Claude Opus 4.8 (batch) vs Claude Opus 4.8 (Fast)
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.
CompareClaude Opus 4.8 (batch)Claude Opus 4.8 (Fast)
| Model | Providers | Best uptime | Fastest p50 | Best p99 | Throughput | Context | Cheapest $/Mtok |
|---|---|---|---|---|---|---|---|
| Claude Opus 4.8 (batch) | 0/1 | — | — | — | — | 1.0M | $2.50 / $12.50 Anthropic |
| Claude Opus 4.8 (Fast) | 1/1 | 100% Anthropic | 723ms Anthropic | 4.28s Anthropic | 113 tps Anthropic | 1.0M | $10.00 / $50.00 Anthropic |
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.