A large model interface gateway providing proxy access to multiple AI models with free tiers and token incentives.
| Model | Speed | Latency | Tests |
|---|---|---|---|
| grok-imagine-1.0-fast | 4998.02 t/s | 4.80s | 15 |
| meta/llama-3.2-1b-instruct | 257.24 t/s | 5.26s | 10 |
| openai/gpt-oss-20b | 227.95 t/s | 1.47s | 5 |
| google/gemma-3-1b-it | 213.18 t/s | 0.52s | 10 |
| meta/llama-3.1-8b-instruct | 200.27 t/s | 0.42s | 15 |
| gemini-2.5-flash | 183.01 t/s | 8.28s | 5 |
| igenius/italia_10b_instruct_16k | 136.00 t/s | 0.62s | 10 |
| openai/gpt-oss-120b | 125.83 t/s | 1.34s | 5 |
| nvidia/nemotron-3-nano-30b-a3b | 123.44 t/s | 0.58s | 10 |
| meta/llama-3.2-3b-instruct | 101.40 t/s | 0.65s | 5 |
| grok-4.1-fast | 99.38 t/s | 1.37s | 5 |
| ibm/granite-guardian-3.0-8b | 93.66 t/s | 0.61s | 10 |
| grok-4.1-mini | 73.19 t/s | 7.00s | 5 |
| google/gemma-7b | 45.48 t/s | 0.60s | 10 |
| google/gemma-2-27b-it | 44.61 t/s | 0.55s | 10 |
| qwen/qwen3.5-397b-a17b | 43.19 t/s | 1.56s | 5 |
| GLM-4.7 | 38.95 t/s | 32.32s | 5 |
| google/gemma-2-9b-it | 36.05 t/s | 0.52s | 10 |
| GLM-4.7-Flash | 33.93 t/s | 1.57s | 5 |
| grok-4.1-expert | 33.09 t/s | 1.05s | 5 |
| Time | Model | Speed | Latency |
|---|---|---|---|
| Mar 2, 03:01 PM | grok-imagine-1.0-fast | 4904.05 t/s | 5.46s |
| Mar 2, 03:00 PM | grok-imagine-1.0-fast | 5606.01 t/s | 4.56s |
| Mar 2, 02:31 PM | nvidia/nemotron-3-nano-30b-a3b | 246.87 t/s | 1.15s |
| Mar 2, 02:30 PM | nvidia/nemotron-3-nano-30b-a3b | 0.00 t/s | 0.00s |
| Mar 2, 02:29 PM | mistralai/codestral-22b-instruct-v0.1 | 0.00 t/s | 0.00s |
| Mar 2, 02:28 PM | 01-ai/yi-large | 0.00 t/s | 0.00s |
| Mar 2, 01:05 PM | grok-imagine-1.0-fast | 4484.02 t/s | 4.38s |
| Mar 2, 10:03 AM | grok-4.1-expert | 33.09 t/s | 1.05s |
| Mar 2, 10:00 AM | grok-4.1-mini | 73.19 t/s | 7.00s |
| Mar 2, 09:59 AM | grok-4.1-fast | 99.38 t/s | 1.37s |