# Model and Pricing

### Supported Models and Pricing

ORA API supports a variety of open-source models, all verifiable through opML.

Price are measured in unit of $ORA.

```
// language model
"deepseek-ai/DeepSeek-V3" = 0.15,                          # Per 1M Tokens
"deepseek-ai/DeepSeek-R1" = 1.35,                          # Per 1M Tokens

"meta-llama/Llama-3.3-70B-Instruct" = 0.68,                # Per 1M Tokens
"meta-llama/Llama-3.2-3B-Instruct" = 0.05,                 # Per 1M Tokens
"meta-llama/Llama-2-13b-chat-hf" = 0.17,                   # Per 1M Tokens
"meta-llama/Llama-2-7b-chat-hf" = 0.15,                    # Per 1M Tokens
"meta-llama/Llama-3.1-405B-Instruct" = 2.69,                # Per 1M Tokens
"meta-llama/Llama-3.2-1B-Instruct" = 0.05,                 # Per 1M Tokens
"meta-llama/Meta-Llama-3-8B-Instruct" = 0.14,              # Per 1M Tokens

"google/gemma-2b-it" = 0.08,                               # Per 1M Tokens
"google/gemma-2-27b-it" = 0.62,                            # Per 1M Tokens
"google/gemma-2-9b-it" = 0.23,                             # Per 1M Tokens
"mistralai/Mistral-7B-Instruct-v0.3" = 0.15,               # Per 1M Tokens
"mistralai/Mixtral-8x22B-Instruct-v0.1" = 0.92,             # Per 1M Tokens
"mistralai/Mistral-7B-Instruct-v0.2" = 0.15,               # Per 1M Tokens
"mistralai/Mixtral-8x7B-Instruct-v0.1" = 0.46,             # Per 1M Tokens
"mistralai/Mistral-7B-Instruct-v0.1" = 0.15,               # Per 1M Tokens

"Qwen/QwQ-32B-Preview" = 0.92,                             # Per 1M Tokens
"Qwen/Qwen2.5-Coder-32B-Instruct" = 0.62,                  # Per 1M Tokens
"Qwen/Qwen2.5-72B-Instruct" = 0.92,                        # Per 1M Tokens
"Qwen/Qwen2-72B-Instruct" = 0.96,                          # Per 1M Tokens

// image generation model
"black-forest-labs/FLUX.1-dev" = 0.020,                    # Per 1M Pixels @ 28 Steps
"black-forest-labs/FLUX.1-canny" = 0.020,                  # Per 1M Pixels @ 28 Steps
"black-forest-labs/FLUX.1-redux-dev" = 0.020,              # Per 1M Pixels @ 28 Steps
"black-forest-labs/FLUX.1-schnell" = 0.006,                # Per 1M Pixels @ 4 Steps

"stabilityai/stable-diffusion-3.5-large" = 0.05,           # Per Image
"stabilityai/stable-diffusion-3.5-large-turbo" = 0.03,     # Per Image
"stabilityai/stable-diffusion-3-medium" = 0.03,            # Per Image
"stabilityai/stable-diffusion-3.5-medium" = 0.03,          # Per Image

// video generation model
"KumoAnonymous/KumoVideo-Turbo" = 1,                       # Per Video
```


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.ora.io/doc/resilient-model-services-rms/model-and-pricing.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.