provider

api.onhub.ai

5 listed endpoints (+15 delisted) · free reliability snapshot (may be up to 24h old)

endpoints

+15 delisted

avg trust score

79.1

ecosystem avg 54.3

avg 30-day uptime

100.0%

ecosystem avg 55.0%

avg latency (EU)

1183 ms

measured from a single EU vantage point; includes network round-trip distance to the endpoint

price band

$0.002–$0.4

USDC per call

networks

Base

B 5

At a glance

api.onhub.ai operates 5 listed x402 endpoints (plus 15 delisted, kept for history) across 1 network. 5 of them carry a letter grade, averaging 79.1 of 100 (above the ecosystem average of 54.3). Average 30-day uptime across the measured endpoints is 100.0% (above the ecosystem average of 55.0%). Advertised prices range from $0.002 to $0.4 USDC per call. Best-scored endpoint: /v1/chat/completions (grade B, 79.5).

Top endpoints by trust score

All endpoints

endpoint▼	grade▼	uptime 30d▼	conf.▼	price▼
/v1/chat/completionsText completion using the model selected in the request body.	B 79.5	100.0%	1.00	$0.002
/v1/searchGrounded Google Search answers with attributable HTTPS sources.	B 79.1	100.0%	1.00	$0.025
/v1/codeWrites and runs Python to compute or verify an answer, returning th…	B 79.1	100.0%	1.00	$0.015
/v1/placesGrounded local search over Google Maps places with ratings, address…	B 79.0	100.0%	1.00	$0.04
/v1/url-contextFetches up to 3 URLs and answers a question grounded in their conte…	B 79.0	100.0%	1.00	≤ $0.4

Recently delisted

endpoint▼	grade▼	uptime 30d▼	conf.▼	price▼
/v1/chat/completions/qwen2-5-coder-32b(delisted)Code generation and software engineering tasks. Model-specific route.	F 32.9	0.0%	0.89	—
/v1/chat/completions/granite-4-micro(delisted)Compact model for structured enterprise tasks.	F 32.9	0.0%	0.89	—
/v1/chat/completions/glm-4-7-flash(delisted)Fast multilingual dialogue and tool use.	F 32.9	0.0%	0.89	—
/v1/chat/completions/openai-gpt-oss-120b(delisted)Open-weight reasoning for deeper agent workflows.	F 32.9	0.0%	0.89	—
/v1/chat/completions/deepseek-r1-32b(delisted)Reasoning-focused generation for analytical tasks.	F 32.9	0.0%	0.89	—
/v1/chat/completions/nemotron-3-120b(delisted)Agentic reasoning and multi-agent workloads.	F 32.9	0.0%	0.89	—
/v1/chat/completions/qwen3-8-27b(delisted)Long-context multimodal reasoning and coding.	F 32.9	0.0%	0.89	—
/v1/chat/completions/llama-3-3-70b(delisted)Fast high-quality general-purpose text generation.	F 32.9	0.0%	0.89	—
/v1/chat/completions/meta-llama-3-2-1b(delisted)Low-latency lightweight instruction following.	F 32.9	0.0%	0.89	—
/v1/chat/completions/meta-llama-3-1-8b(delisted)Fast general-purpose text generation.	F 32.9	0.0%	0.89	—
/v1/chat/completions/mistral-small-3-1(delisted)Balanced text and vision generation with long context.	F 32.9	0.0%	0.89	—
/v1/chat/completions/llama-4-scout(delisted)Multimodal instruction following and vision reasoning.	F 32.9	0.0%	0.89	—
/v1/chat/completions/qwen3-30b(delisted)Efficient multilingual reasoning and instruction following.	F 32.9	0.0%	0.89	—
/v1/chat/completions/gemma-4-26b(delisted)Instruction following with reasoning and vision support.	F 32.9	0.0%	0.89	$0.003
/v1/chat/completions/openai-gpt-oss-20b(delisted)Fast open-weight reasoning for high-volume agent work.	F 32.9	0.0%	0.90	$0.002

Ranked by trust score. Grades are our independent measurement, recomputed daily; provider-supplied names and descriptions are unverified claims. Live re-probe and 90-day history via the paid API.