This collection contains a list of models that support function calling for each provider, organized by the respective inference provider
Célina Hanouti PRO
celinah
AI & ML interests
agents, inference, this website
Recent Activity
upvoted a changelog 6 days ago
Introducing Buckets: S3-like storage on the Hub upvoted an article 7 days ago
Introducing Storage Buckets on the Hugging Face Hub upvoted an article 12 days ago
PRX Part 3 — Training a Text-to-Image Model in 24h! Organizations
-
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
Image-Text-to-Text • 402B • Updated • 60.2k • • 159 -
meta-llama/Llama-4-Scout-17B-16E-Instruct
Image-Text-to-Text • Updated • 230k • • 1.25k -
deepseek-ai/DeepSeek-V3-0324
Text Generation • 685B • Updated • 322k • • 3.09k -
deepseek-ai/DeepSeek-R1
Text Generation • 685B • Updated • 1.37M • • 13.1k
-
meta-llama/Llama-3.1-8B-Instruct
Text Generation • Updated • 7.32M • • 5.57k -
meta-llama/Llama-3.1-70B-Instruct
Text Generation • 71B • Updated • 891k • • 897 -
meta-llama/Llama-3.1-405B-Instruct
Text Generation • 406B • Updated • 152k • 592 -
meta-llama/Llama-3.3-70B-Instruct
Text Generation • Updated • 588k • • 2.69k
The following models support Structured Outputs with Cerebras provider.
The following models support Structured Outputs with Sambanova provider.
-
meta-llama/Llama-3.1-8B-Instruct
Text Generation • Updated • 7.32M • • 5.57k -
meta-llama/Llama-3.1-405B-Instruct
Text Generation • 406B • Updated • 152k • 592 -
meta-llama/Llama-3.3-70B-Instruct
Text Generation • Updated • 588k • • 2.69k -
meta-llama/Llama-4-Scout-17B-16E-Instruct
Image-Text-to-Text • Updated • 230k • • 1.25k
The following models support Structured Outputs with Together AI provider.
-
meta-llama/Llama-3.2-3B-Instruct
Text Generation • Updated • 4.65M • • 2.04k -
meta-llama/Llama-3.3-70B-Instruct
Text Generation • Updated • 588k • • 2.69k -
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
Image-Text-to-Text • 402B • Updated • 60.2k • • 159 -
meta-llama/Llama-4-Scout-17B-16E-Instruct
Image-Text-to-Text • Updated • 230k • • 1.25k
This collection contains a list of models that support structured output for each provider, organized by the respective inference provider
-
meta-llama/Llama-3.1-70B-Instruct
Text Generation • 71B • Updated • 891k • • 897 -
meta-llama/Llama-3.1-8B-Instruct
Text Generation • Updated • 7.32M • • 5.57k -
deepseek-ai/DeepSeek-V3
Text Generation • Updated • 1.05M • • 4.03k -
meta-llama/Llama-3.3-70B-Instruct
Text Generation • Updated • 588k • • 2.69k
-
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
Image-Text-to-Text • 402B • Updated • 60.2k • • 159 -
meta-llama/Llama-4-Scout-17B-16E-Instruct
Image-Text-to-Text • Updated • 230k • • 1.25k -
Qwen/Qwen2.5-7B-Instruct
Text Generation • 8B • Updated • 22.4M • • 1.14k -
Qwen/Qwen2.5-72B-Instruct
Text Generation • 73B • Updated • 738k • • 917
The following models support Structured Outputs with Nebius provider.
-
meta-llama/Llama-3.1-70B-Instruct
Text Generation • 71B • Updated • 891k • • 897 -
meta-llama/Llama-3.1-8B-Instruct
Text Generation • Updated • 7.32M • • 5.57k -
deepseek-ai/DeepSeek-V3
Text Generation • Updated • 1.05M • • 4.03k -
meta-llama/Llama-3.3-70B-Instruct
Text Generation • Updated • 588k • • 2.69k
The following models support Structured Outputs with Fireworks AI provider.
-
mistralai/Mixtral-8x7B-Instruct-v0.1
47B • Updated • 648k • 4.65k -
mistralai/Mixtral-8x22B-Instruct-v0.1
141B • Updated • 34.1k • 745 -
meta-llama/Meta-Llama-3-70B-Instruct
Text Generation • 71B • Updated • 84.6k • • 1.5k -
meta-llama/Meta-Llama-3-8B-Instruct
Text Generation • 8B • Updated • 1.4M • • 4.41k
The following models support Structured Outputs with Novita provider.
