GPT-3.5 Turbo 16K
This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost.
gpt-3.5-turbo-16kReleased 28 Aug 2023 (Aug 2023)Pricing
List prices at OpenAI, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $3.00 | $4.00 |
What it costs a month
At OpenAI list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out$1,200
- RAG over documents2,000 requests a day, 8K in / 0.6K out$1,584
- Coding agent1,000 requests a day, 40K in / 2K out$3,840
- Overnight batch20,000 requests a day, 4K in / 0.4K out$8,160
Where to run it
1 host serve GPT-3.5 Turbo 16K. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
OpenAILab API gpt-3.5-turbo-16k | $3.00 / $4.00 | gpt-3.5-turbo-16k |
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
- 38% less
- 48% less
- 86% less
Other frontier labs
- 8% less
- 8% less
- 94% less
- 54% less
Open-weight picks
- 8% less
- 38% less
- 47% less
- 74% less
Call it
Using OpenAI's API.
from openai import OpenAI
client = OpenAI() # reads OPENAI_API_KEY
response = client.responses.create(model="gpt-3.5-turbo-16k", input="Hello")
print(response.output_text)curl https://api.openai.com/v1/responses \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "gpt-3.5-turbo-16k", "input": "Hello"}'from litellm import completion
response = completion(
model="openai/gpt-3.5-turbo-16k",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does GPT-3.5 Turbo 16K cost?
On OpenAI, GPT-3.5 Turbo 16K costs $3.00 per million input tokens and $4.00 per million output tokens.
Which APIs offer GPT-3.5 Turbo 16K?
GPT-3.5 Turbo 16K runs on 1 API: OpenAI.
What is GPT-3.5 Turbo 16K's context window?
16K tokens, with up to 4K tokens in one reply.
Is GPT-3.5 Turbo 16K being retired?
It has been retired: OpenAI retired it on 23 Oct 2026.
What are cheaper alternatives to GPT-3.5 Turbo 16K?
Models that cost less and keep most of what it can do: GPT-6.1 Terra on OpenAI (38% less), Gemini 4 Hydrogen on Google AI Studio (8% less), Grok 4.7 on xAI (8% less) and Qwen3.8.2 4T A95B on DeepInfra (8% less). Savings are on a mix of 3 input tokens to 1 output token.
When was GPT-3.5 Turbo 16K released?
OpenAI released it on 28 Aug 2023.
What is GPT-3.5 Turbo 16K's API model id?
Use gpt-3.5-turbo-16k with OpenAI.
Sources
Raw catalog entry for gpt-3.5-turbo-16k on OpenAI
{
"deprecation_date": "2026-10-23",
"deprecation_source": "https://developers.openai.com/api/docs/deprecations",
"input_cost_per_token": 0.000003,
"litellm_provider": "openai",
"max_input_tokens": 16385,
"max_output_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 0.000004,
"fedramp_uplift_multiplier": 1.1,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true
}