GPT-3.5 Turbo API: OpenAI's chat / LLM model, one key away
GPT-3.5 Turbo via the ApexApi gateway
The model that made cheap chat ordinary. Long since beaten on price and quality by small GPT-5 tiers; kept for legacy integrations. Call it through ApexApi's unified, OpenAI-compatible API with one `ak-` key, alongside every other model in the catalog. It supports a 16,385-token context window, tool / function calling, and streaming responses. Pricing is $0.60 input and $1.80 output per 1M tokens, billed pay-per-use from your credit balance with no subscription.
GPT-3.5 Turbo is served through ApexApi's unified, OpenAI-compatible API. One key, one format, with smart routing and automatic failover. Provider: OpenAI.
Why GPT-3.5 Turbo
16,385-token context
Reason over long documents, codebases, and multi-turn history in a single request.
Tool & function calling
Structured outputs and tool orchestration for agentic and automation workloads.
OpenAI-compatible
Drop-in with any OpenAI SDK. Change the base URL and key, keep your code.
Specifications
- Modality
- chat
- Context window
- 16.4K tokens
- Max output
- 4.1K tokens
- Streaming
- Yes
- Tool / function calling
- Yes
- Vision input
- —
GPT-3.5 Turbo: measured reliability
From real calls ApexApi made to GPT-3.5 Turbo during health sweeps over the last 30 days. Our own measurements, not vendor claims.
- Success rate
- 100%
- Avg latency
- 3.8s
- Calls measured
- 1
- Last checked
- Aug 30
See how GPT-3.5 Turbo compares against every model we serve on the model rankings.
GPT-3.5 Turbo pricing
- A million tokens in and a million out costs $2.40 here, all-in.
- That makes it the 26th cheapest of the 81 chat models we serve, ranked on output price.
- It runs 40.0× cheaper than GPT-4, the pricier option from the same maker.
Getting started with GPT-3.5 Turbo
OpenAI-compatible. Point your client at ApexApi, swap your key, and call it. No new SDK to learn.
from openai import OpenAI
client = OpenAI(
base_url="https://api.apexapi.dev/v1",
api_key="<YOUR_APEXAPI_KEY>",
)
response = client.chat.completions.create(
model="openai/gpt-3.5-turbo",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)GPT-3.5 Turbo use cases
What teams build with GPT-3.5 Turbo on ApexApi.
Agents & automation
Tool-using agents that orchestrate multi-step workflows and call APIs.
Coding assistants
Code generation, refactoring, reviews, and multi-file reasoning.
RAG & knowledge apps
Summarization and long-document Q&A grounded in your own data.
GPT-3.5 Turbo vs other models
How it compares, and on ApexApi you can switch between any of them with a single string change, same key, same endpoint.
GPT-3.5 Turbo vs Claude Opus 4.7
Compare GPT-3.5 Turbo against this model on price, capabilities, and latency. A/B them with a single key on ApexApi.
Learn more about Claude Opus 4.7 API →GPT-3.5 Turbo vs GPT-5.5
Compare GPT-3.5 Turbo against this model on price, capabilities, and latency. A/B them with a single key on ApexApi.
Learn more about GPT-5.5 API →GPT-3.5 Turbo vs Gemini 3.1 Pro Preview
Compare GPT-3.5 Turbo against this model on price, capabilities, and latency. A/B them with a single key on ApexApi.
Learn more about Gemini 3.1 Pro Preview API →GPT-3.5 Turbo API: FAQ
How do I call GPT-3.5 Turbo through ApexApi?
Create an ApexApi key, point your client at https://api.apexapi.dev/v1, and POST to /v1/chat/completions with the model set to `openai/gpt-3.5-turbo`. The API is OpenAI-compatible, so an existing OpenAI SDK works once you change the base URL and key.
How much does GPT-3.5 Turbo cost on ApexApi?
$0.60 per million input tokens and $1.80 per million output tokens, all-in with no separate platform fee. You buy credits and pay per call, with no subscription or minimum.
What is the context window for GPT-3.5 Turbo?
16,385 tokens. It can return up to 4,096 tokens in a single response.
Does GPT-3.5 Turbo support tool calling and image input?
GPT-3.5 Turbo supports tool / function calling and streaming responses, and it does not support image (vision) input.
What should I use instead of GPT-3.5 Turbo?
From the same maker, GPT-OSS 120B costs less for lighter work and GPT-3.5 Turbo 16k is the step up when this one falls short. Switching is one string: both run on the same endpoint and the same key, so there is nothing to re-integrate.
Ready to build with GPT-3.5 Turbo?
One API key. Every major AI model. Pay only for what you use.
Get your API key, free to start