rapide, free-palier accessible modèle de langage offrant rapide response génération pour bulk traitement et entry-level automatisation.
Technical Specifications
- Provider
- Baidu
- Category
- lightweight
- Release Date
- 2024-03
- Batch API Discount
- Standard rate
- 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)
- ernie-speed
- Supported SDK & API Protocol
- OpenAI-Compatible REST / vLLM / SGLang / HuggingFace TGI
- Lifecycle & Deprecation Status
- Legacy Stable (Upgrade path available in Baidu 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)
- Free across full context window (only KV-cache VRAM scales)
- Prompt Cache Write & TTL Policy
- Automatic prefix KV-caching in vLLM / SGLang (0 cost)
- 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
- 5 GB VRAM (4-bit Quantized) · 17 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
ERNIE Speed Cost, Context, Hardware & API Integration
Open-weights or free-tier model: $0 API license cost when self-hosted.
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 ERNIE Speed:
Benchmark Scores & 6-Axis Capability Radar
- MMLU-Pro
- 64%
- HumanEval
- 72%
- Chatbot Arena Elo
- 1205pts
Strengths
- Free de charge sur Baidu Qianfan API pour registered développeurs
- sous-250ms initial token génération et rapide 175 tokens/sec débit
- Adequate précision pour standard texte résumé et sentiment balisage
Limitations & Trade-offs
- limité analytical profondeur sur complexe technique ou scientifique problems
- Max sortie token ceiling de 4096 tokens
Editorial Assessment
un coût-free, élevé-vitesse utility moteur ideal pour basic élevé-concurrency tâches.
Best for: Bulk texte classification, simple conversationnel routage, et zero-coût prototyping
Compare ERNIE Speed
Frequently Asked Questions about ERNIE Speed
How much does the ERNIE Speed API cost per 1M tokens?+
ERNIE Speed by Baidu is priced at $0 per 1M input tokens and $0 per 1M output tokens. With prompt caching enabled, cached input tokens cost $0 per 1M tokens, and asynchronous Batch API requests receive a 0% discount.
Should I use a $20/month subscription or the ERNIE Speed 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 ERNIE Speed's context window?+
ERNIE Speed features a 128K tokens context window, which equals approximately 96,000 English words or ~256 standard single-spaced pages in a single prompt. Its maximum output generation per turn is 4,096 tokens.
Can I run ERNIE Speed locally on my own GPU (Open Weights)?+
Yes, ERNIE Speed (Confidential / 8B Scale) releases open weights that can be self-hosted locally or on private cloud GPUs using vLLM, Ollama, SGLang, or llama.cpp.
Does Baidu train on data sent to the ERNIE Speed 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 ERNIE Speed perform on coding and reasoning benchmarks?+
ERNIE Speed achieves a composite Intelligence Index of 68/100, scoring N/A% on SWE-bench Verified, N/A% on GPQA Diamond, 64% on MMLU-Pro, and 1205 pts on Chatbot Arena Elo.
What is ERNIE Speed best used for?+
ERNIE Speed is best suited for: Bulk texte classification, simple conversationnel routage, et zero-coût prototyping. Assessment: un coût-free, élevé-vitesse utility moteur ideal pour basic élevé-concurrency tâches.
Baidu Family Lineage, Routing Tiers & Upgrade Path
Step down to a lighter sibling for high-volume routing or step up to Baidu's flagship reasoning tier:
AI Glossary & Architecture Concepts
View full glossary →Key machine learning concepts and benchmarks relevant to ERNIE Speed:
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.
L'architecture de réseau neuronal introduite en 2017 à la base des LLM modernes, utilisant l'auto-attention pour traiter tous les jetons en parallèle plutôt que séquentiellement.
Les scores de benchmarks, tarifs par token et limites évoluent rapidement. Vérifiez toujours les spécifications actuelles sur la documentation officielle du fournisseur.