impulse

GPT-3.5 Turbo Instruct

Frontier lab
API id gpt-3.5-turbo-instruct
Input / 1M
$1.50
at OpenAI
Output / 1M
$2.00
at OpenAI
Context window
8K
tokens
Max output
4K
tokens per reply
Hosts
3
6 listings
Released
-
date not published

Pricing

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

TierInput / 1MOutput / 1M
Standard$1.50$2.00

What it costs a month

At OpenAI list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$600
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$792
  • Coding agent1,000 requests a day, 40K in / 2K out$1,920
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$4,080
Use your own numbers

Where to run it

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

HostIn / out per 1M
OpenAILab API
gpt-3.5-turbo-instruct
$1.50 / $2.00
gpt-3.5-turbo-instruct
$1.50 / $2.00
gpt-35-turbo-instruct
$1.65 / $2.20
+10% vs headline
Show 3 more listings: regions, snapshots and variants
OpenAI
0914
gpt-3.5-turbo-instruct-0914
$1.50 / $2.00
Azure AI Language
0914
gpt-35-turbo-instruct-0914
$1.65 / $2.20
+10% vs headline
0914
gpt-3.5-turbo-instruct-0914
$1.65 / $2.20
+10% vs headline

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

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
    72% less
  • GPT-6 Luna
    OpenAI · on OpenAI
    $0.10 / $0.50
    Has every key capability
    88% less
  • GPT-4o Mini
    OpenAI · on OpenAI
    $0.15 / $0.60
    Has every key capability
    84% less

Other frontier labs

Open-weight picks

  • Motif 3
    Independent · on ai&
    $0.50 / $2.00
    Has every key capability
    46% less
  • GLM 5.3
    Zhipu AI · on CLF AI Gateway
    $0.56 / $1.76
    Has every key capability
    47% less
  • Nemotron 3 Ultra 550B A55B
    NVIDIA · on Perplexity
    $0.25 / $2.50
    Has every key capability
    50% less
  • DeepSeek V4 Pro
    DeepSeek · on CLF AI Gateway
    $0.528 / $1.58
    Has every key capability
    51% less

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-instruct", input="Hello")
print(response.output_text)

Quick answers

How much does GPT-3.5 Turbo Instruct cost?

On OpenAI, GPT-3.5 Turbo Instruct costs $1.50 per million input tokens and $2.00 per million output tokens.

Which APIs offer GPT-3.5 Turbo Instruct?

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

What is GPT-3.5 Turbo Instruct's context window?

8K tokens, with up to 4K tokens in one reply.

Is GPT-3.5 Turbo Instruct being retired?

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

What are cheaper alternatives to GPT-3.5 Turbo Instruct?

Models that cost less and keep most of what it can do: GPT-5.4 Nano on OpenAI (72% less), Grok 4.20 Multi Agent on xAI (4% less), Gemini 3.8 Flash on Google AI Studio (8% less) and Motif 3 on ai& (46% less). Savings are on a mix of 3 input tokens to 1 output token.

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

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

Sources

Raw catalog entry for gpt-3.5-turbo-instruct on OpenAI
{
  "deprecation_date": "2026-09-28",
  "deprecation_source": "https://developers.openai.com/api/docs/deprecations",
  "successor_model": "gpt-5.6-terra",
  "input_cost_per_token": 0.0000015,
  "litellm_provider": "text-completion-openai",
  "max_input_tokens": 8192,
  "max_output_tokens": 4096,
  "mode": "completion",
  "output_cost_per_token": 0.000002,
  "source": "https://developers.openai.com/api/docs/pricing"
}