Welcome to the Deep Realms API documentation! You can find your API key on the profile page.
This page contains the documentation for the Chat API. If you would like to check out the Stories API, please click here.
If you would like to purchase over $300 worth of extra credits as a company, please reach out to us at contact@deeprealms.io and we will provide you with a discount.
Our Chat API is modeled after OpenAI's API, so that you may use it as a drop-in replacement. We provide lower prices than OpenAI, with an additional option to enhance the quality of the model's output, improving it beyond the standard response you might receive via OpenAI's API. This does not work for all kinds of prompts - it will work best with conversational prompts or prompts that involve storytelling. However, there might be other use cases we simply haven't explored.
We do not yet have all of the functionality of OpenAI's API as of now, but the core functionality is already implemented and we will be adding more over time.
* the table below displays prices in USD for various subscription tiers and credit packs.
** Using enhanced outputs (setting the "enhance_output" parameter to true) will increase the price per token by 10%.
Model name | Price per 1000 input tokens | Price per 1000 output tokens | Context size | Description |
---|---|---|---|---|
ChatGPT 3.5 | $0.0004 / 1 credits | $0.0016 / 4 credits | 65,536 tokens | OpenAI's latest ChatGPT model, which is likely the most censored. |
GPT-4o | $0.004 / 10 credits | $0.012 / 30 credits | 65,536 tokens | OpenAI's most powerful model. |
GPT-4o mini | $0.00032 / 0.8 credits | $0.00068 / 1.7 credits | 65,536 tokens | A cheaper and faster version of GPT-4o. |
Claude 3.5 Sonnet | $0.0028 / 7 credits | $0.0088 / 22 credits | 65,536 tokens | A powerful model from Anthropic. This model is censored and may refuse to generate certain content. |
Freya 4.0 | $0.0002 / 0.5 credits | $0.0004 / 1 credits | 65,536 tokens | Our fastest model. |
Magni 4.0 | $0.0004 / 1 credits | $0.0008 / 2 credits | 65,536 tokens | A very capable model. It is about as good as (or slightly better than) "Astral 1.0 (Medium)" but it is cheaper. However, it is also slightly more censored than "Astral 1.0 (Medium)". |
Astral 1.0 (Small) | $0.0004 / 1 credits | $0.0008 / 2 credits | 65,536 tokens | A cheap, fast and powerful model. |
Astral 1.0 (Medium) | $0.0016 / 4 credits | $0.0032 / 8 credits | 65,536 tokens | Our second most powerful uncensored model. |
Astral 1.5 (Large) | $0.0048 / 12 credits | $0.0096 / 24 credits | 65,536 tokens | Our most powerful uncensored model. |
Model name | Price per 1000 input tokens | Price per 1000 output tokens | Context size | Description |
---|---|---|---|---|
ChatGPT 3.5 | $0.000375 / 1 credits | $0.0015 / 4 credits | 65,536 tokens | OpenAI's latest ChatGPT model, which is likely the most censored. |
GPT-4o | $0.00375 / 10 credits | $0.01125 / 30 credits | 65,536 tokens | OpenAI's most powerful model. |
GPT-4o mini | $0.0003 / 0.8 credits | $0.000638 / 1.7 credits | 65,536 tokens | A cheaper and faster version of GPT-4o. |
Claude 3.5 Sonnet | $0.002625 / 7 credits | $0.00825 / 22 credits | 65,536 tokens | A powerful model from Anthropic. This model is censored and may refuse to generate certain content. |
Freya 4.0 | $0.000188 / 0.5 credits | $0.000375 / 1 credits | 65,536 tokens | Our fastest model. |
Magni 4.0 | $0.000375 / 1 credits | $0.00075 / 2 credits | 65,536 tokens | A very capable model. It is about as good as (or slightly better than) "Astral 1.0 (Medium)" but it is cheaper. However, it is also slightly more censored than "Astral 1.0 (Medium)". |
Astral 1.0 (Small) | $0.000375 / 1 credits | $0.00075 / 2 credits | 65,536 tokens | A cheap, fast and powerful model. |
Astral 1.0 (Medium) | $0.0015 / 4 credits | $0.003 / 8 credits | 65,536 tokens | Our second most powerful uncensored model. |
Astral 1.5 (Large) | $0.0045 / 12 credits | $0.009 / 24 credits | 65,536 tokens | Our most powerful uncensored model. |
Model name | Price per 1000 input tokens | Price per 1000 output tokens | Context size | Description |
---|---|---|---|---|
ChatGPT 3.5 | $0.000312 / 1 credits | $0.00125 / 4 credits | 65,536 tokens | OpenAI's latest ChatGPT model, which is likely the most censored. |
GPT-4o | $0.003125 / 10 credits | $0.009375 / 30 credits | 65,536 tokens | OpenAI's most powerful model. |
GPT-4o mini | $0.00025 / 0.8 credits | $0.000531 / 1.7 credits | 65,536 tokens | A cheaper and faster version of GPT-4o. |
