Claude Opus 4.6$11.000/MClaude Opus 4.5$33.000/MClaude Sonnet 3.7$6.600/MClaude Opus 3$33.000/MClaude 2.1$12.800/MClaude 2$12.800/MGPT-5$3.875/MGPT-4.5$97.500/MGPT-4 Turbo Preview$16.000/MGPT-4$39.000/MGPT-4-32k$78.000/Mo3$19.000/Mo3-mini$2.090/Mo4-mini$2.090/Mo1$28.500/Mo1-mini$5.700/Mo1-preview$28.500/MGemini 2.5 Pro$3.875/MGemini 1.5 Pro$2.375/MGemini 1.0 Ultra$12.000/MGemini 1.0 Pro$0.800/MPaLM 2 Bison$0.500/MPaLM 2 Unicorn$5.000/MGemma 3 27B$0.270/MGrok 3$6.600/MGrok 2$4.400/MGrok 1.5$8.000/MDeepSeek-V3$0.519/MDeepSeek-V3-0324$0.519/MDeepSeek-R1$1.042/MClaude Opus 4.6$11.000/MClaude Opus 4.5$33.000/MClaude Sonnet 3.7$6.600/MClaude Opus 3$33.000/MClaude 2.1$12.800/MClaude 2$12.800/MGPT-5$3.875/MGPT-4.5$97.500/MGPT-4 Turbo Preview$16.000/MGPT-4$39.000/MGPT-4-32k$78.000/Mo3$19.000/Mo3-mini$2.090/Mo4-mini$2.090/Mo1$28.500/Mo1-mini$5.700/Mo1-preview$28.500/MGemini 2.5 Pro$3.875/MGemini 1.5 Pro$2.375/MGemini 1.0 Ultra$12.000/MGemini 1.0 Pro$0.800/MPaLM 2 Bison$0.500/MPaLM 2 Unicorn$5.000/MGemma 3 27B$0.270/MGrok 3$6.600/MGrok 2$4.400/MGrok 1.5$8.000/MDeepSeek-V3$0.519/MDeepSeek-V3-0324$0.519/MDeepSeek-R1$1.042/M
BETA
Subscribe
← All providers·AI model pricing index
Groq

Groq

Custom LPU silicon delivering 5-10x the throughput of GPU inference. Hosts open-weights models at industry-leading speeds.

Founded 2016HQ Mountain View, USAWebsite ↗Official pricing ↗API docs ↗
MODELS TRACKED
11
3 categories
FLAGSHIP
Qwen2.5-72B (Groq)
frontier
MIN INPUT
$0.050/M
cheapest model in family
AVG BLENDED
$0.676/M
across 11 priced models
MAX CONTEXT
128K
largest window in family
Frontier
1 model
Llama 3.1 405B (Groq)profile
frontier · 128K ctx
in $2.990/Mout $2.990/M
405B on LPU
Reasoning
1 model
DeepSeek-R1 (Groq)profile
reasoning · 128K ctx
in $0.750/Mout $0.990/M
R1 on LPU
Efficient
9 models
Llama 3.3 70B (Groq)profile
efficient · 128K ctx
in $0.590/Mout $0.790/M
Fastest 70B
Llama 3.1 70B (Groq)profile
efficient · 128K ctx
in $0.590/Mout $0.790/M
70B on LPU
Llama 3.1 8B (Groq)profile
efficient · 128K ctx
in $0.050/Mout $0.080/M
Fastest 8B
Llama 3.2 11B Vision (Groq)profile
multimodal · 128K ctx
in $0.180/Mout $0.180/M
Vision on LPU
Llama 3.2 3B (Groq)profile
efficient · 128K ctx
in $0.060/Mout $0.060/M
Micro on LPU
Mixtral 8x7B (Groq)profile
efficient · 32K ctx
in $0.240/Mout $0.240/M
MoE on LPU
Gemma 2 9B (Groq)profile
efficient · 8K ctx
in $0.200/Mout $0.200/M
Google Gemma fast
Qwen2.5-72B (Groq)profile
frontier · 128K ctx
in $0.790/Mout $0.790/M
Qwen on LPU
Qwen2.5-Coder-32B (Groq)profile
efficient · 128K ctx
in $0.790/Mout $0.790/M
Code on LPU