Measured performance

Provider & model performance

Measured time-to-first-token, time-to-first-byte, effective throughput, and uptime for every LLM provider and model TrustedRouter routes to — continuously sampled, not vendor-claimed.

Last updated 2026-08-04T20:27:57Z

Video leaderboard

Continuously sampled from TrustedRouter's monitor regions using a rolling benchmark set of up to 10,000 samples. Time-to-first-token (TTFT), time-to-first-byte (TTFB), effective throughput, and success rate come from real streaming requests, not vendor claims. Completion rate shows the end-user result. Provider availability excludes failures owned by TrustedRouter, customers, or route configuration, while still reporting those failures under their actual owner. Capacity acceptance measures requests not rejected for provider overload. Effective throughput is provider-reported output tokens divided by complete request time, so buffered delivery cannot inflate the result. Unsupported route and probe-configuration rows are reported separately and do not count as provider downtime. No prompt or output content is ever stored.

Providers

Ranked by provider-attributed availability, then p50 time-to-first-token across all of a provider's models (41 providers · 7671 availability samples · 0 sustained throughput samples). Providers below the evidence floor remain visible as warming, but do not receive a rank.

#ProviderModels CompletionProvider availabilityWithin deadline Capacity acceptedp50 TTFTp95 TTFT Effective throughputFailure ownerConfig excludedSamples
1 mistral 8 100.00% 100.00% 100.00% 100.00% 2258 ms 3224 ms 209
2 friendli 6 100.00% 100.00% 100.00% 100.00% 2461 ms 3438 ms 168
3 grok 4 100.00% 100.00% 100.00% 100.00% 2556 ms 3252 ms 209
4 baseten 8 100.00% 100.00% 100.00% 100.00% 2717 ms 4341 ms 152
5 openai 21 100.00% 100.00% 100.00% 100.00% 2813 ms 4949 ms 201
6 siliconflow 7 100.00% 100.00% 100.00% 100.00% 3166 ms 5484 ms 56
7 minimax 6 100.00% 100.00% 100.00% 100.00% 3232 ms 4294 ms 209
8 lightning 12 100.00% 100.00% 100.00% 100.00% 3426 ms 4882 ms 190
9 thinkingmachines 1 100.00% 100.00% 100.00% 100.00% 3535 ms 4150 ms 110
10 anthropic 10 100.00% 100.00% 100.00% 100.00% 3598 ms 6702 ms 185
11 fireworks 11 99.52% 99.52% 99.52% 100.00% 3074 ms 8629 ms provider 1 209
12 gmi 4 99.39% 99.39% 99.39% 100.00% 3932 ms 5608 ms provider 1 164
13 kimi 11 99.04% 99.04% 99.04% 100.00% 2846 ms 4622 ms provider 2 209
14 wafer 5 99.04% 99.04% 99.04% 99.04% 3361 ms 4435 ms provider 2 209
15 nebius 24 98.96% 98.96% 98.96% 100.00% 2494 ms 6035 ms provider 2 192
16 venice 12 98.09% 98.09% 98.09% 99.52% 2799 ms 7497 ms provider 4 209
17 deepseek 3 98.09% 98.09% 98.09% 100.00% 2814 ms 3743 ms provider 4 209
18 zai 11 98.09% 98.09% 96.65% 100.00% 3519 ms 11102 ms provider 4 209
19 cerebras 6 97.61% 97.61% 97.61% 97.61% 2377 ms 4714 ms provider 5 209
20 parasail 25 96.81% 96.81% 96.81% 97.34% 2972 ms 6062 ms provider 6 12 probe_config_error 188
21 crusoe 14 96.65% 96.65% 96.65% 100.00% 2577 ms 4478 ms provider 7 209
22 phala 1 94.55% 94.55% 94.55% 100.00% 3699 ms 11852 ms provider 6 110
23 together 6 92.21% 92.21% 92.21% 100.00% 2639 ms 3778 ms provider 6 10 probe_config_error 77
24 novita 78 91.71% 91.71% 91.71% 99.02% 2976 ms 5936 ms provider 17 205
25 deepinfra 8 90.91% 90.91% 90.91% 100.00% 2773 ms 4557 ms provider 3 33
alibaba warming 71 0.00% 0.00% 0.00% 100.00% provider 209 209
atlas-cloud warming 67 0.00% 0.00% 0.00% 100.00% provider 209 209
chutes warming 10 0.00% 0.00% 0.00% 100.00% provider 209 209
cloudflare-workers-ai warming 23 0.00% 0.00% 0.00% 100.00% provider 209 209
digitalocean warming 22 0.00% 0.00% 0.00% 100.00% provider 209 209
google-ai-studio warming 8 0.00% 0.00% 0.00% 100.00% provider 209 209
google-vertex warming 9 0.00% 0.00% 0.00% 100.00% provider 209 209
inceptron warming 4 0.00% 0.00% 0.00% 100.00% provider 209 209
makora warming 6 0.00% 0.00% 0.00% 100.00% provider 206 3 unsupported_route 206
morph warming 8 0.00% 0.00% 0.00% 100.00% provider 209 209
neurometric warming 5 0.00% 0.00% 0.00% 100.00% provider 209 209
streamlake warming 3 0.00% 0.00% 0.00% 100.00% provider 209 209
telnyx warming 12 0.00% 0.00% 0.00% 100.00% provider 209 209
tinfoil warming 4 0.00% 0.00% 0.00% 100.00% provider 209 209
xiaomi warming 3 0.00% 0.00% 0.00% 100.00% provider 209 209
zero-g warming 3 0.00% 0.00% 0.00% 100.00% provider 209 209

Models

Qualified models are ranked by provider-attributed availability, then p50 TTFT. Thin availability and throughput measurements stay visible below the ranked set as warming.

#ModelProvider CompletionProvider availabilityWithin deadlineCapacity accepted p50 TTFTp95 TTFTp50 TTFBp95 TTFB Effective throughputConfig excludedSamples
1 openbmb/MiniCPM-V-4_5 nebius 100.00% 100.00% 100.00% 20s 100.00% 2203 ms 3320 ms 2203 ms 3320 ms 11
2 nvidia/Llama-3_1-Nemotron-Ultra-253B-v1 nebius 100.00% 100.00% 100.00% 20s 100.00% 2220 ms 3442 ms 2219 ms 3441 ms 10
3 google/gemma-3-27b-it nebius 100.00% 100.00% 100.00% 20s 100.00% 2226 ms 2455 ms 2226 ms 2455 ms 10
4 mistralai/ministral-8b-2512 mistral 100.00% 100.00% 100.00% 20s 100.00% 2243 ms 2488 ms 2243 ms 2488 ms 45
5 mistralai/mistral-nemo mistral 100.00% 100.00% 100.00% 20s 100.00% 2248 ms 2484 ms 2248 ms 2484 ms 22
6 mistralai/ministral-3b-2512 mistral 100.00% 100.00% 100.00% 20s 100.00% 2252 ms 2842 ms 2252 ms 2842 ms 30
7 mistralai/codestral-2508 mistral 100.00% 100.00% 100.00% 20s 100.00% 2258 ms 2569 ms 2258 ms 2569 ms 25
8 mistralai/ministral-14b-2512 mistral 100.00% 100.00% 100.00% 20s 100.00% 2279 ms 2728 ms 2278 ms 2728 ms 22
9 mistralai/mistral-medium-3-5 mistral 100.00% 100.00% 100.00% 20s 100.00% 2295 ms 2553 ms 2295 ms 2553 ms 18
10 nvidia/Nemotron-3-Nano-Omni nebius 100.00% 100.00% 100.00% 20s 100.00% 2326 ms 2597 ms 2326 ms 2597 ms 11
11 openai/gpt-oss-120b cerebras 100.00% 100.00% 100.00% 20s 100.00% 2342 ms 4034 ms 2342 ms 4034 ms 29
12 qwen/qwen-2.5-7b-instruct together 100.00% 100.00% 100.00% 20s 100.00% 2372 ms 2672 ms 2371 ms 2672 ms 20
13 openai/gpt-4.1-nano openai 100.00% 100.00% 100.00% 20s 100.00% 2379 ms 2529 ms 2379 ms 2529 ms 10
14 cerebras/gemma-4-31b cerebras 100.00% 100.00% 100.00% 15s 100.00% 2383 ms 5674 ms 2383 ms 5674 ms 37
15 google/gemma-4-31b-it lightning 100.00% 100.00% 100.00% 20s 100.00% 2389 ms 2577 ms 2389 ms 2576 ms 13
16 deepseek/deepseek-v4-flash crusoe 100.00% 100.00% 100.00% 20s 100.00% 2399 ms 3362 ms 2399 ms 3362 ms 23
17 z-ai/glm-5.2-fast fireworks 100.00% 100.00% 100.00% 45s 100.00% 2405 ms 6683 ms 2405 ms 6683 ms 15
18 openai/gpt-oss-20b fireworks 100.00% 100.00% 100.00% 20s 100.00% 2414 ms 3121 ms 2414 ms 3121 ms 22
19 lgai-exaone/k-exaone-236b-a23b friendli 100.00% 100.00% 100.00% 20s 100.00% 2420 ms 3273 ms 2420 ms 3273 ms 29
20 google/gemma-4-31b-it crusoe 100.00% 100.00% 100.00% 20s 100.00% 2428 ms 4140 ms 2428 ms 4140 ms 11
21 yutori/n1.5 crusoe 100.00% 100.00% 100.00% 20s 100.00% 2437 ms 3570 ms 2437 ms 3570 ms 18
22 meta-llama/llama-3.3-70b-instruct crusoe 100.00% 100.00% 100.00% 20s 100.00% 2439 ms 3654 ms 2439 ms 3654 ms 18
23 z-ai/glm-5.1 friendli 100.00% 100.00% 100.00% 45s 100.00% 2457 ms 3438 ms 2457 ms 3438 ms 25
