# Text-davinci-003 api pricing?

**URL:** https://community.openai.com/t/text-davinci-003-api-pricing/373376
**Category:** API
**Tags:** pricing, gpt-3
**Created:** [September 14, 2023, 8:47pm UTC](https://community.openai.com/t/text-davinci-003-api-pricing/373376 "2023-09-14T20:47:08Z")
**Posts on this page:** 9
**Page:** 1

<div class="post-metadata">

### Author: ![gianlucaa](https://avatars.discourse-cdn.com/v4/letter/g/b38774/32.png) [@gianlucaa](https://community.openai.com/u/gianlucaa)
#### Post date: [September 14, 2023, 8:47pm UTC](https://community.openai.com/t/text-davinci-003-api-pricing/373376/1 "2023-09-14T20:47:08Z")

</div>

I am using the text-davinci-003 model in Python.

```auto
response = openai.Completion.create(
     engine="text-davinci-003",
     prompt=question,
     max_tokens=100
)

```

I am finding the amount of tokens via: `print(response.usage.total_tokens)`. I cannot find for the life of me the pricing for text-davinci-003 model, only some forum I read that it is 0.0120 / 1000k tokens. so based on this calculation, for my most recent request at 403 tokens, I should be being charged 0.004884 for the request. however, when I go into my billing dashboard, I see it went up by 1 cent. just trying to figure out the total cost. Thanks for the help in advance.

---

<div class="post-metadata">

### Author: ![jochenschultz](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/jochenschultz/32/491030_2.png) [@jochenschultz](https://community.openai.com/u/jochenschultz)
#### Post date: [September 14, 2023, 8:50pm UTC](https://community.openai.com/t/text-davinci-003-api-pricing/373376/2 "2023-09-14T20:50:30Z")

</div>

Did you count the request tokens + completion = total\_tokens?

---

<div class="post-metadata">

### Author: ![anon22939549](https://avatars.discourse-cdn.com/v4/letter/a/f14d63/32.png) [@anon22939549](https://community.openai.com/u/anon22939549)
#### Post date: [September 14, 2023, 8:51pm UTC](https://community.openai.com/t/text-davinci-003-api-pricing/373376/3 "2023-09-14T20:51:01Z")

</div>

[https://platform.openai.com/docs/deprecations/](https://platform.openai.com/docs/deprecations/)

> text-davinci-003 $0.0200 / 1K tokens

403 \text{ tokens} \times \$0.02 / 1000 = \$0.00806

It is reasonable to think there may have been some fractional amount previously billed or simple rounding caused the amount used to de displayed as an additional cent.

You absolutely are right to expect billing to be fair and transparent, _but_…

Worrying because your displayed usage went up one cent after using eight-tenths of a cent, is a _whole nother level_ of penny-pinching.

You’re fine, the billing is fine, when you’re dealing with low usage you should expect the amount shown in your billing dashboard to not be sub-cent accurate.

---

<div class="post-metadata">

### Author: ![gianlucaa](https://avatars.discourse-cdn.com/v4/letter/g/b38774/32.png) [@gianlucaa](https://community.openai.com/u/gianlucaa)
#### Post date: [September 14, 2023, 8:51pm UTC](https://community.openai.com/t/text-davinci-003-api-pricing/373376/4 "2023-09-14T20:51:42Z")

</div>

sorry, what do you mean? I just assumed that response.usage.total\_tokens was the total tokens from the response of the completion request.

---

<div class="post-metadata">

### Author: ![jochenschultz](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/jochenschultz/32/491030_2.png) [@jochenschultz](https://community.openai.com/u/jochenschultz)
#### Post date: [September 14, 2023, 8:53pm UTC](https://community.openai.com/t/text-davinci-003-api-pricing/373376/5 "2023-09-14T20:53:03Z")

</div>

Ah, ok, then please have a look at @anon22939549’s reply. Seems like everything was ok.

---

<div class="post-metadata">

### Author: ![gianlucaa](https://avatars.discourse-cdn.com/v4/letter/g/b38774/32.png) [@gianlucaa](https://community.openai.com/u/gianlucaa)
#### Post date: [September 14, 2023, 8:53pm UTC](https://community.openai.com/t/text-davinci-003-api-pricing/373376/6 "2023-09-14T20:53:52Z")

</div>

interesting, can’t believe I didn’t find this before. thanks!

---

<div class="post-metadata">

### Author: ![goldobinp](https://avatars.discourse-cdn.com/v4/letter/g/e56c9b/32.png) [@goldobinp](https://community.openai.com/u/goldobinp)
#### Post date: [May 5, 2024, 4:01pm UTC](https://community.openai.com/t/text-davinci-003-api-pricing/373376/7 "2024-05-05T16:01:11Z")

</div>

Afternoon. ChatGPT-3.5 suggested to use the “text-davinci-004” model to the API to analyze my 3000 token scientific text. Under [https://platform.openai.com/docs/deprecations](https://platform.openai.com/docs/deprecations) I can’t find the price unfortunately. Please help - provide a price list for using the “text-davinci-004” and “davinci-codex” model. Thank you for your time and help.

---

<div class="post-metadata">

### Author: ![anon22939549](https://avatars.discourse-cdn.com/v4/letter/a/f14d63/32.png) [@anon22939549](https://community.openai.com/u/anon22939549)
#### Post date: [May 8, 2024, 2:11am UTC](https://community.openai.com/t/text-davinci-003-api-pricing/373376/8 "2024-05-08T02:11:01Z")

</div>

These models do not exist. ChatGPT is hallucinating.

All of the models and their prices are listed here,

[https://openai.com/api/pricing](https://openai.com/api/pricing)

---

<div class="post-metadata">

### Author: ![anon22939549](https://avatars.discourse-cdn.com/v4/letter/a/f14d63/32.png) [@anon22939549](https://community.openai.com/u/anon22939549)
#### Post date: [May 8, 2024, 2:11am UTC](https://community.openai.com/t/text-davinci-003-api-pricing/373376/9 "2024-05-08T02:11:12Z")

</div>


