OpenAI compatible API · Attested · Public status
Cloudflare Workers AI performance
Review measured TTFT, effective throughput, uptime, and sampled model routes for Cloudflare Workers AI on TrustedRouter using metadata-only production probes.
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
Cloudflare Workers AIcloudflare-workers-ai
31 samples
Continuously sampled provider performance. TrustedRouter reports unsupported route and probe-configuration rows separately from provider downtime. Prompt and output content is not stored.
| p50 TTFT | 1375 ms |
|---|---|
| p95 TTFT | 6015 ms |
| Effective throughput | — |
| Uptime | 100.00% |
Measured model routes
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| mistralai/mistral-small-3.1-24b-instruct | 594 ms | — | 100.00% | — | 1 |
| meta-llama/llama-3.2-1b-instruct | 707 ms | — | 100.00% | — | 2 |
| openai/gpt-oss-20b | 1022 ms | — | 100.00% | — | 2 |
| openai/gpt-oss-120b | 1035 ms | — | 100.00% | — | 2 |
| qwen/qwen3-30b-a3b-fp8 | 1134 ms | — | 100.00% | — | 1 |
| z-ai/glm-4.7-flash | 1211 ms | — | 100.00% | — | 3 |
| google/gemma-4-26b-a4b-it | 1369 ms | — | 100.00% | — | 3 |
| meta-llama/llama-3.1-8b-instruct-fp8 | 1375 ms | — | 100.00% | — | 2 |
| meta-llama/llama-3.2-3b-instruct | 1457 ms | — | 100.00% | — | 1 |
| meta-llama/llama-3.3-70b-instruct-fp8-fast | 1680 ms | — | 100.00% | — | 3 |
| qwen/qwen3.8-27b | 2683 ms | — | 100.00% | — | 1 |
| qwen/qwen2.5-coder-32b-instruct | 2728 ms | — | 100.00% | — | 3 |
| ibm-granite/granite-4.0-h-micro | 2745 ms | — | 100.00% | — | 3 |
| aisingapore/gemma-sea-lion-v4-27b-it | 3095 ms | — | 100.00% | — | 1 |
| nvidia/nemotron-3-120b-a12b | 3456 ms | — | 100.00% | — | 1 |
| moonshotai/kimi-k3 | 5457 ms | — | 100.00% | — | 2 |