Measured by PPQ · last 7 days (Nov 11 – Nov 18)
Availability is the share of requests that succeeded, hour by hour over the last 72 hours (higher is better). First response is how long until the model starts sending its answer (lower is better). Speed is how many tokens per second arrive from sending the request until the last token, the wait for the first token included (higher is better).
100% chats ran inside our enclave router. PayPerQ can’t see the content of your queries and each reply also carries a receipt proving which provider and model we sent it to. How it works →
anthropic/claude-fable-5.2 | 100% | 3.4 s About 1 in 10 wait over 24.8 s | 93 tok/s About 1 in 10 slower than 73 tok/s | 81% $2.15/M input vs $8.44 list · 74% cost savings |
anthropic/claude-opus-5.5 | 99.9% | 3.1 s About 1 in 10 wait over 12 s | 92 tok/s About 1 in 10 slower than 57 tok/s | 82% $1.22/M input vs $4.22 list · 71% cost savings |
anthropic/claude-sonnet-5.5 | 99.9% | 2.7 s About 1 in 10 wait over 14.2 s | 118 tok/s About 1 in 10 slower than 82 tok/s | 89% $0.48/M input vs $2.11 list · 77% cost savings |
deepseek-v4.1-flash-1017-ultrafast | 100% | 0.9 s About 1 in 10 wait over 2.4 s | 392 tok/s About 1 in 10 slower than 130 tok/s | 97% $0.13/M input vs $2.53 list · 94% cost savings |
deepseek/deepseek-v4-pro-0813 | 100% | 1.5 s About 1 in 10 wait over 3.1 s | 93 tok/s About 1 in 10 slower than 48 tok/s | 85% $0.10/M input vs $0.12 list · 10% cost savings |
deepseek/deepseek-v4.1-flash-1017 | 99.7% | 1 s About 1 in 10 wait over 3 s | 171 tok/s About 1 in 10 slower than 69 tok/s | 95% $0.021/M input vs $0.32 list · 93% cost savings |
google/gemini-3.1-pro-preview | 99.9% | 3 s About 1 in 10 wait over 8.6 s | 84 tok/s About 1 in 10 slower than 58 tok/s | 75% $0.68/M input vs $2.11 list · 67% cost savings |
google/gemini-3.7-flash | 99.9% | 2.4 s About 1 in 10 wait over 5 s | 110 tok/s About 1 in 10 slower than 77 tok/s | 38% $0.52/M input vs $0.79 list · 34% cost savings |
google/gemini-3.8-flash | 99.9% | 2.4 s About 1 in 10 wait over 4.8 s | 93 tok/s About 1 in 10 slower than 55 tok/s | 64% $0.37/M input vs $0.87 list · 57% cost savings |
google/gemini-4-argon | 99.9% | 5.4 s About 1 in 10 wait over 19.6 s | 43 tok/s About 1 in 10 slower than 25 tok/s | 76% $0.58/M input vs $2.11 list · 72% cost savings |
google/gemini-4-carbon | 99.9% | 7.8 s About 1 in 10 wait over 33.9 s | 43 tok/s About 1 in 10 slower than 17 tok/s | 78% $0.55/M input vs $2.11 list · 73% cost savings |
moonshotai/kimi-k3 | 99.9% | 2.1 s About 1 in 10 wait over 5.8 s | 41 tok/s About 1 in 10 slower than 25 tok/s | 93% $0.50/M input vs $3.17 list · 84% cost savings |
moonshotai/kimi-k3.1-pro | 99.9% | 1.8 s About 1 in 10 wait over 4.7 s | 58 tok/s About 1 in 10 slower than 34 tok/s | 96% $0.29/M input vs $2.11 list · 86% cost savings |
openai/gpt-6-astra | 98.7% | 3.9 s About 1 in 10 wait over 14.8 s | 34 tok/s About 1 in 10 slower than 20 tok/s | 87% $2.33/M input vs $10.55 list · 77% cost savings |
openai/gpt-6.1-sol | 99.7% | 2.8 s About 1 in 10 wait over 11.7 s | 34 tok/s About 1 in 10 slower than 18 tok/s | 95% $0.22/M input vs $2.11 list · 89% cost savings |
private/glm-5-3 | 99.9% | 1.7 s About 1 in 10 wait over 3.6 s | 92 tok/s About 1 in 10 slower than 43 tok/s | 94% $0.56/M input vs $1.90 list · 70% cost savings |
venice/abliteration-abliterated-model-large-flash | 100% | 3.2 s About 1 in 10 wait over 5.8 s | 106 tok/s About 1 in 10 slower than 45 tok/s | 99% $0.15/M input vs $1.32 list · 88% cost savings |
venice/abliteration-abliterated-model-large-v2 | 99.9% | 2.2 s About 1 in 10 wait over 6.1 s | 90 tok/s About 1 in 10 slower than 30 tok/s | 97% $0.40/M input vs $3.17 list · 87% cost savings |
z-ai/glm-5.3 | 100% | 1.5 s About 1 in 10 wait over 5.2 s | 92 tok/s About 1 in 10 slower than 43 tok/s | 97% $0.31/M input vs $1.48 list · 78% cost savings |
z-ai/glm-5.3-prime | 100% | 2.3 s About 1 in 10 wait over 6.1 s | 132 tok/s About 1 in 10 slower than 44 tok/s | 98% $0.44/M input vs $2.22 list · 79% cost savings |
$2.15/M input vs $8.44 list · 74% cost savings
$1.22/M input vs $4.22 list · 71% cost savings
$0.48/M input vs $2.11 list · 77% cost savings
$0.13/M input vs $2.53 list · 94% cost savings
$0.10/M input vs $0.12 list · 10% cost savings
$0.021/M input vs $0.32 list · 93% cost savings
$0.68/M input vs $2.11 list · 67% cost savings
$0.52/M input vs $0.79 list · 34% cost savings
$0.37/M input vs $0.87 list · 57% cost savings
$0.58/M input vs $2.11 list · 72% cost savings
$0.55/M input vs $2.11 list · 73% cost savings
$0.50/M input vs $3.17 list · 84% cost savings
$0.29/M input vs $2.11 list · 86% cost savings
$2.33/M input vs $10.55 list · 77% cost savings
$0.22/M input vs $2.11 list · 89% cost savings
$0.56/M input vs $1.90 list · 70% cost savings
$0.15/M input vs $1.32 list · 88% cost savings
$0.40/M input vs $3.17 list · 87% cost savings
$0.31/M input vs $1.48 list · 78% cost savings
$0.44/M input vs $2.22 list · 79% cost savings
Measurements are best-effort: some requests are not timed. The ⓘ beside each model shows the share of successful streamed queries its times cover.