Last Update: 2025/3/26
LLMProvider is dedicated to offering access to a wide range of text-based AI models, currently supporting over 100 model endpoints. If you're interested in models or providers that we don't yet support, feel free to share your suggestions with us on our Discord channel.
The prices listed below are for 1M tokens. A token is the smallest unit of text processed by the model, encompassing words, numbers, and punctuation. Billing is based on the total number of tokens, including both input and output, processed by the model.
Note: Prices are subject to change and are for reference only.
OpenAI
The OpenAI provides a simple interface to state-of-the-art AI models for natural language processing, image generation, semantic search, and speech recognition. Follow this guide to learn how to generate human-like responses to natural language prompts, create vector embeddings for semantic search, and generate images from textual descriptions.
OpenAI Text Token Pricing (Per 1M Tokens)
| Model | Max Output Tokens | Input Cost (per 1M tokens) | Output Cost (per 1M tokens) | Notes |
|---|---|---|---|---|
| openai/gpt-3.5-turbo | 16K | $0.50 | $1.50 | |
| openai/gpt-3.5-turbo-0125 | 16K | $0.50 | $1.50 | |
| openai/gpt-3.5-turbo-1106 | 16K | $0.50 | $1.50 | |
| openai/gpt-3.5-turbo-0613 | 16K | $0.50 | $1.50 | |
| openai/gpt-3.5-turbo-16k | 16K | $0.50 | $1.50 | |
| openai/gpt-4o | 128K | $2.50 | $15.00 | |
| openai/gpt-4o-2024-05-13 | 128K | $2.50 | $15.00 | |
| openai/gpt-4o-2024-08-06 | 128K | $2.50 | $15.00 | |
| openai/gpt-4o-mini | 128K | $0.15 | $1.50 | |
| openai/gpt-4o-mini-2024-07-18 | 128K | $0.15 | $1.50 | |
| openai/gpt-4o-mini-audio-preview | 128K | $0.15 | $1.50 | |
| openai/gpt-4o-mini-audio-preview-2024-12-17 | 128K | $0.15 | $1.50 | |
| openai/gpt-4o-mini-realtime-preview | 128K | $0.60 | $1.50 | |
| openai/gpt-4o-mini-realtime-preview-2024-12-17 | 128K | $0.60 | $1.50 | |
| openai/gpt-4-turbo | 128K | $10.00 | $30.00 | |
| openai/gpt-4-turbo-preview | 128K | $10.00 | $30.00 | |
| openai/gpt-4-1106-preview | 128K | $10.00 | $30.00 | |
| openai/gpt-4 | 8K | $30.00 | $60.00 | |
| openai/gpt-4-32k | 32K | $60.00 | $120.00 | |
| openai/gpt-4-vision-preview | 128K | $10.00 | $30.00 | |
| openai/gpt-4o-audio-preview | 128K | $5.00 | $15.00 | |
| openai/gpt-4o-audio-preview-2024-12-17 | 128K | $5.00 | $15.00 | |
| openai/gpt-4o-realtime-preview | 128K | $5.00 | $15.00 | |
| openai/gpt-4o-realtime-preview-2024-12-17 | 128K | $5.00 | $15.00 | |
| openai/o1-mini | 128K | $1.10 | $1.50 | |
| openai/o1-mini-2024-09-12 | 128K | $1.10 | $1.50 | |
| openai/o3-mini | 128K | $1.10 | $1.50 | New |
| openai/o3-mini-2025-01-31 | 128K | $1.10 | $1.50 | New |
| openai/o1 | 128K | $15.00 | $15.00 | |
| openai/o1-2024-12-17 | 128K | $15.00 | $15.00 | |
| openai/gpt-4.5-preview | 128K | $15.00 | $15.00 | |
| openai/gpt-4.5-preview-2025-02-27 | 128K | $15.00 | $15.00 |
Notes:
- Max Output Tokens refers to the maximum number of tokens the model can generate in a single response.
- Input Cost and Output Cost are calculated per million tokens and may change based on OpenAI's pricing adjustments.
- GPT-4o series offers better performance at a lower price compared to GPT-4-Turbo, making it suitable for most advanced tasks.
- GPT-3.5-Turbo is the most cost-effective option, ideal for everyday tasks.