24 nvidia/nemotron-3-super-120b-a12b crusoe 100.00% 100.00% 100.00% 20s 100.00% 2459 ms 3113 ms 2458 ms 3113 ms 11
25 deepseek/deepseek-v3.2 friendli 100.00% 100.00% 100.00% 20s 100.00% 2461 ms 6297 ms 2461 ms 6297 ms 23
26 minimax/minimax-m2.5 friendli 100.00% 100.00% 100.00% 20s 100.00% 2461 ms 2963 ms 2461 ms 2963 ms 18
27 openai/gpt-oss-120b fireworks 100.00% 100.00% 100.00% 20s 100.00% 2469 ms 4874 ms 2469 ms 4874 ms 21
28 mistralai/mistral-large mistral 100.00% 100.00% 100.00% 20s 100.00% 2471 ms 3996 ms 2471 ms 3996 ms 25
29 Qwen/Qwen3-235B-A22B-Instruct-2507 nebius 100.00% 100.00% 100.00% 20s 100.00% 2494 ms 12874 ms 2494 ms 12874 ms 11
30 mistralai/mistral-small-2603 mistral 100.00% 100.00% 100.00% 20s 100.00% 2501 ms 3224 ms 2501 ms 3224 ms 22
31 openai/gpt-4o openai 100.00% 100.00% 100.00% 20s 100.00% 2529 ms 6018 ms 2529 ms 6018 ms 16
32 qwen/qwen3-235b-a22b-2507 friendli 100.00% 100.00% 100.00% 20s 100.00% 2542 ms 2910 ms 2542 ms 2910 ms 41
33 z-ai/glm-5.2 friendli 100.00% 100.00% 100.00% 45s 100.00% 2545 ms 7418 ms 2545 ms 7418 ms 32
34 openai/gpt-4.1 openai 100.00% 100.00% 100.00% 20s 100.00% 2550 ms 3143 ms 2550 ms 3143 ms 12
35 x-ai/grok-4.20 grok 100.00% 100.00% 100.00% 20s 100.00% 2554 ms 2778 ms 2554 ms 2777 ms 61
36 x-ai/grok-build-0.1 grok 100.00% 100.00% 100.00% 20s 100.00% 2556 ms 3252 ms 2556 ms 3252 ms 49
37 deepseek/deepseek-v4-pro fireworks 100.00% 100.00% 100.00% 20s 100.00% 2567 ms 2743 ms 2567 ms 2743 ms 21
38 openai/gpt-oss-120b crusoe 100.00% 100.00% 100.00% 20s 100.00% 2577 ms 7927 ms 2577 ms 7926 ms 19
39 z-ai/glm-5.2 venice 100.00% 100.00% 100.00% 45s 100.00% 2578 ms 3395 ms 2578 ms 3395 ms 20
40 deepseek/deepseek-v3-0324 crusoe 100.00% 100.00% 100.00% 20s 100.00% 2585 ms 3581 ms 2585 ms 3581 ms 14
41 openai/gpt-oss-120b baseten 100.00% 100.00% 100.00% 20s 100.00% 2586 ms 3906 ms 2586 ms 3906 ms 19
42 thinkingmachines/inkling-1m baseten 100.00% 100.00% 100.00% 45s 100.00% 2586 ms 2837 ms 2585 ms 2837 ms 17
43 openai/gpt-4.1-mini openai 100.00% 100.00% 100.00% 20s 100.00% 2589 ms 4604 ms 2589 ms 4604 ms 11
44 moonshotai/kimi-k2.7-code baseten 100.00% 100.00% 100.00% 20s 100.00% 2596 ms 4397 ms 2596 ms 4397 ms 21
45 qwen/qwen3.5-9b venice 100.00% 100.00% 100.00% 20s 100.00% 2597 ms 3795 ms 2597 ms 3795 ms 17
46 nvidia/nemotron-3-nano-30b-a3b crusoe 100.00% 100.00% 100.00% 20s 100.00% 2599 ms 3918 ms 2597 ms 3918 ms 12
47 qwen/qwen3.6-27b venice 100.00% 100.00% 100.00% 20s 100.00% 2617 ms 3329 ms 2617 ms 3329 ms 14
48 moonshotai/kimi-k2.6 together 100.00% 100.00% 100.00% 20s 100.00% 2639 ms 3340 ms 2639 ms 3339 ms 14
49 moonshotai/moonshot-v1-128k-vision-preview kimi 100.00% 100.00% 100.00% 20s 100.00% 2642 ms 2844 ms 2642 ms 2843 ms 20
50 bytedance/ui-tars-1.5-7b parasail 100.00% 100.00% 100.00% 20s 100.00% 2649 ms 3015 ms 2649 ms 3015 ms 13
51 moonshotai/moonshot-v1-32k-vision-preview kimi 100.00% 100.00% 100.00% 20s 100.00% 2653 ms 3034 ms 2653 ms 3034 ms 25
52 moonshotai/kimi-k2.6 fireworks 100.00% 100.00% 100.00% 20s 100.00% 2662 ms 5684 ms 2662 ms 5684 ms 17
53 nvidia/nemotron-3-nano-omni-reasoning-30b-a3b crusoe 100.00% 100.00% 100.00% 45s 100.00% 2665 ms 3341 ms 2665 ms 3341 ms 11
54 google/gemma-3n-e4b-it together 100.00% 100.00% 100.00% 20s 100.00% 2672 ms 3778 ms 2672 ms 3778 ms 17
55 nvidia/nemotron-3-ultra-550b-a55b baseten 100.00% 100.00% 100.00% 20s 100.00% 2677 ms 3067 ms 2676 ms 3067 ms 17
56 moonshotai/moonshot-v1-128k kimi 100.00% 100.00% 100.00% 20s 100.00% 2692 ms 2941 ms 2692 ms 2941 ms 18
57 qwen/qwen3-235b-a22b-thinking-2507 venice 100.00% 100.00% 100.00% 45s 100.00% 2697 ms 3582 ms 2697 ms 3582 ms 15
58 x-ai/grok-4.3 grok 100.00% 100.00% 100.00% 20s 100.00% 2708 ms 3432 ms 2708 ms 3432 ms 60
59 deepseek/deepseek-v4-pro baseten 100.00% 100.00% 100.00% 20s 100.00% 2717 ms 3642 ms 2717 ms 3642 ms 14
60 z-ai/glm-4.7 baseten 100.00% 100.00% 100.00% 20s 100.00% 2734 ms 5092 ms 2734 ms 5092 ms 18
61 deepseek-ai/DeepSeek-V4-Pro nebius 100.00% 100.00% 100.00% 20s 100.00% 2736 ms 5735 ms 2736 ms 5735 ms 13
62 z-ai/glm-5.1 wafer 100.00% 100.00% 100.00% 45s 100.00% 2737 ms 4682 ms 2737 ms 4682 ms 45
63 openai/gpt-4o lightning 100.00% 100.00% 100.00% 20s 100.00% 2738 ms 3154 ms 2738 ms 3154 ms 12
64 openai/gpt-3.5-turbo lightning 100.00% 100.00% 100.00% 20s 100.00% 2748 ms 3026 ms 2748 ms 3026 ms 17
65 moonshotai/moonshot-v1-32k kimi 100.00% 100.00% 100.00% 20s 100.00% 2768 ms 3669 ms 2768 ms 3669 ms 20
66 moonshotai/Kimi-K2.6 nebius 100.00% 100.00% 100.00% 20s 100.00% 2773 ms 4119 ms 2773 ms 4119 ms 10
67 google/gemini-2.5-flash lightning 100.00% 100.00% 100.00% 20s 100.00% 2784 ms 2961 ms 2784 ms 2961 ms 11
68 anthropic/claude-haiku-4.5 anthropic 100.00% 100.00% 100.00% 15s 100.00% 2787 ms 3963 ms 2787 ms 3963 ms 17
69 openai/gpt-3.5-turbo openai 100.00% 100.00% 100.00% 20s 100.00% 2795 ms 3841 ms 2795 ms 3841 ms 11
70 meta-llama/llama-3.3-70b-instruct parasail 100.00% 100.00% 100.00% 20s 100.00% 2796 ms 3776 ms 2796 ms 3776 ms 11
71 z-ai/glm-4.7 venice 100.00% 100.00% 100.00% 20s 100.00% 2799 ms 3305 ms 2799 ms 3305 ms 25
72 openai/gpt-5.6-terra openai 100.00% 100.00% 100.00% 45s 100.00% 2813 ms 2913 ms 2813 ms 2913 ms 13
73 x-ai/grok-4.5 grok 100.00% 100.00% 100.00% 20s 100.00% 2849 ms 3376 ms 2848 ms 3376 ms 39
74 z-ai/glm-5.2 siliconflow 100.00% 100.00% 100.00% 45s 100.00% 2858 ms 3911 ms 2858 ms 3911 ms 11
75 openai/gpt-4 lightning 100.00% 100.00% 100.00% 20s 100.00% 2868 ms 3122 ms 2868 ms 3122 ms 15
76 openai/gpt-4.1 lightning 100.00% 100.00% 100.00% 20s 100.00% 2875 ms 3744 ms 2875 ms 3744 ms 19
77 z-ai/glm-4.6 venice 100.00% 100.00% 100.00% 20s 100.00% 2934 ms 3995 ms 2934 ms 3995 ms 15
78 moonshotai/kimi-k2.6 baseten 100.00% 100.00% 100.00% 20s 100.00% 2951 ms 3828 ms 2951 ms 3828 ms 22
79 moonshotai/kimi-k2.7-code-highspeed kimi 100.00% 100.00% 100.00% 20s 100.00% 2957 ms 13511 ms 2957 ms 13510 ms 16
80 minimax/minimax-m3 minimax 100.00% 100.00% 100.00% 20s 100.00% 2997 ms 6734 ms 2997 ms 6734 ms 35
81 openai/o3 openai 100.00% 100.00% 100.00% 45s 100.00% 3007 ms 6032 ms 3007 ms 6032 ms 11
82 z-ai/glm-5.1 venice 100.00% 100.00% 100.00% 45s 100.00% 3031 ms 7787 ms 3031 ms 7787 ms 18
83 moonshotai/kimi-k2.5 kimi 100.00% 100.00% 100.00% 20s 100.00% 3033 ms 3626 ms 3033 ms 3626 ms 19
84 z-ai/glm-5.2 together 100.00% 100.00% 100.00% 45s 100.00% 3034 ms 22796 ms 3034 ms 22796 ms 13
85 minimax/minimax-m2.7 minimax 100.00% 100.00% 100.00% 20s 100.00% 3055 ms 5467 ms 3054 ms 5467 ms 30
86 openai/gpt-4-turbo openai 100.00% 100.00% 100.00% 20s 100.00% 3058 ms 4415 ms 3058 ms 4415 ms 10
87 moonshotai/kimi-k2.7-code kimi 100.00% 100.00% 100.00% 20s 100.00% 3069 ms 9050 ms 3069 ms 9050 ms 11
88 z-ai/glm-5.2 fireworks 100.00% 100.00% 100.00% 45s 100.00% 3074 ms 5210 ms 3074 ms 5210 ms 17
89 minimax/minimax-m2 minimax 100.00% 100.00% 100.00% 20s 100.00% 3083 ms 4749 ms 3082 ms 4749 ms 34
90 anthropic/claude-opus-4.8 anthropic 100.00% 100.00% 100.00% 45s 100.00% 3086 ms 8056 ms 3086 ms 8056 ms 18
91 anthropic/claude-sonnet-4.6 anthropic 100.00% 100.00% 100.00% 20s 100.00% 3168 ms 7232 ms 3168 ms 7232 ms 21
92 moonshotai/kimi-k2.6 kimi 100.00% 100.00% 100.00% 20s 100.00% 3208 ms 3778 ms 3208 ms 3778 ms 26
