Flagship (80B+) AI models

All 93 open flagship models. The biggest open models — multi-GPU or API territory. Compare calculated local requirements, provider-published rented-GPU rates, and dated API rates or clearly labeled estimates.

• DeepSeek-R1 — 671B, DeepSeek · $1.60/1M API
• DeepSeek-V3 — 671B, DeepSeek · $0.64/1M API
• Llama 3.1 405B Instruct — 405B, Meta · $0.80/1M API last-known
• Kimi K2 Instruct — 1043B, Moonshot AI · $8.44/1M API est.
• gpt-oss-120b — 117B, OpenAI · $0.10/1M API
• Qwen3-235B-A22B — 235B, Alibaba · $1.14/1M API
• DeepSeek R1 0528 — 684.5B, deepseek-ai · $1.33/1M API
• Llama 4 Maverick (17B-128E) — 402B, Meta · $0.38/1M API last-known
• Llama 4 Scout (17B-16E) — 109B, Meta · $0.20/1M API last-known
• DeepSeek V4 Pro — 861.6B, deepseek-ai · $0.79/1M API
• DeepSeek V3.2 — 685.4B, deepseek-ai · $0.32/1M API
• Mistral Large 2 (2407) — 123B, Mistral AI · $1.08/1M API est.
• DeepSeek V4 Flash — 158.1B, deepseek-ai · $0.09/1M API
• MiniMax M2.7 — 228.7B, MiniMaxAI · $0.60/1M API
• Kimi K2 Instruct 0905 — 1026.5B, moonshotai · $1.55/1M API
• DeepSeek R1 0528 NVFP4 v2 — 393.6B, nvidia · $3.25/1M API est.
• NVIDIA Nemotron 3 Super 120B A12B BF16 — 123.6B, nvidia · $1.09/1M API est.
• DeepSeek V3 0324 — 684.5B, deepseek-ai · $5.58/1M API est.
• Command R+ (08-2024) — 104B, Cohere · $0.93/1M API est.
• MiniMax M2.5 — 228.7B, MiniMaxAI · $0.68/1M API
• Ornith 1.0 397B — 396.8B, ornith-ai · $3.27/1M API est.
• MiniMax M2.7 NVFP4 — 116.3B, nvidia · $1.03/1M API est.
• Step 3.5 Flash — 199.4B, stepfun-ai · $1.70/1M API est.
• NVIDIA Nemotron 3 Ultra 550B A55B NVFP4 — 335B, nvidia · $2.78/1M API est.
• GLM 4.5 Air — 110.5B, zai-org · $0.49/1M API
• Qwen3 Next 80B A3B Instruct — 81.3B, Qwen · $0.60/1M API
• MiMo V2.5 — 310.8B, XiaomiMiMo · $2.59/1M API est.
• DeepSeek V4 Flash 0731 — 304.2B, deepseek-ai · $0.21/1M API
• Llama 3.1 405B — 405.9B, meta-llama · $3.35/1M API est.
• DeepSeek V3.1 — 684.5B, deepseek-ai · $5.58/1M API est.
• DeepSeek V3.2 Exp — 685.4B, deepseek-ai · $0.34/1M API
• Qwen3 235B A22B NVFP4 — 132.8B, nvidia · $1.16/1M API est.
• gpt oss puzzle 88B — 90.8B, nvidia · $0.83/1M API est.
• LLaDA2.1 flash — 102.9B, inclusionAI · $0.92/1M API est.
• DeepSeek V4 Flash NVFP4 — 166.7B, nvidia · $1.43/1M API est.
• Kimi K2 Thinking — 1058.1B, moonshotai · $1.55/1M API
• GLM 4.5 — 358.3B, zai-org · $1.40/1M API
• GLM 4.5 Air — 110.5B, unsloth · $0.98/1M API est.
• Qwen3 235B A22B Instruct 2507 — 235.1B, Qwen · $1.98/1M API est.
• GLM 5.1 — 753.9B, zai-org · $2.00/1M API
• MiniMax M2 — 228.7B, MiniMaxAI · $0.64/1M API
• GLM 5.1 NVFP4 — 381.5B, nvidia · $3.15/1M API est.
• gpt oss 120b — 120.4B, unsloth · $1.06/1M API est.
• MiniMax M2.7 REAP 172B A10B NVFP4 GB10 — 97.6B, scottgl · $0.88/1M API est.
• NVIDIA Nemotron 3 Ultra 550B A55B BF16 — 560.5B, nvidia · $4.58/1M API est.
• DeepSeek V4 Pro NVFP4 — 910B, nvidia · $7.38/1M API est.
• MiniMax M2.5 NVFP4 — 116.3B, nvidia · $1.03/1M API est.
