AI/ML API Inference Pricing

AI/ML API Tokens offer the flexibility to precisely allocate resources where they're most needed, enhancing performance and cost efficiency across your AI applications.

Get API Key

Utilize AI/ML Tokens across any model or mix of models.

Prices are per 1 thousand tokens including input and output tokens for Open-Source Chat, Language, and Code models. For Embedding models, only input tokens are counted, and for Image models, costs depend on the image size and processing steps.

Input price
Output price
OpenAI
GPT-4
gpt-4
gpt-4-turbo
gpt-4-0613
gpt-4-32k
gpt-4-32k-0613
gpt-4o
gpt-4o mini
gpt-4o mini 2024-07-18
1K Tokens
$0.039
$0.013
$0.039
$0.078
$0.078
$0.0065
$0.000195
$0.000195
1K Tokens
$0.078
$0.039
$0.078
$0.156
$0.156
$0.0195
$0.0009
$0.0009
OpenAI
GPT-3.5-turbo
gpt-3.5-turbo
gpt-3.5-turbo-1106
gpt-3.5-turbo-instruct
gpt-3.5-turbo-16k
gpt-3.5-turbo-0613
gpt-3.5-turbo-16k-0613
1K Tokens
$0.00065
$0.0013
$0.00195
$0.0039
$0.00195
$0.0039
1K Tokens
$0.00195
$0.0026
$0.0026
$0.0052
$0.0026
$0.0052
OpenAI
Embeddings
text-embedding-3-small
text-embedding-3-large
text-embedding-ada-002
1K Tokens
$0.000026
$0.000169
$0.00013
OpenAI Image
DALL·E
DALL·E 3 Standard
DALL·E 3 HD
DALL·E 2
256×256
512x512
$0.056
$0.063
1024x1024
1024×1792
$0.14
$0.28
$0.28
$0.42
$0.026
Anthropic
claude-3-opus
claude-3-sonnet
claude-3.5-sonnet
claude-3-haiku
1K Tokens
$0.0195
$0.0039
$0.0039
$0.000325
1K Tokens
$0.0975
$0.0195
$0.0195
$0.001625
Open Source Image
Image Models
25 Steps
50 Steps
75 Steps
100 Steps
512x512
$0.0035
$0.007
$0.01225
$0.0175
1024x1024
$0.035
$0.07
$0.1225
$0.175
Open Source LLM
Chat, Code, Language models
Model size
Up to 4B
4.1B - 8B
8.1B - 21B
21.1B - 41B
41.1B - 80B
80.1B - 110B
Llama 3.1 405B
1K Tokens (Input+Output)
$0.00013
$0.00026
$0.00039
$0.00104
$0.00117
$0.00234
$0.0065
Open Source MoE
Mixture-of-Experts
Model size
Up to 56B
56.1B - 176B
176.1B - 480B
1K Tokens
$0.00078
$0.00156
$0.00312
Open Source
Embeddings
Model size
Up to 150M
151M - 350M
1K Tokens
$0.0000104
$0.0000208
Audio Models
STT, TTS
Nova-2
Whisper-base
Whisper-large
Whisper-medium
Whisper-small
Whisper-tiny
Aura
1k characters
Pre-Recorded /  min
$0.01505
$0.01225
$0.0168
$0.0147
$0.0133
$0.01155
$0.0525
Streaming / min
$0.02065
Music Generation
Chirp-v3.5, chirp-v3.0
Suno AI
Per generation
$0.025

Utilize AI/ML Tokens across any model or mix of models.

Prices are per 1K tokens including input and output tokens for Open Source Chat, Language, and Code models. For Embedding models, only input tokens are counted, and for Image models, costs depend on the image size and processing steps.