93 minimax/minimax-m2.7-highspeed minimax 100.00% 100.00% 100.00% 20s 100.00% 3232 ms 3911 ms 3232 ms 3911 ms 42
94 qwen/qwen3.5-397b-a17b venice 100.00% 100.00% 100.00% 20s 100.00% 3233 ms 4498 ms 3233 ms 4498 ms 16
95 minimax/minimax-m2.1-highspeed minimax 100.00% 100.00% 100.00% 20s 100.00% 3239 ms 4096 ms 3239 ms 4096 ms 31
96 moonshotai/kimi-k2.7-code fireworks 100.00% 100.00% 100.00% 20s 100.00% 3253 ms 6192 ms 3253 ms 6192 ms 13
97 minimax/minimax-m3 wafer 100.00% 100.00% 100.00% 20s 100.00% 3271 ms 4195 ms 3270 ms 4195 ms 44
98 moonshotai/kimi-k3 fireworks 100.00% 100.00% 100.00% 20s 100.00% 3300 ms 16821 ms 3300 ms 16821 ms 19
99 z-ai/glm-4.5-air zai 100.00% 100.00% 91.67% 20s 100.00% 3330 ms 20147 ms 3329 ms 20146 ms 12
100 moonshotai/kimi-k2.6 wafer 100.00% 100.00% 100.00% 20s 100.00% 3361 ms 4063 ms 3361 ms 4063 ms 36
101 deepseek/deepseek-v4-flash parasail 100.00% 100.00% 100.00% 20s 100.00% 3384 ms 13724 ms 3384 ms 13724 ms 10
102 z-ai/glm-5 venice 100.00% 100.00% 100.00% 45s 100.00% 3396 ms 14904 ms 3396 ms 14904 ms 15
103 z-ai/glm-4.6v zai 100.00% 100.00% 100.00% 20s 100.00% 3419 ms 4632 ms 3419 ms 4632 ms 22
104 google/gemini-3.1-flash-lite-preview lightning 100.00% 100.00% 100.00% 15s 100.00% 3426 ms 3615 ms 3426 ms 3615 ms 15
105 anthropic/claude-sonnet-4.5 anthropic 100.00% 100.00% 100.00% 20s 100.00% 3436 ms 5266 ms 3436 ms 5266 ms 18
106 google/gemini-3.5-flash lightning 100.00% 100.00% 100.00% 20s 100.00% 3437 ms 3880 ms 3437 ms 3880 ms 25
107 z-ai/glm-5.2 baseten 100.00% 100.00% 100.00% 45s 100.00% 3450 ms 4487 ms 3450 ms 4487 ms 24
108 minimax/minimax-m2.5-highspeed minimax 100.00% 100.00% 100.00% 20s 100.00% 3455 ms 4024 ms 3455 ms 4023 ms 37
109 deepseek/deepseek-v4-flash fireworks 100.00% 100.00% 100.00% 20s 100.00% 3477 ms 6558 ms 3477 ms 6558 ms 23
110 google/gemini-3-flash-preview lightning 100.00% 100.00% 100.00% 20s 100.00% 3478 ms 4467 ms 3478 ms 4467 ms 16
111 z-ai/glm-5v-turbo zai 100.00% 100.00% 100.00% 45s 100.00% 3484 ms 13558 ms 3484 ms 13558 ms 15
112 openai/o3-mini openai 100.00% 100.00% 100.00% 45s 100.00% 3505 ms 4395 ms 3505 ms 4395 ms 13
113 z-ai/glm-4.5v zai 100.00% 100.00% 100.00% 20s 100.00% 3519 ms 4193 ms 3519 ms 4193 ms 20
114 thinkingmachines/inkling thinkingmachines 100.00% 100.00% 100.00% 45s 100.00% 3535 ms 4150 ms 3535 ms 4150 ms 110
115 anthropic/claude-opus-4.5 anthropic 100.00% 100.00% 100.00% 45s 100.00% 3580 ms 4847 ms 3579 ms 4847 ms 13
116 anthropic/claude-opus-4.7 anthropic 100.00% 100.00% 100.00% 45s 100.00% 3598 ms 5666 ms 3598 ms 5666 ms 21
117 openai/gpt-4-turbo lightning 100.00% 100.00% 100.00% 20s 100.00% 3614 ms 4097 ms 3614 ms 4097 ms 10
118 z-ai/glm-5.2-fast wafer 100.00% 100.00% 100.00% 45s 100.00% 3657 ms 4395 ms 3657 ms 4395 ms 44
119 z-ai/glm-5.1 crusoe 100.00% 100.00% 100.00% 45s 100.00% 3667 ms 5638 ms 3667 ms 5638 ms 20
120 z-ai/glm-5 zai 100.00% 100.00% 100.00% 45s 100.00% 3732 ms 7060 ms 3732 ms 7060 ms 16
121 z-ai/glm-5 gmi 100.00% 100.00% 100.00% 45s 100.00% 3814 ms 5961 ms 3814 ms 5960 ms 42
122 z-ai/glm-5.2 gmi 100.00% 100.00% 100.00% 45s 100.00% 3932 ms 5616 ms 3932 ms 5615 ms 40
123 z-ai/glm-5.1 gmi 100.00% 100.00% 100.00% 45s 100.00% 3959 ms 4806 ms 3959 ms 4806 ms 47
124 z-ai/glm-5v-turbo venice 100.00% 100.00% 100.00% 45s 100.00% 3997 ms 13071 ms 3996 ms 13070 ms 16
125 Qwen/Qwen3-Next-80B-A3B-Thinking nebius 100.00% 100.00% 100.00% 45s 100.00% 3999 ms 4120 ms 3999 ms 4120 ms 10
126 minimax/minimax-m3 fireworks 100.00% 100.00% 100.00% 20s 100.00% 4091 ms 18120 ms 4091 ms 18120 ms 18
127 openai/gpt-5-nano openai 100.00% 100.00% 100.00% 20s 100.00% 4223 ms 4918 ms 4222 ms 4918 ms 10
128 anthropic/claude-opus-4.6 anthropic 100.00% 100.00% 100.00% 45s 100.00% 4230 ms 5544 ms 4230 ms 5544 ms 25
129 anthropic/claude-sonnet-5 anthropic 100.00% 100.00% 100.00% 20s 100.00% 4233 ms 5104 ms 4233 ms 5104 ms 22
130 z-ai/glm-5.2 zai 100.00% 100.00% 100.00% 45s 100.00% 4289 ms 5469 ms 4289 ms 5469 ms 21
131 moonshotai/kimi-k3 kimi 100.00% 100.00% 100.00% 20s 100.00% 4417 ms 7934 ms 4416 ms 7934 ms 19
132 google/gemini-3.1-pro-preview lightning 100.00% 100.00% 100.00% 20s 100.00% 4468 ms 4682 ms 4468 ms 4682 ms 20
133 openai/gpt-5 openai 100.00% 100.00% 100.00% 20s 100.00% 4787 ms 10129 ms 4787 ms 10129 ms 12
134 google/gemini-2.5-pro lightning 100.00% 100.00% 100.00% 20s 100.00% 5129 ms 6360 ms 5129 ms 6360 ms 17
135 zai-org/GLM-5.1 nebius 100.00% 100.00% 100.00% 45s 100.00% 5242 ms 12994 ms 5241 ms 12993 ms 11
136 anthropic/claude-fable-5 anthropic 100.00% 100.00% 100.00% 20s 100.00% 5661 ms 7675 ms 5661 ms 7675 ms 21
137 z-ai/glm-5.1 zai 100.00% 100.00% 100.00% 45s 100.00% 6478 ms 9063 ms 6477 ms 9063 ms 21
138 deepseek/deepseek-v4-flash deepseek 98.59% 98.59% 98.59% 20s 100.00% 2781 ms 3587 ms 2781 ms 3587 ms 71
139 deepseek/deepseek-v4-flash-0731 deepseek 98.21% 98.21% 98.21% 20s 100.00% 2814 ms 3594 ms 2813 ms 3594 ms 56
140 z-ai/glm-4.7 cerebras 97.73% 97.73% 97.73% 20s 97.73% 2347 ms 3045 ms 2347 ms 3045 ms 44
141 cerebras/zai-glm-4.7 cerebras 97.67% 97.67% 97.67% 15s 97.67% 2393 ms 4408 ms 2392 ms 4407 ms 43
142 deepseek/deepseek-v4-pro deepseek 97.56% 97.56% 97.56% 20s 100.00% 2943 ms 3759 ms 2943 ms 3759 ms 82
143 deepseek/deepseek-v4-pro gmi 97.14% 97.14% 97.14% 20s 100.00% 4532 ms 6553 ms 4532 ms 6553 ms 35
144 z-ai/glm-4.6 zai 96.00% 96.00% 96.00% 20s 100.00% 3442 ms 5830 ms 3442 ms 5829 ms 25
145 google/gemma-4-31b-it cerebras 95.65% 95.65% 95.65% 20s 95.65% 2322 ms 5791 ms 2322 ms 5791 ms 23
146 deepseek/deepseek-v4-flash-0731 fireworks 95.65% 95.65% 95.65% 20s 100.00% 4384 ms 10377 ms 4384 ms 10377 ms 23
147 moonshotai/moonshot-v1-8k kimi 95.45% 95.45% 95.45% 20s 100.00% 2846 ms 3755 ms 2846 ms 3755 ms 22
148 z-ai/glm-5.2 wafer 95.00% 95.00% 95.00% 45s 95.00% 3667 ms 5123 ms 3666 ms 5123 ms 40
149 z-ai/glm-5-turbo zai 94.74% 94.74% 89.47% 45s 100.00% 3508 ms 45947 ms 3508 ms 45947 ms 19
150 z-ai/glm-4.7 zai 94.74% 94.74% 94.74% 20s 100.00% 4212 ms 18749 ms 4212 ms 18749 ms 19
151 z-ai/glm-4.5 zai 94.74% 94.74% 89.47% 20s 100.00% 4454 ms 21085 ms 4454 ms 21085 ms 19
152 z-ai/glm-5.2 phala 94.55% 94.55% 94.55% 45s 100.00% 3699 ms 11852 ms 3699 ms 11852 ms 110
153 moonshotai/kimi-k2.6 crusoe 94.12% 94.12% 94.12% 20s 100.00% 2773 ms 19970 ms 2773 ms 19970 ms 17
154 cerebras/gpt-oss-120b cerebras 93.94% 93.94% 93.94% 15s 93.94% 2377 ms 2930 ms 2376 ms 2930 ms 33
155 moonshotai/moonshot-v1-8k-vision-preview kimi 92.31% 92.31% 92.31% 20s 100.00% 2648 ms 3665 ms 2648 ms 3665 ms 13
156 z-ai/glm-4.7-flash venice 90.91% 90.91% 90.91% 20s 95.45% 2694 ms 12583 ms 2694 ms 12583 ms 22
157 thedrummer/cydonia-24b-v4.1 parasail 90.00% 90.00% 90.00% 20s 90.00% 3929 ms 6290 ms 3929 ms 6290 ms 10
158 z-ai/glm-5-turbo venice 87.50% 87.50% 87.50% 45s 100.00% 3702 ms 25026 ms 3702 ms 25026 ms 16
159 z-ai/glm-5.2 crusoe 80.00% 80.00% 80.00% 45s 100.00% 3341 ms 4267 ms 3341 ms 4266 ms 15
160 deepseek/deepseek-v4-pro crusoe 76.92% 76.92% 76.92% 20s 100.00% 2380 ms 3217 ms 2380 ms 3217 ms 13
nvidia/Cosmos3-Super-Reasoner warming nebius 100.00% 100.00% 100.00% 20s 100.00% 2245 ms 2424 ms 2245 ms 2424 ms 8
Qwen/Qwen3-32B warming nebius 100.00% 100.00% 100.00% 20s 100.00% 2274 ms 2326 ms 2274 ms 2325 ms 4
