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 tau2-bench, which measures how reliably a model completes multi-step tool-use tasks. 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.
z-ai/glm-5.2
minimax/minimax-m3
deepseek/deepseek-v4-pro
moonshotai/kimi-k2.6
moonshotai/kimi-k2.7-code
deepseek/deepseek-v4-flash
z-ai/glm-5.1
z-ai/glm-5-turbo
z-ai/glm-5v-turbo
z-ai/glm-5
moonshotai/kimi-k2.5
z-ai/glm-4.7
minimax/minimax-m2.5
qwen/qwen3.5-122b-a10b
nvidia/nemotron-3-super-120b-a12b
qwen/qwen3.5-9b
deepseek/deepseek-v3.2
openai/gpt-oss-120b
deepseek/deepseek-chat-v3.1
deepseek/deepseek-r1-0528
qwen/qwen3-235b-a22b-2507
qwen/qwen3-vl-235b-a22b-instruct
qwen/qwen3-coder-30b-a3b-instruct
qwen/qwen3-embedding-8b
No models match your search.
Benchmark scores from the Artificial Analysis Intelligence Index v4.1. Pricing live from the TensorX platform. All inference on EU-sovereign infrastructure with zero data retention.