OpenAI GPT-4

gpt-4o

Input
Output
$0.0065
1K tokens
$0.0195
1K tokens

gpt-4o mini

Input
Output
$0.000195
1K tokens
$0.0009
1K tokens

gpt-4

$0.039
1K tokens
$0.078
1K tokens

gpt-4-turbo

$0.013
1K tokens
$0.039
1K tokens

gpt-4-0613

$0.039
1K tokens
$0.078
1K tokens

gpt-4-32k

$0.078
1K tokens
$0.156
1K tokens

gpt-4-32k-0613

$0.078
1K tokens
$0.156
1K tokens

OpenAI GPT-3.5-turbo

gpt-3.5-turbo

Input
Output
$0.00065
1K tokens
$0.00195
1K tokens

gpt-4-32k-0613

$0.0013
1K tokens
$0.0026
1K tokens

gpt-3.5-turbo-instruct

$0.00195
1K tokens
$0.0026
1K tokens

gpt-3.5-turbo-16k

$0.0039
1K tokens
$0.0052
1K tokens

gpt-3.5-turbo-0613

$0.00195
1K tokens
$0.0026
1K tokens

gpt-3.5-turbo-16k-0613

$0.0039
1K tokens
$0.0052
1K tokens

OpenAI Embeddings

text-embedding-3-small

Input
$0.000026
1K tokens

text-embedding-3-large

$0.000169
1K tokens

text-embedding-ada-002

$0.00013
1K tokens

Anthropic

claude-3-opus

Input
Output
$0.0195
1K tokens
$0.0975
1K tokens

claude-3-sonnet

$0.0039
1K tokens
$0.0195
1K tokens

claude-3-haiku

$0.000325
1K tokens
$0.001625
1K tokens

Open Source Image

25 Steps

$0.0035
512x512
$0.035
1024x1024

50 Steps

$0.007
1K tokens
$0.07
1K tokens

75 Steps

$0.01225
1K tokens
$0.1225
1K tokens

100 Steps

$0.0175
1K tokens
$0.175
1K tokens

Open Source LLM - Chat, Code, Language models

Up to 4B

Input
$0.00013
1K tokens

4.1B - 8B

$0.00026
1K tokens

8.1B - 21B

$0.00039
1K tokens

21.1B - 41B

$0.00104
1K tokens

41.1B - 80B

$0.00117
1K tokens

80.1B - 110B

$0.00234
1K tokens

Open Source MoE

Up to 56B

Input
$0.00078
1K tokens

56.1B - 176B

$0.00156
1K tokens

176.1B - 480B

$0.00312
1K tokens

Open Source Embeddings

Up to 150M

Input
$0.0000104
1K tokens

151M - 350M

$0.0000208
1K tokens

Audio Models STT, TTS

Nova-2

Pre-Recorded
Streaming
$0.01505
Per min
$0.02065
Per min

Whisper-base

$0.01225
Per min

Whisper-large

$0.0168
Per min

Whisper-medium

$0.0147
Per min

Whisper-small

$0.0133
Per min

Whisper-tiny

$0.01155
Per min

Aura

$0.0525
1k characters

Suno AI

$0.0075
per generation

Ready to get started? Get Your API Key Now!

Get API Key
GET IN TOUCH

Frequently asked questions

What is a Token

Tokens can be thought of as segments of words used in natural language processing. In English, a token typically represents about 4 characters or 0.75 words.
For context, the entire Harry Potter series comprises approximately 1,090,739 words, which translates to around 1.3 million tokens.

Which AI model should I use?

Selecting the ideal AI model hinges on your specific requirements and the tasks you want to achieve.
We suggest testing these models in the Playground to determine which ones offer the optimal balance between cost and performance for your needs.
A frequently used strategy involves utilizing various query types, each directed to the most suitable model for handling them.

How to add my model to API?

Join the Discord Community: If you haven’t already, join our Discord community through the link provided on our website or in our communications.
Navigate to the #feedback Channel: Once you're in our Discord server, find the #feedback channel dedicated to suggestions and improvements.
Detail Your Proposal: Create a post that details your model, its functionalities, and how it can benefit the AI/ML API community.
Be sure to include:The type of model and its use case.Performance metrics or research backing your model.Any other relevant information that would support your case.
Engage with the Community: Be prepared to discuss your proposal with other community members and answer any questions. Community interest can play a significant role in prioritizing new features and additions.

Does using the playground deduct from my token allocation?

Using the Playground consumes only paid tokens for PRO models.

How to manage my subscription

Log in to Your Account: Go to app.aimlapi.com and log in with your credentials to access your dashboard, where you can view your projects and subscription details.
Navigate to the Billing Page: From your dashboard, click on "Billing" to see your plan details, usage, and billing history.
Manage Subscription: On the Billing page, click the "Manage" button to access Stripe’s secure portal for adjusting your subscription settings.

How to upgrade or downgrade my plan

Within Stripe’s portal, you'll be able to:
Upgrade or Downgrade Your Plan: Choose a plan that best fits your current needs. Whether you require more resources or need to scale down, you can select the appropriate plan directly within the portal.
Update Billing Information: Change or update your payment method, billing address, and contact information to ensure uninterrupted service.
View Billing History: Access all past invoices and payments for your records.
Cancel Subscription: If you decide to cancel your subscription, you can do so from here. Please note that we'd appreciate any feedback on how we can improve our services.