AI2API Host BenchmarksEstimated
Olmo 3.1 32b Instruct — API Providers & Speed Matrix
Modelled throughput, TTFT latency and prompt-cache pricing estimates across cloud hosting endpoints, derived from official list prices and public benchmarks.
Olmo 3.1 32b Instruct is a proprietary model served through AI2's official API. Third-party hosting is not available — the matrix below covers the official endpoint only. See the AI2 provider page for details.
Fastest provider
50 t/s
Lowest latency (TTFT)
800 ms P50
Best price
$1 / $3
Blended Pricing Workload Calculator
Switch between standard conversational ratios, agentic caching loops, and heavy RAG workloads.
| Provider & Host | Hardware Stack | Output Speed (TPS) | Latency TTFT (P50) | Input Price ($/1M) | Output Price ($/1M) | Cache Read ($/1M) | Blended Price ($/1M) | SLA |
|---|---|---|---|---|---|---|---|---|
AI2Official | Official cloud API | 50 t/s | 800 ms (1.12 s p90) | $1 | $3 | $0.1 | $1.5 | 99.99% |
Figures are modelled estimates based on published list prices and public throughput benchmarks — not measured on live endpoints. Verify current pricing and terms with each host before committing.