• GLM 5.2 NVFP4 — 381B, nvidia · $3.15/1M API est.
• GLM 5 NVFP4 — 435.2B, nvidia · $3.58/1M API est.
• DeepSeek V4 Flash DSpark — 165.3B, deepseek-ai · $1.42/1M API est.
• Ornith 1.0 397B — 396.8B, deepreinforce-ai · $3.27/1M API est.
• Laguna S 2.1 — 117.6B, poolside · $0.14/1M API
• Solar Open2 250B Nota NVFP4 — 144.6B, nota-ai · $1.26/1M API est.
• Ornith 1.5 397B NVFP4 — 203.5B, ornith-ai · $1.73/1M API est.
• MiMo V2.5 Pro — 1023.2B, XiaomiMiMo · $8.29/1M API est.
• LongCat Flash Chat — 561.9B, meituan-longcat · $4.60/1M API est.
• Hy3 preview — 298.8B, tencent · $0.39/1M API
• GLM 5 — 753.9B, zai-org · $1.26/1M API
• MiMo V2 Flash — 309.8B, XiaomiMiMo · $2.58/1M API est.
• GLM 4.7 — 358.3B, zai-org · $1.08/1M API
• MiMo V2.5 Pro FP4 DFlash — 554.3B, XiaomiMiMo · $4.53/1M API est.
• DeepSeek V4 Flash — 158.1B, unsloth · $1.36/1M API est.
• K EXAONE 236B A23B — 237.1B, LGAI-EXAONE · $2.00/1M API est.
• GLM 5.2 NVFP4 — 432B, lukealonso · $3.56/1M API est.
• Ornith 1.5 397B — 403.4B, ornith-ai · $3.33/1M API est.
• GLM 5.2 — 753.3B, zai-org · $2.00/1M API
• MiniMax M3 NVFP4 — 246.6B, nvidia · $2.07/1M API est.
• A.X K1 — 519B, skt · $4.25/1M API est.
• Qwen3 Next 80B A3B Thinking — 81.3B, Qwen · $0.67/1M API
• DeepSeek V4 Flash 0731 NVFP4 — 304.2B, MJPansa · $2.53/1M API est.
• DeepSeek V4 Pro 0813 — 1650.5B, deepseek-ai · $2.24/1M API
• sarvam 105b — 106B, sarvamai · $0.95/1M API est.
• Qwen3 Coder 480B A35B Instruct — 480.2B, Qwen · $0.65/1M API
• Mistral Medium 3.5 128B NVFP4 — 83.8B, nvidia · $0.77/1M API est.
• XORTRON.CriminalComputing.LARGE.2026.3 — 122.6B, darkc0de · $1.08/1M API est.
• DeepSeek V4 Pro DSpark — 889.5B, deepseek-ai · $7.22/1M API est.
• Hy3 — 298.8B, tencent · $0.33/1M API
• Solar Open2 250B — 250.3B, upstage · $2.10/1M API est.
• DeepSeek V4 Flash DSpark Abliterated Uncensored — 165.3B, drowzeys · $1.42/1M API est.
• MiniMax M3 uncensored NVFP4 — 246.3B, ressl · $2.07/1M API est.
• DeepSeek V4 Flash nvfp4 DSpark — 304.2B, nvidia · $2.53/1M API est.
• GLM 4.6 — 356.8B, zai-org · $1.25/1M API
• GLM 5.2 504B — 290B, 0xSero · $2.42/1M API est.
• GLM 5.2 W4AFP8 — 391.9B, PhalaCloud · $3.24/1M API est.
• Solar Open 100B — 102.7B, upstage · $0.92/1M API est.
• MiniMax M2.1 — 228.7B, MiniMaxAI · $0.75/1M API
• Ling 3.0 flash — 127.5B, inclusionAI · $0.04/1M API
• keys DeepSeekV4 Flash GA 0731 Dspark Abliterated Anchored Tensors — 304.2B, drowzeys · $2.53/1M API est.
• Ling 2.6 flash — 107.5B, inclusionAI · $0.02/1M API last-known
• GLM 5.2 NVFP4 — 379.2B, Mapika · $3.13/1M API est.
• Kimi K2 Base — 1026.5B, moonshotai · $8.31/1M API est.
• bloom — 176.2B, bigscience · $1.51/1M API est.
• DeepSeek V4 Flash 0731 abliterated — 305.7B, cebeuq · $2.55/1M API est.

Other sizes

Large (34–80B) · Medium (14–34B) · Small (4–14B) · Tiny (under 4B) · All models

Compare → · LLM cost calculator →

Open the free LLM cost calculator → · Rate table dated 2026-08-24. $0 markup, your own accounts, we never resell compute. © 2026 Cynosure LLC.