Model Library
Every model we serve, with independent quality benchmarks and transparent pricing.
SmartestiRanked by the Artificial Analysis Intelligence Index, a blended score across reasoning, maths, coding and knowledge benchmarks. Higher is smarter.
Most agenticiRanked by Terminal-Bench v2.1, which measures how reliably a model completes real multi-step engineering tasks in a terminal. Shown as a percentage.
Best valueiIntelligence per dollar: the Intelligence Index divided by blended price, (3x input + output) / 4 per million tokens. Higher means more capability for your spend.
glm-5.3
kimi-k3
glm-5.3-flash
qwen3.8-flash-next
deepseek-v4.1-flash-1017
qwen3.8-2.4t-a95b
deepseek-v4.1-flash
deepseek-v4-pro-0813
deepseek-v4-flash-0731
qwen3.8-27b
glm-5.2
minimax-m3
kimi-k2.7-code
qwen3-embedding-8b
No models match your search.
Benchmark scores from the Artificial Analysis Intelligence Index. Embedding scores from MTEB, as published by the model developer. Pricing live from the TensorX platform. All inference on EU-sovereign infrastructure with zero data retention.