Skip to content

Sign in Start free

Catalogue

Models that do reasoning

Emits a thinking trace before the answer. Slower first token, better on multi-step work.

All chat code embeddings long-context reasoning

Model

Params

Context

ttft

tok/s

$ / M

LL Llama 3.3 70B Instruct fp8 · Llama 3.3 Community 70B 128K 38ms 212 $0.34 DS DeepSeek V3 fp8 · DeepSeek 671B MoE 128K 58ms 132 $0.58 DR DeepSeek R1 Distill 32B fp8 · MIT 32B 128K 34ms 244 $0.20 PH Phi-4 14B fp8 · MIT 14B 16K 20ms 428 $0.09

Put the model next to the user.

One command, thirty-one regions, and an invoice that matches what you actually served.

Deploy a model Talk to an engineer