M input tokens and $0.6 per 1M output tokens. With prompt caching enabled, cached input tokens cost $0.04 per 1M tokens, and asynchronous Batch API requests receive a 50% discount.
Should I use a $20/month subscription or the North Mini Code 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 North Mini Code's context window?+
North Mini Code 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 16,384 tokens.
Can I run North Mini Code locally on my own GPU (Open Weights)?+
Yes, North Mini Code (Confidential (~20B)) releases open weights that can be self-hosted locally or on private cloud GPUs using vLLM, Ollama, SGLang, or llama.cpp.
Does Cohere train on data sent to the North Mini Code 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 North Mini Code perform on coding and reasoning benchmarks?+
North Mini Code achieves a composite Intelligence Index of 47/100, scoring 45% on SWE-bench Verified, 55% on GPQA Diamond, 78% on MMLU-Pro, and 1320 pts on Chatbot Arena Elo.
What is North Mini Code best used for?+
North Mini Code is best suited for: desarrollador IDE copilots, automatizado unit test suites, y rápido terminal CLI codificación agentes. Assessment: de Cohere dedicado codificación companion bringing rápido, confiable code síntesis un desarrolladores.
Cohere Family Lineage, Routing Tiers & Upgrade Path
Step down to a lighter sibling for high-volume routing or step up to Cohere's flagship reasoning tier:
Command A Plus
Command A Reasoning
Command A Translate
Command A Vision
Command A
Aya Vision 32B
AI Glossary & Architecture Concepts
View full glossary →Key machine learning concepts and benchmarks relevant to North Mini Code:
La unidad básica de texto que procesa un modelo de lenguaje, que normalmente equivale a 3 o 4 caracteres o aproximadamente 0,75 palabras. Por ejemplo, una frase típica se divide en varios tokens.
Un conjunto estandarizado de pruebas para evaluar y comparar objetivamente las capacidades de distintos modelos de IA en tareas como programación (SWE-bench) o matemáticas avanzadas (AIME).
La cantidad máxima de tokens que un modelo puede considerar a la vez, incluyendo tanto la entrada que lee como la salida que genera. Una ventana de 1.000.000 de tokens puede procesar unas 750.000 palabras en una sola petición.
Un modelo de IA entrenado para invertir cómputo adicional en pensar y validar hipótesis lógicas antes de responder, diseñado para problemas complejos de ingeniería y matemáticas.
Una técnica de razonamiento paso a paso donde el modelo genera pensamientos intermedios antes de formular la respuesta final, mejorando radicalmente la resolución de problemas matemáticos y lógicos.
La capacidad de un modelo de detectar la necesidad de una función externa y emitir argumentos JSON estructurados para ejecutar API, búsquedas web o consultas a bases de datos.
Las puntuaciones de benchmarks, precios por token y límites de tasa evolucionan rápidamente. Verifique siempre las especificaciones actuales en la documentación oficial del proveedor.