impulse

GPT-3.5 Turbo

Frontier lab

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.

API id gpt-3.5-turboReleased 25 Jan 2024 (Jan 2024)
Input / 1M
$0.50
at OpenAI
Output / 1M
$1.50
at OpenAI
Context window
16K
tokens
Max output
4K
tokens per reply
Hosts
3
12 listings
Released
Jan 2024
25 Jan 2024

Pricing

List prices at OpenAI, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.50$1.50

What it costs a month

At OpenAI list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$263
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$294
  • Coding agent1,000 requests a day, 40K in / 2K out$690
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$1,560
Use your own numbers

Where to run it

3 hosts serve GPT-3.5 Turbo. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
OpenAILab API
gpt-3.5-turbo
$0.50 / $1.50
gpt-35-turbo
$0.50 / $1.50
gpt-3.5-turbo
$0.50 / $1.50
GitHub CopilotSubscription
gpt-3.5-turbo
In the subscription
Show 8 more listings: regions, snapshots and variants
OpenAI
0125
gpt-3.5-turbo-0125
$0.50 / $1.50
1106
gpt-3.5-turbo-1106
$1.00 / $2.00
+67% vs headline
fine-tuning
ft:gpt-3.5-turbo
$3.00 / $6.00
0125 · fine-tuning
ft:gpt-3.5-turbo-0125
$3.00 / $6.00
0613 · fine-tuning
ft:gpt-3.5-turbo-0613
$3.00 / $6.00
1106 · fine-tuning
ft:gpt-3.5-turbo-1106
$3.00 / $6.00
Azure OpenAI
Alias
gpt-3.5-turbo
$0.50 / $1.50
GitHub Copilot
0613
gpt-3.5-turbo-0613
In the subscription

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
Text
Produces
Text
Features
Prompt caching

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than OpenAI.

Smaller OpenAI models

  • GPT-5.4 Nano
    OpenAI · on OpenAI
    $0.20 / $1.25
    Has every key capability
    38% less
  • GPT-6 Luna
    OpenAI · on OpenAI
    $0.10 / $0.50
    Has every key capability
    73% less
  • GPT-4o Mini
    OpenAI · on OpenAI
    $0.15 / $0.60
    Has every key capability
    65% less

Other frontier labs

  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    73% less

Open-weight picks

  • Kimi K2.7 Code
    Moonshot AI · on CLF AI Gateway
    $0.38 / $1.60
    Has every key capability
    9% less
  • Inkling Small
    Independent · on DeepInfra
    $0.45 / $1.20
    Has every key capability
    15% less
  • DeepSeek Flash
    DeepSeek · on DeepSeek
    $0.30 / $1.20
    Has every key capability
    30% less
  • Qwen3.7 Plus
    Alibaba Qwen · on Replicate
    $0.276 / $1.10
    Has every key capability
    36% less

Model line

Newer and older versions, at each lab's own price.

  1. Apr 2024GPT-4 Turbo$10.00 / $30.00
  2. Jan 2024GPT-3.5 TurboThis page$0.50 / $1.50

Call it

Using OpenAI's API.

Python
from openai import OpenAI

client = OpenAI()  # reads OPENAI_API_KEY

response = client.responses.create(model="gpt-3.5-turbo", input="Hello")
print(response.output_text)

Quick answers

How much does GPT-3.5 Turbo cost?

On OpenAI, GPT-3.5 Turbo costs $0.50 per million input tokens and $1.50 per million output tokens.

Which APIs offer GPT-3.5 Turbo?

GPT-3.5 Turbo runs on 3 APIs: OpenAI, Azure OpenAI and Vercel AI Gateway.

What is GPT-3.5 Turbo's context window?

16K tokens, with up to 4K tokens in one reply.

Is GPT-3.5 Turbo being retired?

No retirement date is scheduled for it on any API we track.

What are cheaper alternatives to GPT-3.5 Turbo?

Models that cost less and keep most of what it can do: GPT-5.4 Nano on OpenAI (38% less), Claude Haiku 5.5 on Anthropic (73% less) and Kimi K2.7 Code on CLF AI Gateway (9% less). Savings are on a mix of 3 input tokens to 1 output token.

When was GPT-3.5 Turbo released?

OpenAI released it on 25 Jan 2024.

What is GPT-3.5 Turbo's API model id?

Use gpt-3.5-turbo with OpenAI. Other hosts use their own ids: gpt-35-turbo on Azure OpenAI.

Sources

Raw catalog entry for gpt-3.5-turbo on OpenAI
{
  "deprecation_date": "2026-10-23",
  "deprecation_source": "https://developers.openai.com/api/docs/deprecations",
  "successor_model": "gpt-5.6-terra",
  "input_cost_per_token": 5e-7,
  "litellm_provider": "openai",
  "max_input_tokens": 16385,
  "max_output_tokens": 4096,
  "mode": "chat",
  "output_cost_per_token": 0.0000015,
  "fedramp_uplift_multiplier": 1.1,
  "source": "https://developers.openai.com/api/docs/pricing",
  "supports_function_calling": true,
  "supports_prompt_caching": true,
  "supports_system_messages": true,
  "supports_tool_choice": true
}