Inkling (batch) 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.
CompareInkling (batch)GLM 5.2
| Model | Providers | Best uptime | Fastest p50 | Best p99 | Throughput | Context | Cheapest $/Mtok |
|---|---|---|---|---|---|---|---|
| Inkling (batch) | 0/1 | — | — | — | — | 524K | $1.00 / $4.05 Together |
| GLM 5.2 | 23/31 | 100% Ambient | 644ms Together | 3.67s Cloudflare | 98 tps BaseTen | 1.0M | $0.419 / $1.32 Novita |
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.