Models
Models
Find the right model for every task
Compare providers, context limits, pricing, and capabilities side-by-side. Pick the model that fits your workflow and budget.
4494 models
Orpheus Arabic Saudi
Groq
4K ctx|$40.00 in|$0.000 out
Orpheus V1 English
Groq
4K ctx|$0.000 in|$0.000 out
Llama 4 Scout 17B
Groq
131K ctx|$0.11 in|$0.34 out
Tool CallOpen Weights
Llama Prompt Guard 2 22M
Groq
1K ctx|$0.03 in|$0.03 out
Open Weights
Llama Guard 4 12B
Groq
131K ctx|$0.20 in|$0.20 out
Open Weights
Llama 4 Maverick 17B
Groq
131K ctx|$0.20 in|$0.60 out
Tool CallOpen Weights
Llama Prompt Guard 2 86M
Groq
1K ctx|$0.04 in|$0.04 out
Open Weights
GPT OSS 20B
Groq
131K ctx|$0.07 in|$0.30 out
Tool CallReasoningOpen Weights
Safety GPT OSS 20B
Groq
131K ctx|$0.07 in|$0.30 out
Tool CallReasoningOpen Weights
GPT OSS 120B
Groq
131K ctx|$0.15 in|$0.60 out
Tool CallReasoningOpen Weights
Qwen3 32B
Groq
131K ctx|$0.29 in|$0.59 out
Tool CallReasoningOpen Weights
Compound
Groq
131K ctx|$0.000 in|$0.000 out
Tool CallReasoning
Compound Mini
Groq
131K ctx|$0.000 in|$0.000 out
Tool CallReasoning
Kimi K2 Instruct
Groq
131K ctx|$1.00 in|$3.00 out
Tool CallOpen Weights
Kimi K2 Instruct 0905
Groq
262K ctx|$1.00 in|$3.00 out
Tool CallOpen Weights
Mistral Nemo
Azure
128K ctx|$0.15 in|$0.15 out
Tool CallOpen Weights
GPT-5.2 Chat
Azure
128K ctx|$1.75 in|$14.00 out
Tool CallReasoning
Codex Mini
Azure
200K ctx|$1.50 in|$6.00 out
Tool CallReasoning
Phi-4-multimodal
Azure
128K ctx|$0.08 in|$0.32 out
Open Weights
Phi-3.5-mini-instruct
Azure
128K ctx|$0.13 in|$0.52 out
Open Weights
Llama 4 Scout 17B 16E Instruct
Azure
128K ctx|$0.20 in|$0.78 out
Tool CallOpen Weights
Grok 4.1 Fast (Reasoning)
Azure
128K ctx|$0.20 in|$0.50 out
Tool CallReasoning
Phi-3-medium-instruct (4k)
Azure
4K ctx|$0.17 in|$0.68 out
Open Weights
Ministral 3B
Azure
128K ctx|$0.04 in|$0.04 out
Tool CallOpen Weights