Loading the catalogue…
Loading the catalogue…
What a model can do at the API: tool calling, vision input, extended thinking, prompt caching. Stav grades every model in the catalogue against this list of capabilities, grouped into input, output, serving and tools.
What the model can take in: text, images, audio, video and structured data.
system_promptModel accepts a separate system message distinct from the user message.
vision_inputModel accepts image inputs alongside text.
audio_inputModel accepts audio input.
document_understandingModel accepts native document files (e.g. PDF) end-to-end.
embedding_max_input_tokensLongest input, in tokens, the embedding model accepts.
languagesLanguages the model supports (ISO 639-1 codes).
What the model can return: streaming, structured output, tool calls, audio.
tool_callingModel emits structured function calls per OpenAI tool-use schema.
parallel_tool_callsModel can emit ≥2 tool calls in one response. Modifier on tool_calling.
structured_outputModel returns JSON conforming to a supplied JSON Schema (constrained decoding).
json_modeModel returns syntactically valid JSON when asked. Looser legacy capability.
Operational features: prompt caching, long context, batch inference.
Agent features: function calling, code execution, retrieval, browsing.
web_search_nativeProvider offers a native web-search tool exposed through the same endpoint.
code_execution_nativeProvider offers a native code-execution tool.
file_search_nativeProvider offers a native file-search / RAG primitive.
Source: the capability registry, shared by the website and the customer portal.