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
Together AI

Together AI

Managed inference for hundreds of open-weights models. Strong fine-tuning surface and dedicated capacity.

Founded 2022HQ San Francisco, USAWebsite ↗Official pricing ↗API docs ↗
MODELS TRACKED
10
3 categories
FLAGSHIP
Qwen2.5-72B (Together)
frontier
MIN INPUT
$0.100/M
cheapest model in family
AVG BLENDED
$1.518/M
across 10 priced models
MAX CONTEXT
128K
largest window in family
Frontier
1 model
Llama 3.1 405B (Together)profile
frontier · 128K ctx
in $3.500/Mout $3.500/M
405B managed
Reasoning
1 model
DeepSeek-R1 (Together)profile
reasoning · 64K ctx
in $3.000/Mout $7.000/M
R1 managed
Efficient
8 models
Llama 3.3 70B (Together)profile
efficient · 128K ctx
in $0.880/Mout $0.880/M
Managed inference
Qwen2.5-72B (Together)profile
frontier · 32K ctx
in $1.200/Mout $1.200/M
Qwen managed
DBRX Instruct (Together)profile
frontier · 32K ctx
in $1.200/Mout $1.200/M
132B MoE
Mixtral 8x22B (Together)profile
frontier · 64K ctx
in $1.200/Mout $1.200/M
Largest Mixtral
Falcon 40B (Together)profile
efficient · 2K ctx
in $0.900/Mout $0.900/M
Falcon 40B
WizardLM-2 8x22Bprofile
frontier · 64K ctx
in $1.200/Mout $1.200/M
Instruction tuned
Nous-Hermes-2-Yi-34Bprofile
frontier · 4K ctx
in $0.800/Mout $0.800/M
Nous Hermes fine-tune
Llama 3.1 8B (Together)profile
efficient · 128K ctx
in $0.100/Mout $0.100/M
Budget inference