Introduction #
Welcome to the web application based on OpenAI ChatGPT! This application allows you to engage in casual chat using the powerful GPT-3.5/4 language model, as well as conduct file-based chats using your own files. If you have any questions or need assistance, feel free to reach out to me at [email protected].
Features #
This application offers several exciting features:
- Casual Chat: Engage in casual conversations using GPT-3.5/4.
- File Chat / Q&A: Have file-based chats and ask questions.
- Text to Image: Convert text into images.
Models #
API Base: https://oneapi.laisky.com
Support Models:
Request Model is the value of the model in the user’s request parameters, and Actual Model is the actual model that will be sent by the backend to upstream.
| Request Model | Actual Model | Input Price | Output Price |
|---|---|---|---|
| gpt-3.5-turbo | gpt-3.5-turbo-0125 | 0.5 | 1.5 |
| gpt-3.5-turbo-1106 | 1 | 2 | |
| gpt-3.5-turbo-0125 | 0.5 | 1.5 | |
| gpt-3.5-turbo-16k | gpt-3.5-turbo-0125 | 0.5 | 1.5 |
| gpt-4o | gpt-4o-2024-08-06 | 2.5 | 10 |
| gpt-4o-2024-05-13 | 5 | 15 | |
| gpt-4o-2024-08-06 | 2.5 | 10 | |
| gpt-4o-mini | gpt-4o-mini-2024-07-18 | 0.15 | 0.6 |
| gpt-4o-mini-2024-07-18 | gpt-4o-mini-2024-07-18 | 0.15 | 0.6 |
| gpt-4-turbo-preview | gpt-4-turbo-2024-04-09 | 10 | 30 |
| gpt-4-turbo | gpt-4-turbo-2024-04-09 | 10 | 30 |
| gpt-4-turbo-2024-04-09 | 10 | 30 | |
| gpt-4-1106-preview | 10 | 30 | |
| gpt-4-0125-preview | 10 | 30 | |
| gpt-4-vision-preview | gpt-4-turbo-2024-04-09 | 10 | 30 |
| gpt-4-1106-vision-preview | 10 | 30 | |
| gpt-4 | gpt-4-turbo-2024-04-09 | 10 | 30 |
| gpt-4-32k | gpt-4-turbo-2024-04-09 | 10 | 30 |
| deepseek-chat | 0.14 | 0.28 | |
| deepseek-coder | 0.14 | 0.28 | |
| claude-1 | claude-instant-1.2 | 0.8 | 2.4 |
| claude-2 | claude-2.1 | 8 | 24 |
| claude-3 | claude-3-haiku-20240307 | 0.25 | 1.25 |
| claude-instant-1 | claude-instant-1.2 | 0.8 | 2.4 |
| claude-instant-1.2 | 0.8 | 2.4 | |
| claude-2.1 | 8 | 24 | |
| claude-3-opus | claude-3-opus-20240229 | 15 | 75 |
| claude-3-sonnet | claude-3-sonnet-20240229 | 3 | 15 |
| claude-3-haiku | claude-3-haiku-20240307 | 0.25 | 1.25 |
| claude-3-opus-20240229 | 15 | 75 | |
| claude-3-sonnet-20240229 | 3 | 15 | |
| claude-3-haiku-20240307 | 0.25 | 1.25 | |
| claude-3.5-haiku | claude-3-5-haiku-20241022 | 1 | 5 |
| claude-3-5-haiku-20241022 | 1 | 5 | |
| claude-3.5-sonnet | claude-3-5-sonnet-latest | 3 | 15 |
| claude-3.5-sonnet-8k | claude-3-5-sonnet-latest | 3 | 15 |
| claude-3-5-sonnet-20240620 | 3 | 15 | |
| claude-3-5-sonnet-20241022 | 3 | 15 | |
| claude-3-5-sonnet-latest | 3 | 15 | |
| gemma-7b-it | FREE | ||
| llama3-8b-8192 | FREE | ||
| llama3-70b-8192 | FREE | ||
| llama-3.1-8b-instant | FREE | ||
| llama-3.1-70b-versatile | FREE | ||
