Skip to content

OpenAI · Chat

GPT 35 Turbo 16k

OpenAI 🇺🇸ChatGPT familyOne of its sources says the weights aren't publicly available.The maker lists this model as deprecated (23 Oct 2026).
From Aiml API's listing:
Fast and cost-efficient OpenAI model for a wide range of text generation and conversation tasks.
Maker's price
$1.625 blended / 1M
Max context
16K
Listings
21
Providers
11

Evidence and sources

Training-data cutoff, as its sources state it Maker HQ: US (according to OpenAI's own website)
All rankings: #543 on OpenRouter this week #546 on OpenRouter today #576 on OpenRouter this monthSources: Azure Prices API data, LiteLLM data, Models.dev data, AI/ML API data, OpenRouter data docsPrimary data from Azure Prices API from LiteLLM: deprecation date from Models.dev: weights availability from AI/ML API: primary mode, description from OpenRouter: knowledge cutoff

Advantages and trade-offs

Compared with 10 representative chat models

Trade-offs

Deprecated by its maker

The maker has already deprecated this model (23 Oct 2026).

No open weights

The weights aren't public, so you can't run it yourself.

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 06:07 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 7 maker's prices.

Input & output

as stated by the model's providers
Text
Files
Text

Capabilities

Supported operations and provider-stated features

Function callingStructured outputPrompt caching

Listings

 OpenAIgpt-35-turbo-16k-batch · batchSource: Helicone Costs dataNot published by the provider$1.50$2.00
 Microsoft Azuregpt-35-turbo-16k-0125 · 0125Source: Azure Prices API dataNot published by the provider$0.55$1.65
 Microsoft Azuregpt-35-turbo-16k-1106 · 1106Source: Azure Prices API dataNot published by the provider$1.10$2.20
 OpenAIgpt-3.5-turbo-16k-0613-batch · batch, 0613Source: Helicone Costs dataNot published by the provider$1.50$2.00
 Aihubmixgpt-3.5-turbo-16kSource: AIHubMix data docsNot published by the provider$3.00$4.00
 Fastrouteropenai/gpt-3.5-turbo-16kSource: FastRouter data16K$3.00batch $1.50$4.00batch $2.00
 Flowdotopenai/gpt-3.5-turbo-16kSource: FlowDot data16K$3.00$4.00
 Kiloopenai/gpt-3.5-turbo-16kSources: Kilo AI Gateway data, Models.dev data16K$3.00$4.00
 Nous Portalopenai/gpt-3.5-turbo-16kSource: Nous Portal Inference Gateway data16K$3.00$4.00
 OpenRouterInference by Microsoft Azureopenai/gpt-3.5-turbo-16kSource: OpenRouter data docs16K$3.00$4.00
Show all 17 listings

Showing 10 of 17: the maker's own listing first, then the cheapest per 1M input tokens from each provider.

4 listings without a price are hidden.

These providers advertise this model. Researchers have found some resellers serving a different, cheaper model, so see how to check whether a provider meets your needs.

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Agentic

Data credits: Steel.dev Agent Leaderboards, MIT (licence)

Around the web

  • GPT-3.5 Turbo Model | OpenAI API
    GPT-3.5 Turbo For the complete documentation index, see llms.txt. Markdown versions of documentation pages are …GPT-3.5 Turbo For the complete documentation index, see llms.txt. Markdown versions of documentation pages are available by appending .md to the page URL. Legacy GPT model for cheaper chat and non-ch…

    developers.openai.com

  • GPT-3.5 Turbo fine-tuning and API updates | OpenAI
    Skip to main content Research Products Business Developers Company Foundation (opens in a new window) …Skip to main content Research Products Business Developers Company Foundation (opens in a new window) Log in Try ChatGPT (opens in a new window) Research Products Business Developers Company Foundati…