Claude 3.5 Sonnet | $0.002188 / 7 credits | $0.006875 / 22 credits | 65,536 tokens | A powerful model from Anthropic. This model is censored and may refuse to generate certain content. |
Freya 4.0 | $0.000156 / 0.5 credits | $0.000312 / 1 credits | 65,536 tokens | Our fastest model. |
Magni 4.0 | $0.000312 / 1 credits | $0.000625 / 2 credits | 65,536 tokens | A very capable model. It is about as good as (or slightly better than) "Astral 1.0 (Medium)" but it is cheaper. However, it is also slightly more censored than "Astral 1.0 (Medium)". |
Astral 1.0 (Small) | $0.000312 / 1 credits | $0.000625 / 2 credits | 65,536 tokens | A cheap, fast and powerful model. |
Astral 1.0 (Medium) | $0.00125 / 4 credits | $0.0025 / 8 credits | 65,536 tokens | Our second most powerful uncensored model. |
Astral 1.5 (Large) | $0.00375 / 12 credits | $0.0075 / 24 credits | 65,536 tokens | Our most powerful uncensored model. |
Model name | Price per 1000 input tokens | Price per 1000 output tokens | Context size | Description |
---|---|---|---|---|
ChatGPT 3.5 | $0.00025 / 1 credits | $0.001 / 4 credits | 65,536 tokens | OpenAI's latest ChatGPT model, which is likely the most censored. |
GPT-4o | $0.0025 / 10 credits | $0.0075 / 30 credits | 65,536 tokens | OpenAI's most powerful model. |
GPT-4o mini | $0.0002 / 0.8 credits | $0.000425 / 1.7 credits | 65,536 tokens | A cheaper and faster version of GPT-4o. |
Claude 3.5 Sonnet | $0.00175 / 7 credits | $0.0055 / 22 credits | 65,536 tokens | A powerful model from Anthropic. This model is censored and may refuse to generate certain content. |
Freya 4.0 | $0.000125 / 0.5 credits | $0.00025 / 1 credits | 65,536 tokens | Our fastest model. |
Magni 4.0 | $0.00025 / 1 credits | $0.0005 / 2 credits | 65,536 tokens | A very capable model. It is about as good as (or slightly better than) "Astral 1.0 (Medium)" but it is cheaper. However, it is also slightly more censored than "Astral 1.0 (Medium)". |
Astral 1.0 (Small) | $0.00025 / 1 credits | $0.0005 / 2 credits | 65,536 tokens | A cheap, fast and powerful model. |
Astral 1.0 (Medium) | $0.001 / 4 credits | $0.002 / 8 credits | 65,536 tokens | Our second most powerful uncensored model. |
Astral 1.5 (Large) | $0.003 / 12 credits | $0.006 / 24 credits | 65,536 tokens | Our most powerful uncensored model. |
1.2 /api/v1/models
Post https://www.deeprealms.io/api/v1/chat/completions
Create a model response for a given chat conversation.
model
string (required)
The name of the model to use. You can retrieve a list of available models via the "api/v1/models" endpoint.
messages
array (required)
A list of messages comprising the conversation so far.
temperature
number or null (optional)
The sampling temperature that should be used. The default value is: 1.
max_tokens
integer or null (optional)
The maximum number of tokens that should be generated in a chat completion. This parameter cannot be set if "enhance_output" is set to true. The default value is: null.
stream
boolean (optional)
Whether to stream back partial progress. If set to true, tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE] message. Otherwise, the server will hold the request open until the timeout or until completion, with the response containing the full result as JSON. The default value is: false.
enhance_output
boolean (optional)
If set to true, the model output will generally be of higher quality, but it will take a longer time to generate a response.
curl -X Post https://www.deeprealms.io/api/v1/chat/completions \
-H "Authorization: Bearer $DEEP_REALMS_API_KEY" \
-d '{
"model": "ChatGPT 2.0",
"messages": [
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Hello!"
}
],
"temperature": 0.7,
"max_tokens": 50,
"stream": false,
"enhance_output": true
}'
{
"id": null,
"object": "chat.completion",
"created": 1677868242,
"model": "ChatGPT 2.0",
"usage": {
"prompt_tokens": 13,
"completion_tokens": 7,
"total_tokens": 20
},
"choices": [
{
"message": {
"role": "assistant",
"content": "\n\nThis is a test!"
},
"logprobs": null,
"finish_reason": "stop",
"index": 0
}
]
}
GET https://www.deeprealms.io/api/v1/models
Get a list of available models.
curl -X GET https://www.deeprealms.io/api/v1/models \
-H "Authorization: Bearer $DEEP_REALMS_API_KEY"
{
"object": "list",
"data": [
{
"id": "ChatGPT 2.0",
"object": "model"
},
{
"id": "ChatGPT 3.5",
"object": "model"
},
{
"id": "GPT-4",
"object": "model"
},
{
"id": "Freya 4.0",
"object": "model"
},
{
"id": "Magni 2.0",
"object": "model"
}
]
}