← LLM Directory
Together AI

Together AI

Hosted Platform

Serverless GPU cloud for open-weight models. Fast inference, competitive pricing, 200+ models.

Flagship1 model

ModelInput / 1MOutput / 1MContext
Llama 4 Maverick
Meta's latest MoE on fast serverless inference.
$0.180$0.5401.0M

Reasoning1 model

ModelInput / 1MOutput / 1MContext
DeepSeek R1
DeepSeek reasoning on Together.
$0.550$2.19131K

Coding1 model

ModelInput / 1MOutput / 1MContext
Codestral 22B
Mistral's coding specialist.
$0.150$0.45066K

Popular6 models

ModelInput / 1MOutput / 1MContext
Llama 3.3 70B
Stable 70B on fast inference.
$0.880$0.880131K
Qwen3 235B-A22B
Qwen's MoE model on Together.
$0.800$1.60131K
Qwen3 32B
Dense 32B at low cost.
$0.300$0.600131K
DeepSeek V3
672B MoE at unbeatable pricing.
$0.140$0.28066K
Gemma 3 27B
Google's 27B open-weight on Together.
$0.240$0.240131K
Mistral Small 3.1 24B
Mistral's latest small model.
$0.100$0.100131K

Image2 models

ModelInput / 1MOutput / 1MContext
FLUX.2 Pro
Top open-weight image model. $0.03/MP.
$0.030$0.030
FLUX.2 Dev
Open-weight image generation. Great quality per dollar.
$0.010$0.010

Other Providers