01.d'AI phare commercial modèle founded par Kai-Fu Lee, renowned pour d'avant-garde chinois-English bilingual performances.
Technical Specifications
- Provider
- 01.AI
- Category
- flagship
- Release Date
- 2024-05
- Batch API Discount
- 50% off async batch
- Consumer Subscription
- API Pay-as-you-go
- 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)
- yi-large
- Supported SDK & API Protocol
- 01.AI REST API (OpenAI-Compatible)
- Lifecycle & Deprecation Status
- Legacy Stable (Upgrade path available in 01.AI lineup)
- Production Rate Limits (RPM & TPM)
- 5,000 – 15,000 RPM (Production Tier) · 800,000 – 2,000,000 TPM
- Long-Context Pricing Tier (>128K / >200K)
- Flat rate ($2.5/1M in) across full 33K window
- Prompt Cache Write & TTL Policy
- Cached input at $0.25/1M 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
- API Prompt Engineering & RAG Distillation
- Multimodal Tokenization Billing
- Text BPE (~4 chars/token)
- Weights Precision & Quantization
- Cloud-Hosted Proprietary (FP8 / BF16 Tensor Core Cluster)
- Minimum GPU VRAM Requirement
- Zero Local VRAM Required (100% Serverless Cloud API)
- Supported Inference Engines
- Managed 01.AI Cloud API
- System Card & Safety Framework
- 01.AI Production Safety & Alignment Verified
- Enterprise Compliance (SOC2 / HIPAA / ZDR)
- SOC2 Type II · GDPR · Zero Data Retention (ZDR) & HIPAA BAA Available on Enterprise Tier
Yi-Large Cost, Context, Hardware & API Integration
For single-user chat, a $20/mo subscription caps your bill below this API volume.
Break-even point: ~83 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 Yi-Large:
Benchmark Scores & 6-Axis Capability Radar
- GPQA Diamond
- 52%
- MMLU-Pro
- 76.5%
- HumanEval
- 83.5%
- Chatbot Arena Elo
- 1290pts
Strengths
- Outstanding bilingual chinois-English cross-lingual traduction et compréhension
- Excellent suivi des instructions et équilibré d'entreprise communication ton
- élevé placement sur mondial Chatbot Arena rankings upon launch dans 2024
Limitations & Trade-offs
- fenêtre de contexte limité à 32K tokens par rapport à newer 1M token modèles
- plus expensive tarification palier que newer léger market entrants
Editorial Assessment
un jalon bilingual phare qui demonstrated haut de gamme-palier chinois-English linguistic parity.
Best for: Cross-border bilingual d'entreprise communication, traduction, et élevé-qualité chinois prose
Compare Yi-Large
Frequently Asked Questions about Yi-Large
How much does the Yi-Large API cost per 1M tokens?+
Yi-Large by 01.AI is priced at $2.5 per 1M input tokens and $2.5 per 1M output tokens. With prompt caching enabled, cached input tokens cost $0.25 per 1M tokens, and asynchronous Batch API requests receive a 50% discount.
Should I use a $20/month subscription or the Yi-Large 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 Yi-Large's context window?+
Yi-Large features a 33K tokens context window, which equals approximately 24,576 English words or ~66 standard single-spaced pages in a single prompt. Its maximum output generation per turn is 4,096 tokens.
Can I run Yi-Large locally on my own GPU (Open Weights)?+
No, Yi-Large is a proprietary closed-weights model hosted by 01.AI. It cannot be downloaded for local GPU execution and must be accessed via 01.AI's official API or cloud platform.
Does 01.AI train on data sent to the Yi-Large API, and is commercial use allowed?+
API payloads are excluded from model training by default. License tier: Proprietary Commercial API (01.AI Terms). Full commercial ownership of generated outputs. Supported deployment channels include: 01.AI Cloud API & Enterprise Endpoints.
How does Yi-Large perform on coding and reasoning benchmarks?+
Yi-Large achieves a composite Intelligence Index of 79/100, scoring N/A% on SWE-bench Verified, 52% on GPQA Diamond, 76.5% on MMLU-Pro, and 1290 pts on Chatbot Arena Elo.
What is Yi-Large best used for?+
Yi-Large is best suited for: Cross-border bilingual d'entreprise communication, traduction, et élevé-qualité chinois prose. Assessment: un jalon bilingual phare qui demonstrated haut de gamme-palier chinois-English linguistic parity.
AI Glossary & Architecture Concepts
View full glossary →Key machine learning concepts and benchmarks relevant to Yi-Large:
L'unité textuelle de base traitée par un modèle linguistique, représentant généralement 3 à 4 caractères ou environ 0,75 mot. Par exemple, une phrase courante est découpée en plusieurs jetons.
Une suite de tests standardisés permettant d'évaluer et de comparer objectivement les performances des modèles d'IA sur des tâches ciblées (code avec SWE-bench, mathématiques avec AIME, etc.).
Le nombre maximal de jetons qu'un modèle peut traiter simultanément (entrée et sortie comprises). Une fenêtre de 1 000 000 jetons permet d'analyser environ 750 000 mots en une seule requête.
La capacité d'un LLM à déterminer quand une action externe est requise et à générer des arguments structurés pour invoquer des API, calculatrices ou bases de données avant de poursuivre.
Un standard ouvert créé par Anthropic permettant aux agents d'IA de se connecter de façon uniforme aux systèmes de fichiers locaux, aux environnements de développement et aux API tierces.
Une optimisation tarifaire et technique conservant les états d'attention des préfixes de prompts récurrents, réduisant les coûts d'entrée de 50 à 90 % tout en abaissant la latence.
Les scores de benchmarks, tarifs par token et limites évoluent rapidement. Vérifiez toujours les spécifications actuelles sur la documentation officielle du fournisseur.