Qwen/Qwen2.5-VL-72B-Instruct warming nebius 100.00% 100.00% 100.00% 20s 100.00% 2286 ms 3241 ms 2286 ms 3241 ms 7
NousResearch/Hermes-4-70B warming nebius 100.00% 100.00% 100.00% 20s 100.00% 2301 ms 2788 ms 2301 ms 2788 ms 8
sao10k/l3-8b-lunaris warming novita 100.00% 100.00% 100.00% 20s 100.00% 2335 ms 2435 ms 2335 ms 2435 ms 2
Qwen/Qwen3-30B-A3B-Instruct-2507 warming nebius 100.00% 100.00% 100.00% 20s 100.00% 2342 ms 3719 ms 2342 ms 3719 ms 5
NousResearch/Hermes-4-405B warming nebius 100.00% 100.00% 100.00% 20s 100.00% 2356 ms 6638 ms 2356 ms 6638 ms 7
openai/gpt-oss-20b warming novita 100.00% 100.00% 100.00% 20s 100.00% 2413 ms 2428 ms 2413 ms 2428 ms 2
openai/gpt-oss-120b warming nebius 100.00% 100.00% 100.00% 20s 100.00% 2428 ms 3507 ms 2428 ms 3506 ms 8
qwen/qwen-2.5-72b-instruct warming novita 100.00% 100.00% 100.00% 20s 100.00% 2445 ms 2464 ms 2445 ms 2464 ms 3
qwen/qwen3-235b-a22b-fp8 warming novita 100.00% 100.00% 100.00% 20s 100.00% 2511 ms 2999 ms 2511 ms 2999 ms 6
deepseek/deepseek-ocr-2 warming novita 100.00% 100.00% 100.00% 20s 100.00% 2522 ms 2525 ms 2522 ms 2524 ms 2
meta-llama/llama-3.3-70b-instruct warming together 100.00% 100.00% 100.00% 20s 100.00% 2543 ms 3057 ms 2543 ms 3057 ms 7
meta-llama/llama-4-scout-17b-16e-instruct warming novita 100.00% 100.00% 100.00% 20s 100.00% 2566 ms 3978 ms 2566 ms 3978 ms 5
openai/gpt-4o-mini warming openai 100.00% 100.00% 100.00% 20s 100.00% 2567 ms 2657 ms 2567 ms 2657 ms 9
meta-llama/llama-3.1-8b-instruct warming novita 100.00% 100.00% 100.00% 20s 100.00% 2569 ms 8505 ms 2569 ms 8505 ms 2
sao10k/l31-70b-euryale-v2.2 warming novita 100.00% 100.00% 100.00% 20s 100.00% 2581 ms 2909 ms 2581 ms 2909 ms 2
openai/gpt-5.4-mini warming openai 100.00% 100.00% 100.00% 20s 100.00% 2605 ms 3401 ms 2605 ms 3400 ms 8
openai/gpt-oss-120b warming novita 100.00% 100.00% 100.00% 20s 100.00% 2616 ms 16126 ms 2616 ms 16126 ms 4
meta-llama/llama-4-maverick-17b-128e-instruct-fp8 warming novita 100.00% 100.00% 100.00% 20s 100.00% 2619 ms 2801 ms 2619 ms 2801 ms 4
qwen/qwen3-235b-a22b-instruct-2507 warming novita 100.00% 100.00% 100.00% 20s 100.00% 2632 ms 2640 ms 2632 ms 2640 ms 3
zai-org/autoglm-phone-9b-multilingual warming novita 100.00% 100.00% 100.00% 20s 100.00% 2639 ms 3007 ms 2639 ms 3007 ms 4
qwen/qwen3.5-27b warming deepinfra 100.00% 100.00% 100.00% 20s 100.00% 2643 ms 3119 ms 2642 ms 3119 ms 4
zai-org/glm-4.7-flash warming novita 100.00% 100.00% 100.00% 20s 100.00% 2646 ms 2646 ms 2646 ms 2646 ms 1
google/gemma-3-12b-it warming deepinfra 100.00% 100.00% 100.00% 20s 100.00% 2651 ms 2924 ms 2651 ms 2924 ms 6
qwen/qwen3.6-35b-a3b warming novita 100.00% 100.00% 100.00% 20s 100.00% 2656 ms 2871 ms 2656 ms 2871 ms 3
zai-org/glm-4.6v warming novita 100.00% 100.00% 100.00% 20s 100.00% 2659 ms 2659 ms 2659 ms 2659 ms 1
inclusionai/ling-2.6-flash warming novita 100.00% 100.00% 100.00% 20s 100.00% 2671 ms 2671 ms 2671 ms 2671 ms 1
openai/gpt-5.2 warming openai 100.00% 100.00% 100.00% 20s 100.00% 2683 ms 2700 ms 2683 ms 2700 ms 5
qwen/qwen2.5-vl-72b-instruct warming parasail 100.00% 100.00% 100.00% 20s 100.00% 2694 ms 2896 ms 2694 ms 2896 ms 7
moonshotai/kimi-k2-instruct warming novita 100.00% 100.00% 100.00% 20s 100.00% 2700 ms 3234 ms 2700 ms 3234 ms 2
google/gemma-3-27b-it warming novita 100.00% 100.00% 100.00% 20s 100.00% 2709 ms 2808 ms 2709 ms 2808 ms 2
moonshotai/kimi-k2.5 warming novita 100.00% 100.00% 100.00% 20s 100.00% 2709 ms 2815 ms 2709 ms 2800 ms 2
nvidia/nemotron-3-ultra-550b-a55b warming nebius 100.00% 100.00% 100.00% 20s 100.00% 2711 ms 2777 ms 2710 ms 2776 ms 5
deepseek/deepseek-r1-0528 warming novita 100.00% 100.00% 100.00% 45s 100.00% 2730 ms 3088 ms 2730 ms 3087 ms 2
openai/gpt-5.6-luna warming openai 100.00% 100.00% 100.00% 45s 100.00% 2752 ms 3318 ms 2752 ms 3317 ms 7
zai-org/GLM-5.2 warming nebius 100.00% 100.00% 100.00% 45s 100.00% 2760 ms 3444 ms 2760 ms 3444 ms 6
google/gemma-3-27b-it warming parasail 100.00% 100.00% 100.00% 20s 100.00% 2763 ms 3603 ms 2763 ms 3603 ms 8
meta-llama/llama-4-maverick warming parasail 100.00% 100.00% 100.00% 20s 100.00% 2767 ms 3010 ms 2767 ms 3010 ms 8
google/gemma-4-26b-a4b-it warming deepinfra 100.00% 100.00% 100.00% 20s 100.00% 2773 ms 3364 ms 2773 ms 3364 ms 6
qwen/qwen3.5-27b warming novita 100.00% 100.00% 100.00% 20s 100.00% 2797 ms 2820 ms 2797 ms 2820 ms 3
deepseek/deepseek-r1-distill-llama-70b warming novita 100.00% 100.00% 100.00% 45s 100.00% 2820 ms 3314 ms 2820 ms 3313 ms 3
moonshotai/kimi-k2-0905 warming novita 100.00% 100.00% 100.00% 20s 100.00% 2821 ms 2913 ms 2820 ms 2912 ms 3
qwen/qwen3-235b-a22b-thinking-2507 warming novita 100.00% 100.00% 100.00% 45s 100.00% 2831 ms 2831 ms 2831 ms 2831 ms 1
qwen/qwen3-omni-30b-a3b-instruct warming novita 100.00% 100.00% 100.00% 20s 100.00% 2844 ms 2890 ms 2844 ms 2890 ms 2
qwen/qwen3-omni-30b-a3b-thinking warming novita 100.00% 100.00% 100.00% 45s 100.00% 2857 ms 2952 ms 2857 ms 2951 ms 2
kwaipilot/kat-coder-pro warming novita 100.00% 100.00% 100.00% 20s 100.00% 2863 ms 2863 ms 2862 ms 2862 ms 1
zai-org/glm-4.6 warming novita 100.00% 100.00% 100.00% 20s 100.00% 2870 ms 3783 ms 2870 ms 3783 ms 4
qwen/qwen3-next-80b-a3b-instruct warming parasail 100.00% 100.00% 100.00% 20s 100.00% 2876 ms 6296 ms 2876 ms 6296 ms 6
deepseek/deepseek-v4-flash-0731 warming novita 100.00% 100.00% 100.00% 20s 100.00% 2884 ms 2884 ms 2883 ms 2883 ms 1
google/gemma-3-4b-it warming deepinfra 100.00% 100.00% 100.00% 20s 100.00% 2888 ms 2888 ms 2888 ms 2888 ms 1
qwen/qwen3-coder-next warming novita 100.00% 100.00% 100.00% 20s 100.00% 2893 ms 2893 ms 2892 ms 2892 ms 1
nvidia/nemotron-3-super-120b-a12b warming nebius 100.00% 100.00% 100.00% 20s 100.00% 2895 ms 3731 ms 2895 ms 3731 ms 9
openai/gpt-5.1 warming openai 100.00% 100.00% 100.00% 20s 100.00% 2897 ms 3079 ms 2897 ms 3079 ms 5
qwen/qwen3-next-80b-a3b-instruct warming novita 100.00% 100.00% 100.00% 20s 100.00% 2909 ms 2909 ms 2909 ms 2909 ms 1
qwen/qwen3-coder-next warming parasail 100.00% 100.00% 100.00% 20s 100.00% 2913 ms 3747 ms 2912 ms 3747 ms 5
moonshotai/Kimi-K2.7-Code warming nebius 100.00% 100.00% 100.00% 20s 100.00% 2914 ms 3155 ms 2914 ms 3154 ms 6
qwen/qwen3.5-122b-a10b warming novita 100.00% 100.00% 100.00% 20s 100.00% 2916 ms 3037 ms 2916 ms 3037 ms 3
qwen/qwen3-vl-235b-a22b-thinking warming novita 100.00% 100.00% 100.00% 45s 100.00% 2920 ms 3865 ms 2920 ms 3865 ms 7
nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B warming nebius 100.00% 100.00% 100.00% 20s 100.00% 2927 ms 2928 ms 2927 ms 2928 ms 2
zai-org/glm-4.5v warming novita 100.00% 100.00% 100.00% 20s 100.00% 2927 ms 3016 ms 2926 ms 3016 ms 2
qwen/qwen3.6-27b warming novita 100.00% 100.00% 100.00% 20s 100.00% 2936 ms 3320 ms 2936 ms 3320 ms 2
moonshotai/kimi-k2.7-code warming parasail 100.00% 100.00% 100.00% 20s 100.00% 2940 ms 3197 ms 2939 ms 3197 ms 6
moonshotai/kimi-k2.6 warming parasail 100.00% 100.00% 100.00% 20s 100.00% 2946 ms 15480 ms 2946 ms 15480 ms 8
minimax/minimax-m3 warming parasail 100.00% 100.00% 100.00% 20s 100.00% 2956 ms 3449 ms 2956 ms 3448 ms 7
z-ai/glm-5.2 warming parasail 100.00% 100.00% 100.00% 45s 100.00% 2972 ms 3242 ms 2972 ms 3241 ms 9
inclusionai/ling-2.6-1t warming novita 100.00% 100.00% 100.00% 20s 100.00% 2976 ms 3444 ms 2976 ms 3444 ms 3
