Nexia bot | Limited Test
response
User input
notifications
-
Auto model-select – simple heuristic:
gpt-4.1-mini for short / factual prompts,
escalate to gpt-4.1 when the prompt is long (> 40 words) or contains keywords analyse, strategy, compare, optimise, legal, regulation. -
Temperature – 0.7 for mini, 0.3 for 4.1.
Both use max_tokens.
GPT-4o mini (“o” for “omni”) is a fast, affordable small model for focused tasks. It accepts both text and image inputs, and produces text outputs (including Structured Outputs). It is ideal for fine-tuning, and model outputs from a larger model like GPT-4o can be distilled to GPT-4o-mini to produce similar results at lower cost and latency.
$0.15 • $0.6
128,000 context window
16,384 max output tokens
Oct 01, 2023 knowledge cutoff
GPT-4.1 is our flagship model for complex tasks. It is well suited for problem solving across domains.
$2 • $8
1,047,576 context window
32,768 max output tokens
Jun 01, 2024 knowledge cutoff
OpenAI o4-mini
Our faster, cost-efficient reasoning model delivering strong performance on math, coding and vision
Price Input: $1.100 / 1M tokens Cached input: $0.275 / 1M tokens Output:$4.400 / 1M tokens
OpenAI o3
Our most powerful reasoning model with leading performance on coding, math, science, and vision
Price Input: $10.00 / 1M tokens Cached input: $2.50 / 1M tokens Output: $40.00 / 1M tokens
