xAI Grok 3
The xai.grok-3 model excels at enterprise use cases such as data extraction, coding, and summarizing text. This model has a deep domain knowledge in finance, healthcare, law, and science.
The xai.grok-3 and xai.grok-3-fast models, both use the same underlying model and deliver identical response quality. The difference lies in how they're served: The xai.grok-3-fast model is served on faster infrastructure, offering response times that are significantly faster than the standard xai.grok-3 model. The increased speed comes at a higher cost per output token.
The xai.grok-3 and xai.grok-3-fast models point to the same underlying model. Select xai.grok-3-fast for latency-sensitive applications, and select xai.grok-3 for reduced cost.
Available in These Regions
- US East (Ashburn) (on-demand only)
- US Midwest (Chicago) (on-demand only)
- US West (Phoenix) (on-demand only)
External Calls
The xAI Grok models that can be accessed through the OCI Generative AI service, are hosted externally by xAI. Therefore, a call to an xAI Grok model (through the OCI Generative AI service) results in a call to an xAI location.
Key Features
- Model name in OCI
Generative AI:
xai.grok-3 - Available On-Demand: Access this model on-demand, through the Console playground or the API.
- Text-Mode Only: Input text and get a text output. (No image support.)
- Knowledge: Has a deep domain knowledge in finance, healthcare, law, and science.
- Context Length: 131,072 tokens (maximum prompt + response length is 131,072 tokens for each run). In the playground, the response length is capped at 16,000 tokens for each run.
- Excels at These Use Cases: Data extraction, coding, and summarizing text
- Function Calling: Yes, through the API.
- Structured Outputs: Yes.
- Has Reasoning: No.
- Knowledge Cutoff: November 2024
Limits
- Tokens per minute (TPM)
-
Inference calls to this model are capped at 100,000 tokens per minute (TPM) per customer or tenancy.
To see the current limit for your tenancy, in the Console, navigate to Governance and Administration. Under Tenancy Management, select Limits, quotas, and usage. Under Service, select Generative AI and review the service limits. To request a service limit increase, select Request a service limit increase. For the TPM limit increase, use the following limit name:
grok-3-chat-tokens-per-minute-count.
On-Demand Mode
-
You pay as you go for each inference call when you use the models in the playground or when you call the models through the API.
- Low barrier to start using Generative AI.
- Great for experimenting, proof of concepts, and evaluating the models.
- Available for the pretrained models in regions not listed as (dedicated AI cluster only).
To ensure reliable access to Generative AI models in the on-demand mode, we recommend implementing a back-off strategy, which involves delaying requests after a rejection. Without one, repeated rapid requests can lead to further rejections over time, increased latency, and potential temporary blocking of client by the Generative AI service. By using a back-off strategy, such as an exponential back-off strategy, you can distribute requests more evenly, reduce load, and improve retry success, following industry best practices and enhancing the overall stability and performance of your integration to the service.
The Grok models are available only in the on-demand mode.
See the following table for this model's product name in the pricing page.
| Model Name | OCI Model Name | Pricing Page Product Name |
|---|---|---|
| xAI Grok 3 | xai.grok-3 |
xAI – Grok 3 |
Release Date
| Model | Beta Release Date | General Availability Release Date | On-Demand Retirement Date | Dedicated Mode Retirement Date |
|---|---|---|---|---|
xai.grok-3 |
2025-05-22 | 2025-06-24 | Tentative | This model isn't available for the dedicated mode. |
Model Parameters
To change the model responses, you can change the values of the following parameters in the playground or the API.
- Maximum output tokens
-
The maximum number of tokens that you want the model to generate for each response. Estimate four characters per token. Because you're prompting a chat model, the response depends on the prompt and each response doesn't necessarily use up the maximum allocated tokens. The maximum prompt + output length is 131,072 tokens for each run. In the playground, the maximum output tokens is capped at 16,000 tokens for each run.
- Temperature
-
The level of randomness used to generate the output text. Min: 0, Max: 2
Tip
Start with the temperature set to 0 or less than one, and increase the temperature as you regenerate the prompts for a more creative output. High temperatures can introduce hallucinations and factually incorrect information. - Top p
-
A sampling method that controls the cumulative probability of the top tokens to consider for the next token. Assign
pa decimal number between 0 and 1 for the probability. For example, enter 0.75 for the top 75 percent to be considered. Setpto 1 to consider all tokens. - Frequency penalty
-
A penalty that's assigned to a token when that token appears frequently. High penalties encourage fewer repeated tokens and produce a more random output.
This penalty can be positive or negative. Positive numbers encourage the model to use new tokens and negative numbers encourage the model to repeat the tokens. Min: -2, Max: 2. Set to 0 to disable.
- Presence penalty
-
A penalty that's assigned to each token when it appears in the output to encourage generating outputs with tokens that haven't been used. Min: -2, Max: 2. Set to 0 to disable.