Models that do chat

LL Llama 3.3 70B Instruct fp8 · Llama 3.3 Community 70B 128K 38ms 212 $0.34 LL Llama 3.1 8B Instruct fp8 · Llama 3.1 Community 8B 128K 19ms 486 $0.06 QW Qwen2.5 72B Instruct fp8 · Qwen 72B 128K 41ms 198 $0.36 MS Mistral Small 3 24B fp8 · Apache 2.0 24B 32K 22ms 364 $0.14 MX Mixtral 8x7B Instruct fp8 · Apache 2.0 46.7B MoE 32K 31ms 276 $0.22 DS DeepSeek V3 fp8 · DeepSeek 671B MoE 128K 58ms 132 $0.58 GM Gemma 2 27B fp8 · Gemma 27B 8K 24ms 332 $0.16 PH Phi-4 14B fp8 · MIT 14B 16K 20ms 428 $0.09 CR Command R 35B fp8 · CC-BY-NC · canary 35B 128K 29ms 288 $0.19