    openai.com

  • While anticipation builds for GPT-4, OpenAI quietly releases GPT-3.5 | TechCrunch
    Apps While anticipation builds for GPT-4, OpenAI quietly releases GPT-3.5 Kyle Wiggers 4:08 PM PST …Apps While anticipation builds for GPT-4, OpenAI quietly releases GPT-3.5 Kyle Wiggers 4:08 PM PST · December 1, 2022 According to OpenAI, GPT-3.5 was trained on a blend of text and code published pr…

    techcrunch.com

  • OpenAI opens GPT-3.5 Turbo up for custom tuning | The Verge
    Skip to main content OpenAI opens GPT-3.5 Turbo up for custom tuning AI Business News …Skip to main content OpenAI opens GPT-3.5 Turbo up for custom tuning AI Business News OpenAI opens GPT-3.5 Turbo up for custom tuning Illustration: The Verge Part Of From ChatGPT to Gemini: how AI is…

    theverge.com

  • gpt-3.5-turbo-instruct Model | OpenAI API
    Supported features fine_tuning Quick comparison Model · Input · Cached input · Output gpt-3.5-turbo-instruct · …Supported features fine_tuning Quick comparison Model · Input · Cached input · Output gpt-3.5-turbo-instruct · $1.5 · - · $2 GPT-4o mini · $0.15 · $0.075 · $0.6 o3-mini · $1.1 · $0.55 · $4.4 Snapshot…

    developers.openai.com

  • OpenAI GPT-3.5
    General · Relese date · March 15, 2022 Author · OpenAI Type · Autoregressive, Transformer, …General · Relese date · March 15, 2022 Author · OpenAI Type · Autoregressive, Transformer, Language model Start building with OpenAI GPT-3.5 OpenAI GPT-3 has a rich ecosystem of libraries and resourc…

    lablab.ai

  • OpenAI partners with Scale AI to allow companies to fine-tune GPT-3.5 | TechCrunch
    OpenAI logo with colorful, symmetrical background Image Credits: Bryce Durbin / TechCrunch AI OpenAI partners …OpenAI logo with colorful, symmetrical background Image Credits: Bryce Durbin / TechCrunch AI OpenAI partners with Scale AI to allow companies to fine-tune GPT-3.5 Kyle Wiggers 8:00 AM PDT · August 2…

    techcrunch.com

  • Switching from GPT-4 to GPT-3.5: prompting best practices - Prompting - OpenAI Developer Community
    Prompting gpt-4 , gpt-35-turbo stasbichenko July 6, 2023, 1:23pm 1 We’re building a long-form conversational …Prompting gpt-4 , gpt-35-turbo stasbichenko July 6, 2023, 1:23pm 1 We’re building a long-form conversational chat assistant. We built a 5000-token system prompt for GPT-4 and we’re now switching to G…

    community.openai.com

  • Why GPT-3.5 Deprecated? And what will happen now? - ChatGPT - OpenAI Developer Community
    Topic · Replies · Views · Activity Pleading with Openai Developers to not retire gpt-3.5-turbo-0613 …Topic · Replies · Views · Activity Pleading with Openai Developers to not retire gpt-3.5-turbo-0613 on June 13th Deprecations api · 19 · 4.5k · Jun 2024 Deprecation of chat-gpt-4o-latest Deprecations…

    community.openai.com

  • GPT-3.5 vs. GPT-4: Biggest differences to consider | TechTarget
    conversations, and document search and analysis. Capabilities. GPT-3.5 was trained on 175 billion parameters, while …conversations, and document search and analysis. Capabilities. GPT-3.5 was trained on 175 billion parameters, while GPT-4 was trained on a parameter close to 1 trillion. **GPT-4 ** OpenAI designed GP…

    techtarget.com

Also known as: gpt-3.5-turbo-16k-0613, gpt-35-turbo-16k, gpt-35-turbo-16k-0125, gpt-35-turbo-16k-0613, gpt-35-turbo-16k-1106, gpt-35-turbo16k, gpt-35-turbo16k-0125, gpt-35-turbo16k-1106, openai/gpt-3.5-turbo-16k

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works