Llama 3 8B Lunaris vs GLM 5.2
One line per model: the best value available from any of its providers at each point, which is what a caller routing to the healthy endpoint would see.
CompareLlama 3 8B LunarisGLM 5.2
| Model | Providers | Best uptime | Fastest p50 | Best p99 | Throughput | Context | Cheapest $/Mtok |
|---|---|---|---|---|---|---|---|
| Llama 3 8B Lunaris | 3/3 | 100% Novita | 147ms DeepInfra | 839ms DeepInfra | 73 tps DeepInfra | 8K | $0.040 / $0.050 DeepInfra |
| GLM 5.2 | 26/31 | 100% Ambient | 279ms Friendli | 2.56s Cloudflare | 100 tps Friendli | 1.0M | $0.433 / $1.36 Novita |
Measured 3m ago. Each figure is the best available across that model's providers.
History
Availability
Best uptime available from any provider. Axis starts at 90%; it expands to 0 when a model falls below.
Time to first token
Fastest p50 available from any provider. Logarithmic axis.
Throughput
Best median tokens per second available.