← Back to Directory

GPT-3.5 Turbo (older v0613)

OPENAI Developer Architecture Profile

OpenRouter ↗HuggingFace ↗
Intelligence (ELO)1431Aider: 38.3%
Max Context Limit4,095Max Out: 3,685 tokens
Prompt CachingStandardNo Cache Discount
Standard API / 1M$3.00Blended Standard Rate

Model Capabilities & Contract SLAs

  • Coding & Logic
  • Fictional
GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks. Training data up to Sep 2021.

Granular Pricing Matrix

Input Tokens (Standard Prompt)$1.00 / 1M
Output Tokens (Completion)$2.00 / 1M

Pricing data via OpenRouter. Sync: 10/2/2026

Evaluate Competitors

VS Engine MatchupGPT-3.5 Turbo (older v0613) vs Mistral: Mistral Medium 3.5 (batch)VS Engine MatchupGPT-3.5 Turbo (older v0613) vs OpenAI: GPT Mini LatestVS Engine MatchupGPT-3.5 Turbo (older v0613) vs SpaceXAI: Grok 4.20 Multi-AgentVS Engine MatchupGPT-3.5 Turbo (older v0613) vs Qwen: Qwen3 Coder 30B A3B InstructVS Engine MatchupGPT-3.5 Turbo (older v0613) vs Qwen: Qwen3 235B A22BVS Engine MatchupGPT-3.5 Turbo (older v0613) vs OpenAI: o3