Calculate the cost of using xai.grok-4.3 from Bedrock Mantle for your AI applications
Pricing data last updated:
Mode: Responses
Max: 131,072 tokens
Max: 16,384 tokens
Built for enterprise-grade reliability, governance, and scale. Deploy in seconds.
xai.grok-4.3 is a responses model from Bedrock Mantle, one of 6 responses models they offer. It is priced at $1.25 per 1M input tokens and $2.50 per 1M output tokens, ranking 16 out of 54 responses models by cost and cheaper than 70% of models in this category. xai.grok-4.3 supports vision, function calling, reasoning, structured output — one of only 4 responses models with this combination. It accepts up to 131K input tokens.
Note: Use the interactive calculator above to estimate costs for your specific usage patterns.
Use the maximum token limits shown above to understand the model's capacity. This model can handle up to 131,072 input tokens. The maximum output length is 16,384 tokens.
At $1.25 per 1M input tokens and $2.50 per 1M output tokens, xai.grok-4.3 ranks 16 out of 54 responses models by input cost. It is more affordable compared to the median of $2.48 for responses models, and is cheaper than 70% of models in this category.
xai.grok-4.3 is one of 6 Bedrock Mantle responses models, one of only 4 responses models combining function calling, reasoning, structured output, vision.
| Model | Provider | Input / 1M tokens | Output / 1M tokens | vs xai.grok-4.3 |
|---|---|---|---|---|
| codex-mini | Azure | $1.50 | $6.00 | +20% |
| gpt-5.1-codex | Azure | $1.38 | $11.00 | +10% |
| gpt-5.1-codex-2025-11-13 | Azure | $1.25 | $10.00 | 0% |
Similar responses models from other providers
Yes. xai.grok-4.3 costs $1.25 per 1M input tokens compared to codex-mini's $1.50 per 1M input tokens, making it 20% more affordable. Both are responses models and share support for vision, function calling, reasoning, prompt caching, structured output.
xai.grok-4.3 input pricing is $1.25 per 1M tokens, which is 49% below the median of $2.48 for responses models. It ranks 16 out of 54 responses models by input cost, making it cheaper than 70% of models in this category. For output, it costs $2.50 per 1M tokens compared to the median of $15.25.
Among Bedrock Mantle's 6 responses models, xai.grok-4.3 ranks 2 by input cost. Its combination of function calling, reasoning, structured output, vision is shared by only 3 other responses models.
The most comparable responses models to xai.grok-4.3 are: codex-mini from Azure ($1.50/1M input tokens); gpt-5.1-codex from Azure ($1.38/1M input tokens); gpt-5.1-codex-2025-11-13 from Azure ($1.25/1M input tokens); gpt-5-codex from Azure ($1.25/1M input tokens). These alternatives were selected based on similar capabilities, pricing, and provider diversity. You can compare any of these models in detail using the Bifrost Model Library.
xai.grok-4.3 is priced based on input and output tokens. Use the interactive calculator at the top of this page to estimate costs for your specific workload. Enter your expected input and output tokens volume and the calculator will show the total cost breakdown. For reference, processing 1M input tokens costs $1.25 and generating 1M output tokens costs $2.50.