qwen/qwen3.5-397b-a17b warming novita 100.00% 100.00% 100.00% 20s 100.00% 2976 ms 2976 ms 2976 ms 2976 ms 1
arcee-ai/trinity-large-thinking warming parasail 100.00% 100.00% 100.00% 45s 100.00% 2987 ms 3132 ms 2987 ms 3132 ms 7
qwen/qwen3-vl-235b-a22b-instruct warming parasail 100.00% 100.00% 100.00% 20s 100.00% 2990 ms 4681 ms 2990 ms 4681 ms 9
openai/gpt-oss-20b warming parasail 100.00% 100.00% 100.00% 20s 100.00% 2991 ms 15247 ms 2991 ms 15246 ms 8
google/gemma-3-27b-it warming deepinfra 100.00% 100.00% 100.00% 20s 100.00% 2992 ms 3918 ms 2991 ms 3918 ms 5
minimaxai/minimax-m1-80k warming novita 100.00% 100.00% 100.00% 20s 100.00% 2992 ms 3288 ms 2992 ms 3288 ms 2
deepseek/deepseek-r1-turbo warming novita 100.00% 100.00% 100.00% 45s 100.00% 2996 ms 3219 ms 2995 ms 3219 ms 5
google/gemma-4-31b-it warming parasail 100.00% 100.00% 100.00% 20s 100.00% 3013 ms 3770 ms 3013 ms 3770 ms 7
deepseek/deepseek-ocr warming novita 100.00% 100.00% 100.00% 20s 100.00% 3016 ms 3021 ms 3016 ms 3021 ms 2
openai/gpt-4 warming openai 100.00% 100.00% 100.00% 20s 100.00% 3022 ms 4112 ms 3021 ms 4112 ms 6
minimax/minimax-m2.7 warming novita 100.00% 100.00% 100.00% 20s 100.00% 3026 ms 5685 ms 3026 ms 5685 ms 3
thedrummer/skyfall-36b-v2 warming parasail 100.00% 100.00% 100.00% 20s 100.00% 3048 ms 3521 ms 3048 ms 3521 ms 8
z-ai/glm-5v-turbo warming siliconflow 100.00% 100.00% 100.00% 45s 100.00% 3060 ms 3848 ms 3060 ms 3848 ms 7
qwen/qwen3-235b-a22b-2507 warming crusoe 100.00% 100.00% 100.00% 20s 100.00% 3070 ms 5893 ms 3070 ms 5893 ms 7
qwen/qwen3-vl-235b-a22b-instruct warming novita 100.00% 100.00% 100.00% 20s 100.00% 3079 ms 3239 ms 3079 ms 3239 ms 3
openai/gpt-oss-120b warming parasail 100.00% 100.00% 100.00% 20s 100.00% 3108 ms 5143 ms 3108 ms 5142 ms 9
deepseek/deepseek-v4-flash warming siliconflow 100.00% 100.00% 100.00% 20s 100.00% 3115 ms 4284 ms 3115 ms 4284 ms 8
zai-org/glm-5 warming novita 100.00% 100.00% 100.00% 45s 100.00% 3126 ms 3274 ms 3126 ms 3274 ms 2
inclusionai/ling-3.0-flash warming novita 100.00% 100.00% 100.00% 20s 100.00% 3157 ms 4306 ms 3157 ms 4306 ms 5
openai/gpt-5.6-sol warming openai 100.00% 100.00% 100.00% 45s 100.00% 3159 ms 3227 ms 3158 ms 3227 ms 5
tencent/hunyuan-a13b-instruct warming siliconflow 100.00% 100.00% 100.00% 20s 100.00% 3166 ms 3247 ms 3166 ms 3247 ms 7
deepseek/deepseek-v4-pro warming novita 100.00% 100.00% 100.00% 20s 100.00% 3169 ms 4025 ms 3169 ms 4025 ms 5
openai/o4-mini warming openai 100.00% 100.00% 100.00% 45s 100.00% 3173 ms 3478 ms 3173 ms 3478 ms 9
google/gemma-4-26b-a4b-it warming parasail 100.00% 100.00% 100.00% 20s 100.00% 3188 ms 5306 ms 3188 ms 5306 ms 8
openai/gpt-5.5 warming openai 100.00% 100.00% 100.00% 45s 100.00% 3199 ms 9458 ms 3199 ms 9458 ms 9
minimax/minimax-m2.1 warming novita 100.00% 100.00% 100.00% 20s 100.00% 3201 ms 3317 ms 3201 ms 3317 ms 4
qwen/qwen3-coder-480b-a35b-instruct warming novita 100.00% 100.00% 100.00% 20s 100.00% 3216 ms 3348 ms 3216 ms 3348 ms 3
z-ai/glm-5.1 warming parasail 100.00% 100.00% 100.00% 45s 100.00% 3254 ms 4435 ms 3254 ms 4435 ms 8
minimax/minimax-m2.5-highspeed warming novita 100.00% 100.00% 100.00% 20s 100.00% 3340 ms 4418 ms 3340 ms 4418 ms 4
google/gemma-4-26b-a4b-it warming novita 100.00% 100.00% 100.00% 20s 100.00% 3366 ms 6647 ms 3366 ms 6647 ms 3
deepseek/deepseek-v4-pro warming siliconflow 100.00% 100.00% 100.00% 20s 100.00% 3375 ms 6249 ms 3375 ms 6249 ms 6
moonshotai/kimi-k2.7-code warming novita 100.00% 100.00% 100.00% 20s 100.00% 3378 ms 3723 ms 3378 ms 3722 ms 3
qwen/qwen3-max warming novita 100.00% 100.00% 100.00% 20s 100.00% 3384 ms 3953 ms 3384 ms 3953 ms 2
z-ai/glm-5.2 warming deepinfra 100.00% 100.00% 100.00% 45s 100.00% 3420 ms 4557 ms 3419 ms 4557 ms 3
deepseek/deepseek-v3.2 warming novita 100.00% 100.00% 100.00% 20s 100.00% 3426 ms 3817 ms 3426 ms 3817 ms 2
zai-org/glm-4.7 warming novita 100.00% 100.00% 100.00% 20s 100.00% 3431 ms 3751 ms 3431 ms 3751 ms 4
qwen/qwen3-coder-30b-a3b-instruct warming novita 100.00% 100.00% 100.00% 20s 100.00% 3455 ms 3455 ms 3455 ms 3455 ms 1
baidu/ernie-4.5-vl-424b-a47b warming novita 100.00% 100.00% 100.00% 20s 100.00% 3475 ms 3558 ms 3475 ms 3558 ms 3
deepseek/deepseek-v3-turbo warming novita 100.00% 100.00% 100.00% 20s 100.00% 3498 ms 3498 ms 3497 ms 3497 ms 1
zai-org/glm-5.1 warming novita 100.00% 100.00% 100.00% 45s 100.00% 3723 ms 3984 ms 3723 ms 3983 ms 3
minimax/minimax-m3 warming siliconflow 100.00% 100.00% 100.00% 20s 100.00% 3726 ms 6429 ms 3726 ms 6429 ms 8
openai/o1 warming openai 100.00% 100.00% 100.00% 45s 100.00% 3793 ms 6216 ms 3793 ms 6216 ms 9
tencent/hy3 warming novita 100.00% 100.00% 100.00% 20s 100.00% 3831 ms 4145 ms 3831 ms 4145 ms 3
deepseek/deepseek-v3.1 warming novita 100.00% 100.00% 100.00% 20s 100.00% 3833 ms 4194 ms 3833 ms 4194 ms 3
deepseek/deepseek-v4-flash warming novita 100.00% 100.00% 100.00% 20s 100.00% 3841 ms 5202 ms 3841 ms 5202 ms 3
anthropic/claude-opus-5 warming anthropic 100.00% 100.00% 100.00% 45s 100.00% 3852 ms 4521 ms 3852 ms 4521 ms 9
stepfun/step-3.7-flash warming novita 100.00% 100.00% 100.00% 20s 100.00% 3964 ms 5343 ms 3963 ms 5343 ms 5
inclusionai/ring-2.6-1t warming novita 100.00% 100.00% 100.00% 20s 100.00% 3981 ms 3981 ms 3981 ms 3981 ms 1
z-ai/glm-5 warming siliconflow 100.00% 100.00% 100.00% 45s 100.00% 3991 ms 5484 ms 3991 ms 5484 ms 9
deepseek/deepseek-v3.1-terminus warming novita 100.00% 100.00% 100.00% 20s 100.00% 4140 ms 4140 ms 4139 ms 4139 ms 1
xiaomimimo/mimo-v2.5-pro warming novita 100.00% 100.00% 100.00% 20s 100.00% 4359 ms 5904 ms 4359 ms 5904 ms 5
z-ai/glm-5.2 warming novita 100.00% 100.00% 100.00% 45s 100.00% 4681 ms 7302 ms 4681 ms 7301 ms 3
mindai/macaron-v1-venti warming novita 100.00% 100.00% 100.00% 20s 100.00% 5936 ms 8555 ms 5935 ms 8555 ms 3
meta-llama/Llama-3.3-70B-Instruct warming nebius 100.00% 100.00% 100.00% 20s 100.00% 5984 ms 11916 ms 5984 ms 11916 ms 5
moonshotai/kimi-k3 warming novita 100.00% 100.00% 100.00% 20s 100.00% 6055 ms 6055 ms 6055 ms 6055 ms 1
nvidia/nemotron-3-nano-30b-a3b warming novita 100.00% 100.00% 100.00% 20s 100.00% 9086 ms 9086 ms 9086 ms 9086 ms 1
MiniMaxAI/MiniMax-M3 warming nebius 87.50% 87.50% 87.50% 20s 100.00% 2781 ms 3520 ms 2781 ms 3520 ms 8
moonshotai/kimi-k3 warming nebius 85.71% 85.71% 85.71% 20s 100.00% 2827 ms 3121 ms 2827 ms 3121 ms 7
deepseek/deepseek-v4-pro warming parasail 80.00% 80.00% 80.00% 20s 80.00% 3527 ms 12034 ms 3527 ms 12033 ms 5
qwen/qwen3-vl-8b-instruct warming parasail 77.78% 77.78% 77.78% 20s 77.78% 2920 ms 6439 ms 2920 ms 6439 ms 9
meta-llama/llama-3.1-70b-instruct warming deepinfra 75.00% 75.00% 75.00% 20s 100.00% 2716 ms 3263 ms 2716 ms 3263 ms 4
google/gemma-4-31b-it warming novita 75.00% 75.00% 75.00% 20s 100.00% 2885 ms 3188 ms 2885 ms 3188 ms 4
mistralai/mistral-nemo warming novita 66.67% 66.67% 66.67% 20s 100.00% 8210 ms 10772 ms 8210 ms 10772 ms 3
zai-org/glm-4.5-air warming novita 50.00% 50.00% 50.00% 20s 100.00% 2898 ms 2898 ms 2898 ms 2898 ms 2
google/gemma-4-31b-it warming deepinfra 50.00% 50.00% 50.00% 20s 100.00% 3136 ms 5850 ms 3136 ms 5850 ms 4
aisingapore/gemma-sea-lion-v4-27b-it warming cloudflare-workers-ai 0.00% 0.00% 0.00% 20s 100.00% 8