OpenAI Transcription and speech generation Pricing
| Model | Use Case | Cost | Notes |
|---|---|---|---|
| openai/Whisper | Transcription | $0.006 / minute | |
| openai/TTS | Speech generation | $15.00 / 1M characters | |
| openai/TTS HD | Speech generation | $30.00 / 1M characters |
OpenAI Image Generation Pricing
| Model | Quality | 256x256 | 512x512 | 1024x1024 | 1024x1792 | Notes |
|---|---|---|---|---|---|---|
| openai/DALL·E 2 | * | $0.016 | $0.018 | $0.00 | * | |
| openai/DALL·E 3 | Standard | * | * | $0.04 | $0.08 | |
| openai/DALL·E 3 | HD | * | * | $0.08 | $0.12 |
Embeddings Pricing
| Model | Price per 1M tokens | Notes |
|---|---|---|
| openai/text-embedding-3-small | $0.02 | |
| openai/text-embedding-3-large | $0.13 | |
| openai/text-embedding-ada-002 | $0.10 |
Gemini
Gemini offers a range of advanced AI models for natural language processing, including text generation, summarization, and translation. The models are designed to generate human-like responses to text prompts, making them ideal for chatbots, content generation, and research assistance.
Gemini Text Token Pricing (Per 1M Tokens)
| Model | Max Output Tokens | Input Cost (per 1M tokens) | Output Cost (per 1M tokens) | Notes |
|---|---|---|---|---|
| gemini/gemini-1.5-pro | 128K | $1.25 | $5.00 | |
| gemini/gemini-1.5-pro-latest | 128K | $1.25 | $5.00 | |
| gemini/gemini-2.0-pro-exp | 128K | $1.25 | $5.00 | |
| gemini/gemini-1.5-flash | 128K | $0.075 | $0.30 | |
| gemini/gemini-1.5-flash-8b | 128K | $0.075 | $0.30 | |
| gemini/gemini-2.0-flash | 128K | $0.075 | $0.30 | |
| gemini/gemini-1.5-flash-latest | 128K | $0.075 | $0.30 | |
| gemini/gemini-2.0-flash-lite-preview | 128K | $0.075 | $0.30 | |
| gemini/gemini-2.0-flash-exp | 128K | $3.50 | $10.50 | |
| gemini/gemini-2.0-flash-exp | 128K | $3.50 | $10.50 | |
| gemini/gemini-2.0-flash-thinking-exp | 128K | $3.50 | $10.50 | |
| gemini/gemini-exp-1206 | 128K | $3.50 | $10.50 |
Anthropic
Anthropic provides a range of advanced AI models for natural language processing, including text generation, summarization, and translation. The models are designed to generate human-like responses to text prompts, making them ideal for chatbots, content generation, and research assistance.
Anthropic Text Token Pricing (Per 1M Tokens)
| Model | Max Output Tokens | Input Cost (per 1M tokens) | Output Cost (per 1M tokens) | Notes |
|---|---|---|---|---|
| anthropic/claude-instant-1.2 | 100K | $1.00 | $3.00 | |
| anthropic/claude-2 | 100K | $1.50 | $4.50 | |
| anthropic/claude-2.0 | 100K | $1.50 | $4.50 | |
| anthropic/claude-3-haiku-20240307 | 100K | $1.50 | $4.50 | |
| anthropic/claude-3-sonnet-20240229 | 100K | $2.00 | $6.00 | |
| anthropic/claude-3-opus-20240229 | 100K | $2.50 | $7.50 | |
| anthropic/claude-3-5-sonnet-20240620 | 100K | $3.00 | $9.00 | |
| anthropic/claude-3-5-sonnet-20241022 | 100K | $3.50 | $10.50 |
Anthropic Claude on Amazon Bedrock (Anthropic Claude)
Anthropic Claude is now available on Amazon Bedrock, a fully managed foundation model (FM) service from AWS. This integration allows businesses to leverage Claude’s advanced natural language processing (NLP) capabilities for various AI-driven applications, including chatbots, content generation, summarization, and research assistance.
Why Use Claude on Amazon Bedrock?
- Fully Managed Infrastructure: No need to manage servers or fine-tuning infrastructure—AWS handles deployment and scaling.
- Customizability: Businesses can fine-tune Claude for domain-specific applications while maintaining Anthropic’s AI safety features.
- Seamless AWS Integration: Works with AWS Lambda, Amazon S3, DynamoDB, and other AWS services for building AI-powered workflows.
