GPT-3.5 Turbo: API Pricing, Context Window & Benchmarks
GPT-3.5 Turbo is a language model from OpenAI, released in March 2023, with a 16K-token context window, and pricing from $0.500/M input and $1.50/M output.
The latest GPT-3.5 Turbo model with higher accuracy at responding in requested formats and a fix for a bug which caused a text encoding issue for non-English language function calls.
GPT-3.5 Turbo benchmarks
Rankings
Quality Tracker
GPT-3.5 Turbo Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Sat Jul 18 2026GPT-3.5 Turbo pricing
Providers
GPT-3.5 Turbo starts at $0.500 per million input tokens and $1.50 per million output tokens via Azure. See all 2 providers below with their per-token pricing, latency, throughput, and modality support.
| Provider | Input $/M | Output $/M | Workload 1M + 100K | Context in / out | TTFT p50 / p95 s | Output avg / p5 c/s | Success 7d | Modalities in / out |
|---|---|---|---|---|---|---|---|---|
 Azure | $0.500 | $1.50 | $0.650 | 16.4K/4.1K | —/0.80 | 90/— | — | / |
 OpenAI | $0.500 | $1.50 | $0.650 | 16.4K/4.1K | 1.50/2.95 | 279/175 | 97.06%(34) | / |
Workload cost uses 1M input tokens plus 100K output tokens at published list prices without assuming a cache hit. Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests. Success is calculated from completed versus failed requests over the trailing seven days.
GPT-3.5 Turbo context window
Input and output token limits for GPT-3.5 Turbo, plus how it ranks on long-context understanding.
GPT-3.5 Turbo API
Run a request to see the response
Use it in your code
Billed at $0.50 input / $1.50 output per 1M tokens through the LLM Stats gateway.
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://gateway.llm-stats.com/v1"
)
response = client.chat.completions.create(
model="gpt-3.5-turbo-0125",
messages=[
{"role": "user", "content": "What is machine learning?"}
]
)
print(response.choices[0].message.content)Need an API key? Create one above in the playground, or read the API documentation.
GPT-3.5 Turbo latency
GPT-3.5 Turbo time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.
Provider operational metrics
Time to first token, output throughput, and failed-request rate from live API traffic
GPT-3.5 Turbo examples
Recent arena outputs from GPT-3.5 Turbo, picked from the highest-ranked matchups.
GPT-3.5 Turbo license
GPT-3.5 Turbo is a proprietary model available under its provider's product and API terms, has a knowledge cutoff of September 2021.
- License
- Proprietary
- Hosted access
- Knowledge cutoff
- September 2021
Proprietary license - usage restrictions apply
GPT-3.5 Turbo resources
Official sources for GPT-3.5 Turbo: api documentation, official playground, official launch post.
GPT-3.5 Turbo vs other models
The most-compared alternatives to GPT-3.5 Turbo are GPT-4, Claude 3 Sonnet, Gemma 2 27B. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like GPT-3.5 Turbo
Models ranked just above and below GPT-3.5 Turbo by LLM Stats score.
FAQ
Common questions about GPT-3.5 Turbo.