baichuan/baichuan-m2-32b warming novita 0.00% 0.00% 0.00% 20s 100.00% 3
baidu/cobuddy warming novita 0.00% 0.00% 0.00% 20s 100.00% 1
baidu/ernie-4.5-21B-a3b warming novita 0.00% 0.00% 0.00% 20s 50.00% 2
bytedance/doubao-seed-1.6-251015 warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 4
bytedance/doubao-seed-1.6-flash-250828 warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 6
bytedance/doubao-seed-1.8-251228 warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 2
bytedance/doubao-seed-2.0-code-preview-260215 warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 1
bytedance/doubao-seed-2.0-lite-260428 warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 3
bytedance/doubao-seed-2.0-mini-260428 warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 1
bytedance/doubao-seed-2.0-pro-260215 warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 5
bytedance/doubao-seed-2.1-pro-260628 warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 4
bytedance/doubao-seed-2.1-turbo-260628 warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 2
bytedance/doubao-seed-evolving warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 2
deepseek/deepseek-ocr warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 3
deepseek/deepseek-r1-distill-llama-70b warming digitalocean 0.00% 0.00% 0.00% 45s 100.00% 10
deepseek/deepseek-r1-distill-qwen-32b warming cloudflare-workers-ai 0.00% 0.00% 0.00% 45s 100.00% 10
deepseek/deepseek-v3.1 warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 4
deepseek/deepseek-v3.1-terminus warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 3
deepseek/deepseek-v3.2 warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 2
deepseek/deepseek-v3.2 warming chutes 0.00% 0.00% 0.00% 20s 100.00% 27
deepseek/deepseek-v3.2 warming digitalocean 0.00% 0.00% 0.00% 20s 100.00% 10
deepseek/deepseek-v3.2-exp warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 5
deepseek/deepseek-v4-flash warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 3
deepseek/deepseek-v4-flash warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 2
deepseek/deepseek-v4-flash warming digitalocean 0.00% 0.00% 0.00% 20s 100.00% 2
deepseek/deepseek-v4-flash warming makora 0.00% 0.00% 0.00% 20s 100.00% 29
deepseek/deepseek-v4-flash warming morph 0.00% 0.00% 0.00% 20s 100.00% 27
deepseek/deepseek-v4-flash-0731 warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 7
deepseek/deepseek-v4-pro warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 3
deepseek/deepseek-v4-pro warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 1
deepseek/deepseek-v4-pro warming digitalocean 0.00% 0.00% 0.00% 20s 100.00% 7
deepseek/deepseek-v4-pro warming makora 0.00% 0.00% 0.00% 20s 100.00% 3 unsupported_route 31
google/gemini-2.0-flash warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 3
google/gemini-2.0-flash-lite warming atlas-cloud 0.00% 0.00% 0.00% 15s 100.00% 4
google/gemini-2.5-flash warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 6
google/gemini-2.5-flash warming google-ai-studio 0.00% 0.00% 0.00% 20s 100.00% 38
google/gemini-2.5-flash warming google-vertex 0.00% 0.00% 0.00% 20s 100.00% 14
google/gemini-2.5-flash-lite warming atlas-cloud 0.00% 0.00% 0.00% 15s 100.00% 3
google/gemini-2.5-flash-lite warming google-vertex 0.00% 0.00% 0.00% 15s 100.00% 20
google/gemini-2.5-pro warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 4
google/gemini-2.5-pro warming google-vertex 0.00% 0.00% 0.00% 20s 100.00% 19
google/gemini-3-flash-preview warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 3
google/gemini-3-flash-preview warming google-ai-studio 0.00% 0.00% 0.00% 20s 100.00% 29
google/gemini-3-flash-preview warming google-vertex 0.00% 0.00% 0.00% 20s 100.00% 26
google/gemini-3.1-flash-image-preview warming google-ai-studio 0.00% 0.00% 0.00% 20s 100.00% 24
google/gemini-3.1-flash-lite warming atlas-cloud 0.00% 0.00% 0.00% 15s 100.00% 4
google/gemini-3.1-flash-lite warming google-ai-studio 0.00% 0.00% 0.00% 15s 100.00% 17
google/gemini-3.1-flash-lite warming google-vertex 0.00% 0.00% 0.00% 15s 100.00% 35
google/gemini-3.1-pro-preview warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 1
google/gemini-3.1-pro-preview warming google-ai-studio 0.00% 0.00% 0.00% 20s 100.00% 22
google/gemini-3.1-pro-preview warming google-vertex 0.00% 0.00% 0.00% 20s 100.00% 28
google/gemini-3.5-flash warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 2
google/gemini-3.5-flash warming google-ai-studio 0.00% 0.00% 0.00% 20s 100.00% 21
google/gemini-3.5-flash warming google-vertex 0.00% 0.00% 0.00% 20s 100.00% 13
google/gemini-3.5-flash-lite warming google-ai-studio 0.00% 0.00% 0.00% 15s 100.00% 35
google/gemini-3.5-flash-lite warming google-vertex 0.00% 0.00% 0.00% 15s 100.00% 26
google/gemini-3.6-flash warming google-ai-studio 0.00% 0.00% 0.00% 20s 100.00% 23
google/gemini-3.6-flash warming google-vertex 0.00% 0.00% 0.00% 20s 100.00% 28
google/gemma-2b-it warming telnyx 0.00% 0.00% 0.00% 20s 100.00% 15
google/gemma-3-12b-it warming novita 0.00% 0.00% 0.00% 20s 100.00% 4
google/gemma-4-12b-it warming neurometric 0.00% 0.00% 0.00% 20s 100.00% 40
google/gemma-4-26b-a4b-it warming cloudflare-workers-ai 0.00% 0.00% 0.00% 20s 100.00% 14
google/gemma-4-26b-a4b-it warming makora 0.00% 0.00% 0.00% 20s 100.00% 38
google/gemma-4-31b-it warming digitalocean 0.00% 0.00% 0.00% 20s 100.00% 15
google/gemma-4-31b-it warming tinfoil 0.00% 0.00% 0.00% 20s 100.00% 52
google/gemma-4-31b-it warming together 0.00% 0.00% 0.00% 20s 100.00% 10 probe_config_error 6
google/gemma-4-31b-turbo warming chutes 0.00% 0.00% 0.00% 20s 100.00% 19
google/gemma-4-e2b-it warming neurometric 0.00% 0.00% 0.00% 20s 100.00% 45
ibm-granite/granite-4.0-h-micro warming cloudflare-workers-ai 0.00% 0.00% 0.00% 20s 100.00% 6
ibm-granite/granite-4.1-8b warming neurometric 0.00% 0.00% 0.00% 20s 100.00% 37
kwaipilot/kat-coder-air-v2.5 warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 1
kwaipilot/kat-coder-air-v2.5 warming streamlake 0.00% 0.00% 0.00% 20s 100.00% 69
kwaipilot/kat-coder-pro-v2 warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 7
kwaipilot/kat-coder-pro-v2 warming streamlake 0.00% 0.00% 0.00% 20s 100.00% 65
kwaipilot/kat-coder-pro-v2.5 warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 4
kwaipilot/kat-coder-pro-v2.5 warming streamlake 0.00% 0.00% 0.00% 20s 100.00% 75
meituan-longcat/longcat-2.0 warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 4
meta-llama/llama-3.1-70b-instruct warming telnyx 0.00% 0.00% 0.00% 20s 100.00% 16
meta-llama/llama-3.1-8b-instruct warming telnyx 0.00% 0.00% 0.00% 20s 100.00% 19
meta-llama/llama-3.1-8b-instruct-fp8 warming cloudflare-workers-ai 0.00% 0.00% 0.00% 20s 100.00% 11
meta-llama/llama-3.2-11b-vision-instruct warming cloudflare-workers-ai 0.00% 0.00% 0.00% 20s 100.00% 4
meta-llama/llama-3.2-1b-instruct warming cloudflare-workers-ai 0.00% 0.00% 0.00% 20s 100.00% 10
meta-llama/llama-3.2-3b-instruct warming cloudflare-workers-ai 0.00% 0.00% 0.00% 20s 100.00% 11
meta-llama/llama-3.3-70b-instruct warming digitalocean 0.00% 0.00% 0.00% 20s 100.00% 6
meta-llama/llama-3.3-70b-instruct warming novita 0.00% 0.00% 0.00% 20s 0.00% 1