- Secure & Enterprise-Ready: Built-in compliance and security controls for enterprise applications.
Anthropic Claude Text Token Pricing (Per 1M Tokens)
| Model | Max Output Tokens | Input Cost (per 1M tokens) | Output Cost (per 1M tokens) | Notes |
|---|---|---|---|---|
| anthropic-aws/claude-instant-1.2 | 100K | $1.00 | $3.00 | |
| anthropic-aws/claude-2 | 100K | $1.50 | $4.50 | |
| anthropic-aws/claude-2.0 | 100K | $1.50 | $4.50 | |
| anthropic-aws/claude-3-haiku-20240307 | 100K | $1.50 | $4.50 | |
| anthropic-aws/claude-3-sonnet-20240229 | 100K | $2.00 | $6.00 | |
| anthropic-aws/claude-3-opus-20240229 | 100K | $2.50 | $7.50 | |
| anthropic-aws/claude-3-5-sonnet-20240620 | 100K | $3.00 | $9.00 | |
| anthropic-aws/claude-3-5-sonnet-20241022 | 100K | $3.50 | $10.50 |
For more details, visit:
🔗 Anthropic on Amazon Bedrock
🔗 Claude Models on AWS
Gizmo OpenAI (Reverse Openai Web API)
Gizmo OpenAI is a service focused on reverse-engineering the OpenAI web-based model API.It fully supports All-Tools, Actions, GPTs, and related interfaces, providing efficient and stable API access for developers to integrate and utilize OpenAI's advanced features.
Gizmo ALL Tools Token Pricing (Per 1M Tokens)
| Model | Max Output Tokens | Input Cost (per 1M tokens) | Output Cost (per 1M tokens) | Notes |
|---|---|---|---|---|
| gizmo/gizmo-gpt-4 | 100K | $30.00 | $60.00 | |
| gizmo/gizmo-gpt-4o | 100K | $2.50 | $10.00 | |
| gizmo/gizmo-gpt-4o-mini | 100K | $2.50 | $10.00 | |
| gizmo/gizmo-gpt-3.5-turbo | 100K | $2.50 | $10.00 | |
| gizmo/gizmo-o1-mini | 100K | $3.00 | $12.00 | |
| gizmo/gizmo-o1-preview | 100K | $15.00 | $60.00 | |
| gizmo/alk-gpt-4 | 100K | $30.00 | $60.00 | alk: convert API models to a web interface for browser access |
| gizmo/alk-gpt-4o | 100K | $2.50 | $10.00 | |
| gizmo/alk-claude-3-5-sonnet-20240620 | 100K | $15.00 | $60.00 | |
| gizmo/alk-claude-3-opus-20240229 | 100K | $15.00 | $60.00 |
Qwen
Qwen models outperform the baseline models of similar model sizes on a series of benchmark datasets, e.g., MMLU, C-Eval, GSM8K, MATH, HumanEval, MBPP, BBH, etc., which evaluate the models’ capabilities on natural language understanding, mathematic problem solving, coding, etc. Qwen-72B achieves better performance than LLaMA2-70B on all tasks and outperforms GPT-3.5 on 7 out of 10 tasks.
Qwen Text Token Pricing (Per 1M Tokens)
| Model | Max Output Tokens | Input Cost (per 1K tokens) | Output Cost (per 1K tokens) | Notes |
|---|---|---|---|---|
| qwen/qwen-max | 32K | $3.08 | $9.23 | Flagship model, strongest reasoning ability |
| qwen/qwen-plus | 131K | $0.12 | $0.31 | Balanced in effect, speed, and cost |
| qwen/qwen-turbo | 1,000K | $0.05 | $0.09 | Fast and very low cost for simple tasks |
| qwen/qwen-long | 10,000K | $0.08 | $0.03 | Balanced in effect and speed, cost-efficient for large-scale text analysis |
| qwen/qwen-vl-max | 100K | $3.08 | $9.23 | Visual models can be experienced online for image understanding capabilities |
| qwen/qwen-vl-max-latest | 100K | $3.08 | $9.23 | Visual models can be experienced online for image understanding capabilities |
Qwen Transcription and speech generation Pricing
| Model | Use Case | Cost | Notes |
|---|---|---|---|
| qwen/paraformer-v2 | Transcription | $0.0048 / minute | |
| qwen/qwen2-audio-instruct | Speech generation | $15.00 / 1M characters |
OpenAI Image Generation Pricing
| Model | Quality | 1024x1024 | Notes |
|---|---|---|---|
| qwen/wanx-v1 | * | $0.06/次 |
Embeddings Pricing
| Model | Price per 1M tokens | Notes |
|---|---|---|
| openai/text-embedding-v1 | $0.10 | |
| openai/text-embedding-v2 | $0.10 | |
| openai/text-embedding-v3 | $0.10 |
For more details, visit:
🔗 Qwen Models
🔗 Qwen Documentation
DeepSeek
DeepSeek is an AI company specializing in large language models (LLMs). It offers models like DeepSeek Chat for general conversations and DeepSeek Coder for code generation, focusing on efficiency, scalability, and cost-effective AI solutions.
