ZeroReader
ZeroReader provides micropayment access to embedding, reranking, sentiment analysis, image generation, and language models.
Trust signal
4 of 4 pillars
coverage 100%
Pillars
Signals
Evidence tiers, not an endorsement · trust model v0.1.0 (provisional) · CDP-lane settlement only (D3) · Trust API coming soon
On-chain traction
ERC-8004 agent registry
Not found in the ERC-8004 agent registry. This is the default state — absence is not a negative signal.
Identity & classification
Settlement volume
USDC settled on-chain · monthly
as of Jul 12, 2026
Endpoints(29)
BGE-M3 (Multilingual) — Best multilingual embedding model. 100+ languages.
BGE Small EN v1.5 — Fast, lightweight English embeddings.
Qwen3 Embedding 0.6B — Compact embedding model from Qwen.
IBM Granite 4.0 Micro — Ultra-cheap, fast responses. Best for simple tasks.
Llama 3.2 1B — Smallest Llama. Fastest, cheapest.
BGE Reranker — Re-rank search results for better relevance.
DistilBERT Sentiment — Sentiment analysis (positive/negative).
BGE Large EN v1.5 — High-quality English embeddings.
GLM 4.7 Flash — Zhipu AI model. Strong multilingual.
GPT-OSS 20B (OpenAI) — OpenAI's open-source 20B model.
Llama 3.2 3B — Good balance of speed and quality for simple tasks.
Llama 3.1 8B (Fast) — Best value. Fast inference, solid quality.
Mistral 7B — European open-source model. Good at structured output.
M2M100 1.2B (Translation) — 100-language translation model.
Qwen3 30B (MoE, 3B active) — 30B MoE model with only 3B active params. Fast + smart.
Gemma 3 12B (Google) — Google's open model. Good at reasoning.
Mistral Small 3.1 24B — Strong mid-size European model.
SEA-LION 27B — Southeast Asian languages specialist.
Llama 4 Scout 17B — Latest Llama 4 architecture. 17B with 16 experts.
Llama 3.2 11B Vision — Vision + text model. Can understand images.
MeloTTS (Text-to-Speech) — Text to speech synthesis.
Qwen 2.5 Coder 32B — Code generation specialist. Excellent for programming tasks.
QwQ 32B (Reasoning) — Reasoning-focused model from Qwen.
Llama 3.3 70B (Fast) — Flagship open-source LLM. Best quality on CF Workers AI.
Whisper (Speech-to-Text) — OpenAI Whisper. Transcription in 90+ languages.
FLUX.1 Schnell — Fast image generation (~2s). Good for prototyping.
GPT-OSS 120B (OpenAI) — OpenAI's largest open-source model.
Whisper Large v3 Turbo — Latest Whisper. Better accuracy, faster.
DeepSeek R1 32B (Reasoning) — Chain-of-thought reasoning. Best for math/logic/code.