GPT-3.5 Turbo 16k 0613 Pricing - Cost Calculator

Track gpt-3.5-turbo-16k-0613 pricing with real-time alerts, compare providers, and monitor cost changes across long-context conversational AI workflows.

Released 13 June 2023, GPT-3.5 Turbo 16k 0613 is a text model from OpenAI that has been deprecated. It was replaced by GPT-3.5 Turbo on 13 September 2024. The context window holds 16,384 tokens. It costs between $1.50 and $3.00 per million input tokens, depending on service tier.

Last updated Sep 27, 2026

Never miss an AI pricing or launch update

Get notified about new model launches, pricing changes, provider updates, deprecations, and cost-saving insights.

🔒 We respect your privacy. Unsubscribe anytime.

Model Details

Released
Jun 13, 2023
Status
Deprecated(on Sep 13, 2024)
Context Length
16,384
Superseded By
GPT-3.5 Turbo

Where is GPT-3.5 Turbo 16k 0613 a perfect fit?

gpt-3.5-turbo-16k-0613 is built for applications needing larger context windows along with early function-calling support. Ideal for:
- Long document summarisation and analysis
- Multi-turn conversations with extended memory
- Processing large prompts such as reports, logs, or transcripts
- Early tool-calling and function-based workflows
- Backend systems requiring more context than standard 4k models
- Applications handling continuous conversational history

Quick Model Estimate

(USD 3.0000 per 1M tokens)
(USD 4.0000 per 1M tokens)

Your GPT-3.5 Turbo 16k 0613 Cost Estimate

💰 Total Cost

—

for 1000 input + 1000 output tokens

📥 Input (1000 × $3.000000) —
📤 Output (1000 × $4.000000) —

Cost Breakdown

📥 Input 📤 Output

Prices are watched for changes and checked against the provider's own page.

Pricing

Provider ↕
Modality ↕
Service Tier ↕
Input Price
(per 1M tokens) ↕
Output Price
(per 1M tokens) ↕
Context Size ↕
View
OpenAI LogoOpenAITextStandard$3.0000$4.000016,384 tokens→
OpenAI LogoOpenAITextBatch$1.5000$2.000016,384 tokens→

Other Models in the GPT-3.5 Family

GPT-3.5 0301

Active

Text · 4,091 context

GPT-3.5 Turbo

Legacy

Text · 16,384 context

GPT-3.5 Turbo 0125

Legacy

Text · 16,384 context

GPT-3.5 Turbo 0613

Deprecated

Text · 4,096 context

GPT-3.5 Turbo 1106

Deprecated

Text · 16,384 context

GPT-3.5 Turbo Instruct

Deprecated

Text · 4,096 context

GPT-3.5 Turbo Legacy

Deprecated

Fine-tuning · 16,384 context

FAQs about GPT-3.5 Turbo 16k 0613

How much does GPT-3.5 Turbo 16k 0613 cost per 1M tokens?

GPT-3.5 Turbo 16k 0613 costs between $1.50 and $3.00 per million input tokens, and between $2.00 and $4.00 per million output tokens. The range covers Standard and Batch pricing.

What does a typical workload cost with GPT-3.5 Turbo 16k 0613?

1,000 requests of 2,000 input and 500 output tokens each — 2,000,000 input and 500,000 output tokens in total — costs $4.00 with GPT-3.5 Turbo 16k 0613 at its lowest rates. Use the calculator on this page for your own volumes.

Where can I use GPT-3.5 Turbo 16k 0613?

GPT-3.5 Turbo 16k 0613 is available through OpenAI, from $1.50 per million input tokens.

Is there cheaper GPT-3.5 Turbo 16k 0613 pricing than the standard rate?

Yes. Batch pricing for GPT-3.5 Turbo 16k 0613 starts at $1.50 per million input tokens against $3.00 on the standard tier, about 50% lower.

What is GPT-3.5 Turbo 16k 0613's context window?

GPT-3.5 Turbo 16k 0613 has a context window of 16,384 tokens.

Is GPT-3.5 Turbo 16k 0613 still available?

GPT-3.5 Turbo 16k 0613 is deprecated and was retired on 13 September 2024. The replacement is GPT-3.5 Turbo.