Production-scale AI with Ray
Verdict: needs review · Last checked 2026-09-15
Quality score
6.4
Latency
82 ms
Uptime (30d)
96.7%
Region
GLOBAL
Payment
—
Supported models
llama
Baseline model pricing
upstream $ per 1M tokens · models.devWhat the underlying model providers charge. Compare against what the relay quotes on their site to spot markup.
| Family | Model | Input | Output | Context |
|---|---|---|---|---|
| Meta Llama | Muse Spark 1.3 | $1.25 | $4.25 | 1.0M |
| Muse Spark 1.3 Contributor | $0.100 | $0.200 | 1.0M |
Model authenticity analysis
MVP placeholder
Our authenticity probes are being built. Once live, this section will show whetherProduction-scale AI with Ray’s claimed models pass response-fingerprint checks against the upstream provider. See Methodology.