Loading
90 days of the enterprise, pro and team plans free, no card needed. See the plans
OpenAI
openai/gpt-4-turboCatalogue: Indexed in the reference catalogue; nothing on this deployment answers as this model yet.
Published by the vendor; the platform bills at the target's declared price.
OpenAI openai/gpt-4-turbo
The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling. Training data: up to December 2023.
GPT-4 Turbo earns a request when it needs tool calls, image input; a short, general request would go to MiniMax M3.1 Flash (free) instead - free per million input tokens against $10.0 here; and the hardest requests, where the quality floor rules it out, to Claude Opus 5.5 (batch). Your rules decide the floor; the trace shows the comparison for every request.
Lower input price and an intelligence index within 5 points.
Nothing on this deployment answers as this model yet. Connect your own provider under Model providers, or add a target to your catalogue - the router picks it up without retraining.
# targets.yaml - declare a target that runs GPT-4 Turbo
targets:
- id: gpt-4-turbo
kind: llm
name: GPT-4 Turbo
metadata:
model: openai/gpt-4-turbo # links the target to this catalogue entry
capabilities:
domains: [general]
supports_tools: true
context_window: 128000
cost:
usd_per_1k_tokens: 0.020000Input list price per million tokens; GPT-4 Turbo is the most expensive of 13 listed.
Photo: RDNE Stock project
A higher intelligence index, best first, with the price it comes at.
Other models by the same vendor in the catalogue.
The catalogue prints input and output prices and what three typical monthly workloads cost on each.