meta-llama/llama-3.3-70b-instruct warming telnyx 0.00% 0.00% 0.00% 20s 100.00% 24
meta-llama/llama-3.3-70b-instruct warming tinfoil 0.00% 0.00% 0.00% 20s 100.00% 45
meta-llama/llama-3.3-70b-instruct-fp8-fast warming cloudflare-workers-ai 0.00% 0.00% 0.00% 15s 100.00% 10
meta-llama/llama-4-maverick warming digitalocean 0.00% 0.00% 0.00% 20s 100.00% 9
meta-llama/llama-4-scout-17b-16e-instruct warming cloudflare-workers-ai 0.00% 0.00% 0.00% 20s 100.00% 8
meta-llama/llama-guard-3-8b warming cloudflare-workers-ai 0.00% 0.00% 0.00% 20s 100.00% 10
microsoft/wizardlm-2-8x22b warming novita 0.00% 0.00% 0.00% 20s 100.00% 1
mindai/macaron-v1-tall warming novita 0.00% 0.00% 0.00% 20s 100.00% 2
minimax/minimax-m2.5 warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 5
minimax/minimax-m2.5 warming digitalocean 0.00% 0.00% 0.00% 20s 100.00% 10
minimax/minimax-m2.5 warming inceptron 0.00% 0.00% 0.00% 20s 100.00% 47
minimax/minimax-m2.7 warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 5
minimax/minimax-m2.7 warming morph 0.00% 0.00% 0.00% 20s 100.00% 25
minimax/minimax-m2.7 warming telnyx 0.00% 0.00% 0.00% 20s 100.00% 12
minimax/minimax-m3 warming morph 0.00% 0.00% 0.00% 20s 100.00% 24
minimax/minimax-m3 warming telnyx 0.00% 0.00% 0.00% 20s 100.00% 15
mistralai/ministral-3-14b-instruct warming digitalocean 0.00% 0.00% 0.00% 20s 100.00% 7
mistralai/mistral-nemo warming chutes 0.00% 0.00% 0.00% 20s 100.00% 19
mistralai/mistral-small-3.1-24b-instruct warming cloudflare-workers-ai 0.00% 0.00% 0.00% 20s 100.00% 9
moonshotai/kimi-k2.5 warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 2
moonshotai/kimi-k2.5 warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 1
moonshotai/kimi-k2.5 warming digitalocean 0.00% 0.00% 0.00% 20s 100.00% 14
moonshotai/kimi-k2.5 warming telnyx 0.00% 0.00% 0.00% 20s 100.00% 20
moonshotai/kimi-k2.6 warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 1
moonshotai/kimi-k2.6 warming chutes 0.00% 0.00% 0.00% 20s 100.00% 20
moonshotai/kimi-k2.6 warming cloudflare-workers-ai 0.00% 0.00% 0.00% 20s 100.00% 6
moonshotai/kimi-k2.6 warming digitalocean 0.00% 0.00% 0.00% 20s 100.00% 12
moonshotai/kimi-k2.6 warming inceptron 0.00% 0.00% 0.00% 20s 100.00% 53
moonshotai/kimi-k2.6 warming telnyx 0.00% 0.00% 0.00% 20s 100.00% 17
moonshotai/kimi-k2.7-code warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 3
moonshotai/kimi-k2.7-code warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 2
moonshotai/kimi-k2.7-code warming cloudflare-workers-ai 0.00% 0.00% 0.00% 20s 100.00% 13
moonshotai/kimi-k2.7-code warming inceptron 0.00% 0.00% 0.00% 20s 100.00% 48
moonshotai/kimi-k3 warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 3
moonshotai/kimi-k3 warming cloudflare-workers-ai 0.00% 0.00% 0.00% 20s 100.00% 11
moonshotai/kimi-k3 warming makora 0.00% 0.00% 0.00% 20s 100.00% 28
moonshotai/kimi-k3 warming telnyx 0.00% 0.00% 0.00% 20s 100.00% 14
morph/morph-v3-fast warming morph 0.00% 0.00% 0.00% 15s 100.00% 28
morph/morph-v3-large warming morph 0.00% 0.00% 0.00% 20s 100.00% 28
nvidia/nemotron-3-120b-a12b warming cloudflare-workers-ai 0.00% 0.00% 0.00% 20s 100.00% 6
nvidia/nemotron-3-nano-omni warming digitalocean 0.00% 0.00% 0.00% 20s 100.00% 5
nvidia/nemotron-3-super-120b warming digitalocean 0.00% 0.00% 0.00% 20s 100.00% 11
nvidia/nemotron-3-ultra-550b warming digitalocean 0.00% 0.00% 0.00% 20s 100.00% 13
nvidia/nemotron-nano-12b-v2-vl warming digitalocean 0.00% 0.00% 0.00% 20s 100.00% 9
openai/gpt-4.1-mini warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 2
openai/gpt-5.4-mini warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 7
openai/gpt-5.5 warming atlas-cloud 0.00% 0.00% 0.00% 45s 100.00% 4
openai/gpt-5.6-luna warming atlas-cloud 0.00% 0.00% 0.00% 45s 100.00% 3
openai/gpt-5.6-sol warming atlas-cloud 0.00% 0.00% 0.00% 45s 100.00% 2
openai/gpt-5.6-terra warming atlas-cloud 0.00% 0.00% 0.00% 45s 100.00% 2
openai/gpt-oss-120b warming cloudflare-workers-ai 0.00% 0.00% 0.00% 20s 100.00% 10
openai/gpt-oss-120b warming tinfoil 0.00% 0.00% 0.00% 20s 100.00% 50
openai/gpt-oss-20b warming cloudflare-workers-ai 0.00% 0.00% 0.00% 20s 100.00% 9
qwen/qwen-flash warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 3
qwen/qwen-flash-2025-07-28 warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 3
qwen/qwen-mt-flash warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 2
qwen/qwen-mt-lite warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 3
qwen/qwen-mt-plus warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 3
qwen/qwen-mt-turbo warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 2
qwen/qwen-plus warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 5
qwen/qwen-plus-2025-07-28 warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 7
qwen/qwen-plus-2025-09-11 warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 3
qwen/qwen-plus-2025-12-01 warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 1
qwen/qwen-plus-character warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 1
qwen/qwen-vl-ocr warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 4
qwen/qwen-vl-ocr-2025-11-20 warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 3
qwen/qwen2.5-coder-32b-instruct warming cloudflare-workers-ai 0.00% 0.00% 0.00% 20s 100.00% 5
qwen/qwen3-235b-a22b warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 2
qwen/qwen3-235b-a22b warming telnyx 0.00% 0.00% 0.00% 20s 100.00% 16
qwen/qwen3-235b-a22b-2507 warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 4
qwen/qwen3-235b-a22b-instruct-2507 warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 4
qwen/qwen3-235b-a22b-thinking-2507 warming alibaba 0.00% 0.00% 0.00% 45s 100.00% 3
qwen/qwen3-235b-a22b-thinking-2507 warming chutes 0.00% 0.00% 0.00% 45s 100.00% 14
qwen/qwen3-30b-a3b warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 6
qwen/qwen3-30b-a3b-fp8 warming cloudflare-workers-ai 0.00% 0.00% 0.00% 20s 100.00% 12
qwen/qwen3-30b-a3b-instruct-2507 warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 1
qwen/qwen3-30b-a3b-thinking-2507 warming alibaba 0.00% 0.00% 0.00% 45s 100.00% 2
qwen/qwen3-32b warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 2
qwen/qwen3-32b warming chutes 0.00% 0.00% 0.00% 20s 100.00% 25
qwen/qwen3-32b warming digitalocean 0.00% 0.00% 0.00% 20s 100.00% 10
qwen/qwen3-8b warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 3
qwen/qwen3-coder-30b-a3b-instruct warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 1
qwen/qwen3-coder-480b-a35b-instruct warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 2
qwen/qwen3-coder-flash warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 1
qwen/qwen3-coder-flash warming digitalocean 0.00% 0.00% 0.00% 20s 100.00% 13
qwen/qwen3-coder-flash-2025-07-28 warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 2
qwen/qwen3-coder-next warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 2
qwen/qwen3-coder-plus warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 2
qwen/qwen3-coder-plus-2025-07-22 warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 3
qwen/qwen3-coder-plus-2025-09-23 warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 4
qwen/qwen3-max warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 3