DeepSeek Text Token Pricing (Per 1M Tokens)
| Model | Max Output Tokens | Input Cost (per 1K tokens) | Output Cost (per 1K tokens) | Notes |
|---|---|---|---|---|
| deepseek/deepseek-chat | 64K | $0.14 | $0.28 | |
| deepseek/deepseek-coder | 64K | $0.14 | $0.28 |
MiniMax
MiniMax Text Token Pricing (Per 1M Tokens)
| Model | Max Output Tokens | Input Cost (per 1M tokens) | Output Cost (per 1M tokens) | Notes |
|---|---|---|---|---|
| llmvision/abab6.5s-chat | 64K | $0.14 | $0.14 | |
| llmvision/abab6.5g-chat | 64K | $0.68 | $0.68 | |
| llmvision/abab6.5t-chat | 64K | $0.68 | $0.68 | |
| llmvision/abab5.5s-chat | 64K | $0.68 | $0.68 | |
| llmvision/abab5.5-chat | 64K | $1.44 | $1.44 |
LLMVersion
LLMVision specializes in cutting-edge AI models for text-to-speech (TTS), speech-to-text (STT), and immersive role-playing experiences. Designed for high-performance voice synthesis and recognition, LLMVision enhances interactive AI applications with natural, expressive, and context-aware dialogue capabilities.
LLMVision Text Token Pricing (Per 1M Tokens)
| Model | Max Output Tokens | Input Cost (per 1M tokens) | Output Cost (per 1M tokens) | Notes |
|---|---|---|---|---|
| llmvision/SenseCharacter-20240721-01 | 64K | $0.50 | $1.50 | |
| llmvision/SenseCharacter-20240721-02 | 64K | $0.50 | $1.50 | |
| llmvision/SenseCharacter-20240721-03 | 64K | $0.50 | $1.50 | |
| llmvision/SenseCharacter-20240618-01 | 64K | $0.50 | $1.50 | |
| llmvision/SenseCharacter-20240619-01 | 64K | $0.50 | $1.50 | |
| llmvision/SenseCharacter-20240724-01 | 64K | $0.50 | $1.50 | |
| llmvision/SenseCharacter-20240809-01 | 64K | $0.50 | $1.50 | |
| llmvision/SenseCharacter-20240829-01 | 64K | $0.50 | $1.50 | |
| llmvision/SenseCharacter-20241231-01 | 64K | $0.50 | $1.50 | |
| llmvision/SenseCharacter-20250108-01 | 64K | $0.50 | $1.50 | |
| llmvision/SenseCharacter-20250124-01 | 64K | $0.50 | $1.50 | New |
LLMVision Transcription and speech generation Pricing
| Model | Use Case | Cost | Notes |
|---|---|---|---|
| llmvision/lmp-stt-20241013 | Transcription | $0.0048 / minute | |
| llmvision/lmp-tts-20241012 | Speech generation | $15.00 / 1M characters |
LLMVision Image Generation Pricing
| Model | Quality | 1024x1024 | Notes |
|---|---|---|---|
| llmvision/ALLTools-dalle | * | $0.06/次 |
For Providers
If you’re interested in collaborating with LLMProvider, we invite you to visit our providers page to learn more about how to get involved.
Contact Us
If you have any questions, feedback, or would like to discuss potential partnerships, feel free to reach out to us via the following channels:
- GitHub Repository – For code, issues, and contributions.
- Discord Channel – Join our community to ask questions, share feedback, or engage with other providers and users.
- Email Us – For direct inquiries or support.