Model Catalog

18 supported · 20 coming soon · 38 total

Strength:reasoningcodingagentscustomer supportfinancehealthcarevisioncost optimizationlow latencycreative writing
Showing 38 of 38 models
Model ↑Provider ↕Access ↕StrengthsServingStatus
Claude 3 Opus
200K ctx
AnthropicHosted
reasoningfinancehealthcare
APIAdd API key
Claude 3.5 Haiku
200K ctx
AnthropicHosted
low latencycost optimizationcustomer support
APIAdd API key
Claude 3.5 Sonnet
200K ctx
AnthropicHosted
reasoningcodingagents+1
APIAdd API key
Claude 4 Sonnet
200K ctx
AnthropicHosted
reasoningcodingagents
APIComing Soon
Command R
128K ctx
CohereHosted
cost optimizationcustomer support
APIAdd API key
Command R+
128K ctx
CohereHosted
reasoningagentscustomer support
APIAdd API key
DeepSeek R1
128K ctx
DeepSeekOpen Source
reasoningcoding
GPU 80GB+vLLM
Coming Soon
DeepSeek V3
128K ctx
DeepSeekOpen Source
codingreasoningcost optimization
GPU 80GB+vLLM
Add API key
Falcon 180B
4K ctx
TIIOpen Source
reasoning
GPU 80GB+vLLM
Coming Soon
Gemini 2.0 Flash
1000K ctx
GoogleHosted
low latencyagentsvision
APIComing Soon
Gemini 2.5 Flash
1000K ctx
GoogleHosted
low latencyvisioncost optimization
APIAdd API key
Gemini 2.5 Pro
1000K ctx
GoogleHosted
reasoningcodingvision
APIAdd API key
Gemma 3 27B
128K ctx
GoogleOpen Source
reasoningcost optimization
GPU 16GB+Ollama · vLLM
Coming Soon
GPT-4.5 Preview
128K ctx
OpenAIHosted
reasoningcreative writing
APIComing Soon
GPT-4o
128K ctx
OpenAIHosted
reasoningcodingvision+1
APIAdd API key
GPT-4o (Azure)
128K ctx
Azure OpenAIHosted
reasoningcodingvision
APIComing Soon
GPT-4o mini
128K ctx
OpenAIHosted
cost optimizationlow latencycoding
APIAdd API key
Grok 3
131K ctx
xAIHosted
reasoningcoding
APIComing Soon
Grok 3 Mini
131K ctx
xAIHosted
cost optimizationlow latency
APIComing Soon
Llama 3.1 405B
128K ctx
Together AIHosted
reasoningcodingagents
APIComing Soon
Llama 3.1 70B
128K ctx
MetaOpen Source
reasoningagentscoding
GPU 40GB+vLLM · Ollama
Add API key
Llama 3.1 8B
128K ctx
MetaOpen Source
cost optimizationlow latency
GPU 8GB+vLLM · Ollama
Add API key
Llama 3.3 70B
128K ctx
MetaOpen Source
reasoningcodingcost optimization
GPU 40GB+vLLM · Ollama
Add API key
Llama 3.3 70B (Groq)
128K ctx
GroqHosted
low latencycost optimizationcoding
APIComing Soon
Llama 4 Maverick
1000K ctx
MetaOpen Source
reasoningcodingagents
GPU 80GB+vLLM
Coming Soon
Mistral Large 2
128K ctx
Mistral AIHosted
reasoningcodingfinance
APIAdd API key
Mistral Small 3.1
128K ctx
Mistral AIHosted
cost optimizationlow latencyfinance
APIAdd API key
Mixtral 8x22B
65K ctx
Mistral AIOpen Source
reasoningcoding
GPU 80GB+vLLM
Add API key
Nemotron 70B
128K ctx
NVIDIAHosted
reasoningcoding
APIComing Soon
Nova Lite
300K ctx
AWS BedrockHosted
low latencycost optimization
APIComing Soon
Nova Pro
300K ctx
AWS BedrockHosted
reasoningagentsvision
APIComing Soon
o3
200K ctx
OpenAIHosted
reasoningcodingagents
APIComing Soon
o3 mini
200K ctx
OpenAIHosted
reasoningcoding
APIAdd API key
Phi-4
16K ctx
MicrosoftOpen Source
reasoningcodingcost optimization
GPU 8GB+Ollama · vLLM
Coming Soon
Pixtral Large
128K ctx
Mistral AIHosted
visionreasoning
APIComing Soon
Qwen 2.5 72B
128K ctx
AlibabaOpen Source
codingreasoninglow latency
GPU 40GB+vLLM · Ollama
Add API key
Qwen 2.5 Coder 32B
128K ctx
AlibabaOpen Source
coding
GPU 20GB+vLLM
Coming Soon
Sonar Large
127K ctx
PerplexityHosted
reasoninglow latency
APIComing Soon