qwen/qwen3-max-2025-09-23 warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 5
qwen/qwen3-max-2026-01-23 warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 3
qwen/qwen3-next-80b-a3b-instruct warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 4
qwen/qwen3-next-80b-a3b-thinking warming alibaba 0.00% 0.00% 0.00% 45s 100.00% 2
qwen/qwen3-vl-235b-a22b-instruct warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 4
qwen/qwen3-vl-235b-a22b-thinking warming alibaba 0.00% 0.00% 0.00% 45s 100.00% 3
qwen/qwen3-vl-235b-a22b-thinking warming atlas-cloud 0.00% 0.00% 0.00% 45s 100.00% 5
qwen/qwen3-vl-30b-a3b-instruct warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 4
qwen/qwen3-vl-30b-a3b-thinking warming alibaba 0.00% 0.00% 0.00% 45s 100.00% 5
qwen/qwen3-vl-32b-instruct warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 2
qwen/qwen3-vl-32b-thinking warming alibaba 0.00% 0.00% 0.00% 45s 100.00% 2
qwen/qwen3-vl-8b-instruct warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 5
qwen/qwen3-vl-8b-instruct warming neurometric 0.00% 0.00% 0.00% 20s 100.00% 45
qwen/qwen3-vl-8b-thinking warming alibaba 0.00% 0.00% 0.00% 45s 100.00% 5
qwen/qwen3-vl-8b-thinking warming neurometric 0.00% 0.00% 0.00% 45s 100.00% 42
qwen/qwen3-vl-flash warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 2
qwen/qwen3-vl-flash-2025-10-15 warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 5
qwen/qwen3-vl-flash-2026-01-22 warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 1
qwen/qwen3-vl-plus warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 2
qwen/qwen3-vl-plus-2025-09-23 warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 1
qwen/qwen3-vl-plus-2025-12-19 warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 3
qwen/qwen3.5-122b-a10b warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 4
qwen/qwen3.5-122b-a10b warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 2
qwen/qwen3.5-27b warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 1
qwen/qwen3.5-27b warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 4
qwen/qwen3.5-35b-a3b warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 3
qwen/qwen3.5-35b-a3b warming parasail 0.00% 0.00% 0.00% 20s 0.00% 1 probe_config_error 1
qwen/qwen3.5-397b-a17b warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 5
qwen/qwen3.5-397b-a17b warming chutes 0.00% 0.00% 0.00% 20s 100.00% 27
qwen/qwen3.5-397b-a17b warming digitalocean 0.00% 0.00% 0.00% 20s 100.00% 5
qwen/qwen3.5-397b-a17b warming morph 0.00% 0.00% 0.00% 20s 100.00% 25
qwen/qwen3.5-flash warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 3
qwen/qwen3.5-flash warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 1
qwen/qwen3.5-flash-2026-02-23 warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 3
qwen/qwen3.5-plus warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 1
qwen/qwen3.5-plus warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 4
qwen/qwen3.5-plus-2026-02-15 warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 4
qwen/qwen3.6-27b warming chutes 0.00% 0.00% 0.00% 20s 100.00% 15
qwen/qwen3.6-27b warming morph 0.00% 0.00% 0.00% 20s 100.00% 28
qwen/qwen3.6-35b-a3b warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 4
qwen/qwen3.6-35b-a3b warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 2
qwen/qwen3.6-35b-a3b warming parasail 0.00% 0.00% 0.00% 20s 100.00% 11 probe_config_error 1
qwen/qwen3.6-flash warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 3
qwen/qwen3.6-flash-2026-04-16 warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 2
qwen/qwen3.6-plus warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 2
qwen/qwen3.6-plus warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 4
qwen/qwen3.6-plus-2026-04-02 warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 4
qwen/qwen3.7-flash warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 5
qwen/qwen3.7-flash-2026-07-15 warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 1
qwen/qwen3.7-max warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 4
qwen/qwen3.7-max-2026-05-20 warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 1
qwen/qwen3.7-max-2026-06-08 warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 4
qwen/qwen3.7-plus warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 4
qwen/qwen3.7-plus warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 1
qwen/qwen3.7-plus-2026-05-26 warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 1
qwen/qwq-32b warming cloudflare-workers-ai 0.00% 0.00% 0.00% 20s 100.00% 6
tencent/hy3 warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 3
x-ai/grok-4.3 warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 2
x-ai/grok-4.5 warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 2
x-ai/grok-build-0.1 warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 4
xiaomi/mimo-v2.5 warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 2
xiaomi/mimo-v2.5 warming xiaomi 0.00% 0.00% 0.00% 20s 100.00% 73
xiaomi/mimo-v2.5-pro warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 3
xiaomi/mimo-v2.5-pro warming digitalocean 0.00% 0.00% 0.00% 20s 100.00% 8
xiaomi/mimo-v2.5-pro warming xiaomi 0.00% 0.00% 0.00% 20s 100.00% 72
xiaomi/mimo-v2.5-pro-ultraspeed warming xiaomi 0.00% 0.00% 0.00% 20s 100.00% 64
z-ai/glm-4.6 warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 1
z-ai/glm-4.7 warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 2
z-ai/glm-4.7-flash warming cloudflare-workers-ai 0.00% 0.00% 0.00% 20s 100.00% 14
z-ai/glm-5 warming atlas-cloud 0.00% 0.00% 0.00% 45s 100.00% 2
z-ai/glm-5 warming digitalocean 0.00% 0.00% 0.00% 45s 100.00% 13
z-ai/glm-5-turbo warming atlas-cloud 0.00% 0.00% 0.00% 45s 100.00% 3
z-ai/glm-5.1 warming alibaba 0.00% 0.00% 0.00% 45s 100.00% 2
z-ai/glm-5.1 warming atlas-cloud 0.00% 0.00% 0.00% 45s 100.00% 4
z-ai/glm-5.1 warming chutes 0.00% 0.00% 0.00% 45s 100.00% 20
z-ai/glm-5.1 warming digitalocean 0.00% 0.00% 0.00% 45s 100.00% 7
z-ai/glm-5.1 warming telnyx 0.00% 0.00% 0.00% 45s 100.00% 25
z-ai/glm-5.2 warming alibaba 0.00% 0.00% 0.00% 45s 100.00% 8
z-ai/glm-5.2 warming atlas-cloud 0.00% 0.00% 0.00% 45s 100.00% 2
z-ai/glm-5.2 warming chutes 0.00% 0.00% 0.00% 45s 100.00% 23
z-ai/glm-5.2 warming cloudflare-workers-ai 0.00% 0.00% 0.00% 45s 100.00% 6
z-ai/glm-5.2 warming digitalocean 0.00% 0.00% 0.00% 45s 100.00% 13
z-ai/glm-5.2 warming inceptron 0.00% 0.00% 0.00% 45s 100.00% 61
z-ai/glm-5.2 warming makora 0.00% 0.00% 0.00% 45s 100.00% 43
z-ai/glm-5.2 warming morph 0.00% 0.00% 0.00% 45s 100.00% 24
z-ai/glm-5.2 warming telnyx 0.00% 0.00% 0.00% 45s 100.00% 16
z-ai/glm-5.2 warming tinfoil 0.00% 0.00% 0.00% 45s 100.00% 62
z-ai/glm-5.2 warming zero-g 0.00% 0.00% 0.00% 45s 100.00% 63
z-ai/glm-5.2-nvfp4 warming makora 0.00% 0.00% 0.00% 45s 100.00% 37
zero-g/0gm-1.0-35b-a3b warming zero-g 0.00% 0.00% 0.00% 20s 100.00% 63
zero-g/0gm-1.0-35b-a3b-sia warming zero-g 0.00% 0.00% 0.00% 20s 100.00% 83
Workspace access

Sign in

Choose a sign in method. New email and OAuth accounts include $0.10 in starter credit; wallet-only accounts start at $0.

By signing in you agree to the terms of service and privacy policy.