-
Qwen/Qwen2.5-72B-Instruct
Text Generation • 73B • Updated • 738k • • 917 -
deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
Text Generation • 33B • Updated • 948k • • 1.53k -
deepseek-ai/DeepSeek-R1-Distill-Llama-70B
Text Generation • Updated • 94k • • 755 -
meta-llama/Meta-Llama-3-70B-Instruct
Text Generation • 71B • Updated • 84.6k • • 1.5k
This collection contains a list of models that support function calling for each provider, organized by the respective inference provider
This collection contains a list of models that support structured output for each provider, organized by the respective inference provider
-
meta-llama/Llama-3.1-70B-Instruct
Text Generation • 71B • Updated • 891k • • 897 -
meta-llama/Llama-3.1-8B-Instruct
Text Generation • Updated • 7.32M • • 5.57k -
deepseek-ai/DeepSeek-V3
Text Generation • Updated • 1.05M • • 4.03k -
meta-llama/Llama-3.3-70B-Instruct
Text Generation • Updated • 588k • • 2.69k
-
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
Image-Text-to-Text • 402B • Updated • 60.2k • • 159 -
meta-llama/Llama-4-Scout-17B-16E-Instruct
Image-Text-to-Text • Updated • 230k • • 1.25k -
deepseek-ai/DeepSeek-V3-0324
Text Generation • 685B • Updated • 322k • • 3.09k -
deepseek-ai/DeepSeek-R1
Text Generation • 685B • Updated • 1.37M • • 13.1k
-
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
Image-Text-to-Text • 402B • Updated • 60.2k • • 159 -
meta-llama/Llama-4-Scout-17B-16E-Instruct
Image-Text-to-Text • Updated • 230k • • 1.25k -
Qwen/Qwen2.5-7B-Instruct
Text Generation • 8B • Updated • 22.4M • • 1.14k -
Qwen/Qwen2.5-72B-Instruct
Text Generation • 73B • Updated • 738k • • 917
-
meta-llama/Llama-3.1-8B-Instruct
Text Generation • Updated • 7.32M • • 5.57k -
meta-llama/Llama-3.1-70B-Instruct
Text Generation • 71B • Updated • 891k • • 897 -
meta-llama/Llama-3.1-405B-Instruct
Text Generation • 406B • Updated • 152k • 592 -
meta-llama/Llama-3.3-70B-Instruct
Text Generation • Updated • 588k • • 2.69k
The following models support Structured Outputs with Cerebras provider.
The following models support Structured Outputs with Nebius provider.
-
meta-llama/Llama-3.1-70B-Instruct
Text Generation • 71B • Updated • 891k • • 897 -
meta-llama/Llama-3.1-8B-Instruct
Text Generation • Updated • 7.32M • • 5.57k -
deepseek-ai/DeepSeek-V3
Text Generation • Updated • 1.05M • • 4.03k -
meta-llama/Llama-3.3-70B-Instruct
Text Generation • Updated • 588k • • 2.69k
The following models support Structured Outputs with Sambanova provider.
-
meta-llama/Llama-3.1-8B-Instruct
Text Generation • Updated • 7.32M • • 5.57k -
meta-llama/Llama-3.1-405B-Instruct
Text Generation • 406B • Updated • 152k • 592 -
meta-llama/Llama-3.3-70B-Instruct
Text Generation • Updated • 588k • • 2.69k -
meta-llama/Llama-4-Scout-17B-16E-Instruct
Image-Text-to-Text • Updated • 230k • • 1.25k
The following models support Structured Outputs with Fireworks AI provider.
-
mistralai/Mixtral-8x7B-Instruct-v0.1
47B • Updated • 648k • 4.65k -
mistralai/Mixtral-8x22B-Instruct-v0.1
141B • Updated • 34.1k • 745 -
meta-llama/Meta-Llama-3-70B-Instruct
Text Generation • 71B • Updated • 84.6k • • 1.5k -
meta-llama/Meta-Llama-3-8B-Instruct
Text Generation • 8B • Updated • 1.4M • • 4.41k
The following models support Structured Outputs with Together AI provider.
-
meta-llama/Llama-3.2-3B-Instruct
Text Generation • Updated • 4.65M • • 2.04k -
meta-llama/Llama-3.3-70B-Instruct
Text Generation • Updated • 588k • • 2.69k -
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
Image-Text-to-Text • 402B • Updated • 60.2k • • 159 -
meta-llama/Llama-4-Scout-17B-16E-Instruct
Image-Text-to-Text • Updated • 230k • • 1.25k
The following models support Structured Outputs with Novita provider.
-
Qwen/Qwen2.5-72B-Instruct
Text Generation • 73B • Updated • 738k • • 917 -
deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
Text Generation • 33B • Updated • 948k • • 1.53k -
deepseek-ai/DeepSeek-R1-Distill-Llama-70B
Text Generation • Updated • 94k • • 755 -
meta-llama/Meta-Llama-3-70B-Instruct
Text Generation • 71B • Updated • 84.6k • • 1.5k