Flagship (80B+) AI models

All 47 open flagship models. The biggest open models — multi-GPU or API territory. The honest, $0-markup cost to run each — free on your machine, a rented GPU, or your own API key.

DeepSeek-R1 — 671B, DeepSeek · $1.60/1M API
DeepSeek-V3 — 671B, DeepSeek · $0.50/1M 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 · $0.11/1M 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
Llama 4 Scout (17B-16E) — 109B, Meta · $0.20/1M API
DeepSeek V4 Pro — 861.6B, deepseek-ai · $0.66/1M API
DeepSeek V3.2 — 685.4B, deepseek-ai · $5.58/1M API est.
Mistral Large 2 (2407) — 123B, Mistral AI · $1.08/1M API est.
DeepSeek V4 Flash — 158.1B, deepseek-ai · $1.36/1M API est.
MiniMax M2.7 — 228.7B, MiniMaxAI · $1.93/1M API est.
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 · $1.93/1M 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 · $0.98/1M API est.
Qwen3 Next 80B A3B Instruct — 81.3B, Qwen · $0.75/1M API est.
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 · $0.32/1M API
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 · $2.97/1M API est.
Qwen3 235B A22B Instruct 2507 — 235.1B, Qwen · $1.98/1M API est.
GLM 5.1 — 753.9B, zai-org · $2.03/1M API
MiniMax M2 — 228.7B, MiniMaxAI · $0.63/1M API
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.
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 · $2.49/1M API est.
GLM 5 — 753.9B, zai-org · $6.13/1M API est.
MiMo V2 Flash — 309.8B, XiaomiMiMo · $2.58/1M API est.
GLM 4.7 — 358.3B, zai-org · $1.08/1M API
sarvam 105b — 106B, sarvamai · $0.95/1M API est.
Qwen3 Coder 480B A35B Instruct — 480.2B, Qwen · $0.61/1M API
GLM 4.6 — 356.8B, zai-org · $1.09/1M API

Other sizes

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

Compare → · Cost calculator →