Model Catalog
Deploy leading open-source models in one click.
uploadUpload model
P
Parthexpand_morechat
ChatLlama 3 70B Instruct
Meta · 70B params · 8k ctx
Meta's flagship open-source chat model. Excellent reasoning and instruction following.
memoryH100 SXM
rocket_launch2,410 deploys
$0.6/1M in
Deployarrow_forwardchat
ChatLlama 3 8B Instruct
Meta · 8B params · 8k ctx
Smaller Llama 3 variant. Fast, cheap, ideal for high-volume inference.
memoryA100 PCIe
rocket_launch5,680 deploys
$0.1/1M in
Deployarrow_forwardchat
ChatMistral 7B Instruct
Mistral AI · 7B params · 32k ctx
Long-context, Apache-licensed instruct model. Strong for agentic workloads.
memoryA100 PCIe
rocket_launch3,120 deploys
$0.08/1M in
Deployarrow_forwardimage
ImageStable Diffusion XL
Stability AI · 3.5B params · - ctx
Highest-quality open-source image generation. Optimized for inference.
memoryA100 SXM
rocket_launch1,840 deploys
Per-image pricing
Deployarrow_forwardcode
CodeCode Llama 34B
Meta · 34B params · 16k ctx
Specialized for code generation, completion, and reasoning.
memoryH100 SXM
rocket_launch980 deploys
$0.4/1M in
Deployarrow_forwardhub
EmbeddingBGE Large EN v1.5
BAAI · 335M params · 512 ctx
State-of-the-art English embedding model for retrieval and search.
memoryRTX 4090
rocket_launch4,210 deploys
$0.02/1M in
Deployarrow_forward