AI Relay Compare

Novita AI

Verdict: needs review · Last checked 2026-09-15
Quality score
6.5
Get this relay →
Latency
294 ms
Uptime (30d)
96.7%
Region
GLOBAL
Payment

Supported models

deepseekqwen

Baseline model pricing

upstream $ per 1M tokens · models.dev

What the underlying model providers charge. Compare against what the relay quotes on their site to spot markup.

FamilyModelInputOutputContext
DeepSeekDeepSeek V4 Flash Vision Exp$0.150$0.6001M
DeepSeek V4 Flash$0.150$0.6001M
Alibaba QwenQwen3.8 Flash$0.150$0.4701M
Qwen3.8 Max$2.00$6.001M

Model authenticity analysis

MVP placeholder

Our authenticity probes are being built. Once live, this section will show whetherNovita AI’s claimed models pass response-fingerprint checks against the upstream provider. See Methodology.