ModelAtlas

llamagate

Inference providerbilled per token

Endpoints
16
Models
16

Models served

16 shown

ModelCreatorTypeIn $/1MOut $/1MContextMax outputToolsRegion
codellama-7b
codellama-7b
UnattributedChat$0.06$0.1216.4K4.1KRegion not stated
deepseek-coder-6-7b
deepseek-coder-6.7b
DeepSeekChat$0.06$0.1216.4K4.1KRegion not stated
deepseek-r1-7b-qwen
deepseek-r1-7b-qwen
DeepSeekChat$0.08$0.15131K16.4KRegion not stated
deepseek-r1-8b
deepseek-r1-8b
DeepSeekChat$0.10$0.2065.5K16.4KRegion not stated
dolphin3-8b
dolphin3-8b
UnattributedChat$0.08$0.15128K8.2KRegion not stated
gemma3-4b
gemma3-4b
GoogleChat$0.03$0.08128K8.2KRegion not stated
Llama 3.1 8B Instruct
llama-3.1-8b
MetaChat$0.03$0.05131K8.2KRegion not stated
Llama-3.2-3B
llama-3.2-3b
MetaChat$0.04$0.08131K8.2KRegion not stated
llava-7b
llava-7b
UnattributedChat$0.10$0.204.1K2KRegion not stated
mistral-7b-v0-3
mistral-7b-v0.3
Mistral AIChat$0.10$0.1532.8K8.2KRegion not stated
Nomic Embed Text v1.5
nomic-embed-text
UnattributedEmbedding$0.02$08.2K8.2KRegion not stated
openthinker-7b
openthinker-7b
UnattributedChat$0.08$0.1532.8K8.2KRegion not stated
Qwen2.5-Coder-7B
qwen2.5-coder-7b
Alibaba (Qwen)Chat$0.06$0.1232.8K8.2KRegion not stated
Qwen3 8B
qwen3-8b
Alibaba (Qwen)Chat$0.04$0.1432.8K8.2KRegion not stated
Qwen3 Embedding 8B
qwen3-embedding-8b
Alibaba (Qwen)Embedding$0.02$041K41KRegion not stated
qwen3-vl-8b
qwen3-vl-8b
Alibaba (Qwen)Chat$0.15$0.5532.8K8.2KRegion not stated

One row per model and variant. Dated pins appear on the model page, not as separate rows. Prices are indicative; verify with the provider.