| llama-3.1-405b-instruct | FREE | ||
| mistral-7b-instruct-v0.3 | FREE | ||
| mixtral-8x7b-32768 | FREE | ||
| gemini-pro | 0.5 | 1 | |
| gemini-pro-vision | 0.5 | 1 | |
| gemini-1.5-flash | gemini-1.5-flash-002 | 0.02 | 0.04 |
| gemini-1.5-flash-001 | 0.02 | 0.04 | |
| gemini-1.5-flash-002 | 0.02 | 0.04 | |
| gemini-1.5-pro | gemini-1.5-pro-002 | 0.25 | 0.5 |
| gemini-1.5-pro-001 | 0.25 | 0.5 | |
| gemini-1.5-pro-002 | 0.25 | 0.5 | |
| gemini-1.5-pro-latest | 0.25 | 0.5 | |
| gpt-3.5-turbo-0301 | gemini-pro | 0.5 | 1 |
| gpt-3.5-turbo-16k-0613 | gemini-pro | 0.5 | 1 |
| dall-e-2 | 0.02/pic | ||
| dall-e-3 | 0.04/pic | ||
| flux-pro | 0.055/pic | ||
| flux-schnell | 0.003/pic | ||
| sdxl-turbo | FREE | ||
| tts-1 | 15 | ||
| tts-1-hd | 30 | ||
| whisper-1 | 0.006/min | ||
| whisper-large-v3 | FREE | ||
| test-embedding-ada-002 | 0.1 | ||
| text-embedding-3-small | 0.02 | ||
| text-embedding-3-large | 0.13 | ||
| @cf/meta/llama-2-7b-chat-fp16 | FREE | ||
| @cf/meta/llama-2-7b-chat-int8 | FREE | ||
| @cf/mistral/mistral-7b-instruct-v0.1 | FREE | ||
| @hf/thebloke/deepseek-coder-6.7b-base-awq | FREE | ||
| @hf/thebloke/deepseek-coder-6.7b-instruct-awq | FREE | ||
| @cf/deepseek-ai/deepseek-math-7b-base | FREE | ||
| @cf/deepseek-ai/deepseek-math-7b-instruct | FREE | ||
| @cf/thebloke/discolm-german-7b-v1-awq | FREE | ||
| @cf/tiiuae/falcon-7b-instruct | FREE | ||
| @cf/google/gemma-2b-it-lora | FREE | ||
| @hf/google/gemma-7b-it | FREE | ||
| @cf/google/gemma-7b-it-lora | FREE | ||
| @hf/nousresearch/hermes-2-pro-mistral-7b | FREE | ||
| @hf/thebloke/llama-2-13b-chat-awq | FREE | ||
| @cf/meta-llama/llama-2-7b-chat-hf-lora | FREE | ||
| @cf/meta/llama-3-8b-instruct | FREE | ||
| @hf/thebloke/llamaguard-7b-awq | FREE | ||
| @hf/thebloke/mistral-7b-instruct-v0.1-awq | FREE | ||
| @hf/mistralai/mistral-7b-instruct-v0.2 | FREE | ||
| @cf/mistral/mistral-7b-instruct-v0.2-lora | FREE | ||
| @hf/thebloke/neural-chat-7b-v3-1-awq | FREE | ||
| @cf/openchat/openchat-3.5-0106 | FREE | ||
| @hf/thebloke/openhermes-2.5-mistral-7b-awq | FREE | ||
| @cf/microsoft/phi-2 | FREE | ||
| @cf/qwen/qwen1.5-0.5b-chat | FREE | ||
| @cf/qwen/qwen1.5-1.8b-chat | FREE | ||
| @cf/qwen/qwen1.5-14b-chat-awq | FREE | ||
| @cf/qwen/qwen1.5-7b-chat-awq | FREE | ||
| @cf/defog/sqlcoder-7b-2 | FREE | ||
| @hf/nexusflow/starling-lm-7b-beta | FREE | ||
| @cf/tinyllama/tinyllama-1.1b-chat-v1.0 | FREE | ||
| @hf/thebloke/zephyr-7b-beta-awq | FREE |
the unit of input/output price is USD per million tokens
Pricing #
Free User #
As a new user, you will automatically receive a unique token for free. This token allows you to chat with GPT-3.5-turbo.
There are three types of tokens you can use:
FREETIER-*: Free token with rate limits.- Your own OpenAI token: Unlimited usage.
- Paid token: Unlimited usage.