OpenAI: GPT-4 Turbo is an API-access large language model from Openai priced at $10.00/1M input tokens and $30.00/1M output tokens with a 128k context window. Context caching reduces input costs to $5.00/1M for cache reads. Supported capabilities include tool calling.
Economics (OpenRouter)
Input / 1M
$10.00
Output / 1M
$30.00
Est. Monthly Cost
$513.00
Based on current usage settings
Cache Read$5.00
Cache Write$12.50
Capabilities (models.dev)
ReasoningNo
Tool CallSupported
Audio InNo
Audio OutNo
Modalitymultimodal
Context Window128k
Benchmarks (AA)
Intelligence Index
General reasoning and knowledge
—
Coding Index
Code generation & debugging
—
Math Index
Mathematical reasoning
—
Performance
—tokens/sec
* Median output throughput
Model ID: openai/gpt-4-turbo • Data Sources: OpenRouter, Artificial Analysis, models.dev