Amazon Bedrock Pricing
Pricing Overview
Jai Infoway introduces Amazon Bedrock, a comprehensive managed service that provides access to a diverse selection of high-performing foundation models (FMs) from top AI providers, including AI21 Labs, Anthropic, Cohere, Meta, Stability AI, and Amazon. This service offers a unified API for building generative AI applications, streamlining the development process while upholding privacy and security standards.
With Amazon Bedrock, billing is primarily based on model inference and customization. Clients can opt for one of two consumption plans for inference:
On Demand: This option enables users to access FMs on a pay-as-you-go basis, without the need for any fixed time-based commitments.
Provisioned Throughput: In this mode, clients can allocate sufficient throughput to meet their application’s performance needs by committing to a specific time-based term.
Jai Infoway brings you the versatility and efficiency of Amazon Bedrock, empowering you to leverage a variety of foundation models and payment options for your generative AI applications.
Pricing breakdown
Pricing is dependent on modality, provider, and model. Please select the model provider to see detailed pricing.
AI21 Labs
On-Demand pricing for inference:
| AI21 models | Price for 1000 input tokens | Price for 1000 output tokens |
|---|---|---|
Jurassic-2 Mid | $0.0125 | $0.0125 |
Jurassic-2 Ultra | $0.0188 | $0.0188 |
Currently, model customization (fine-tuning) and Provisioned Throughput are not supported for AI21 Lab models on Amazon Bedrock.
AI21 Labs
On-Demand pricing for inference:
| Amazon Titan models | Price for 1000 input tokens | Price for 1000 output tokens |
|---|---|---|
Titan Text – Lite | $0.0003 | $0.0004 |
Titan Text – Express | $0.0013 | $0.0017 |
Titan Embeddings | $0.0001 | n/a |
Pricing for model customization (fine-tuning):
| Amazon Titan | Price to train 1000 tokens* | Price to store each custom model per month | Price to infer from a custom model for 1 model unit per hour (with no-commit Provisioned Throughput pricing) |
|---|---|---|---|
Titan Text – Lite | $0.0004 | $1.95 | $7.10 |
Titan Text – Express | $0.0008 | $1.95 | $20.50 |
*Total tokens trained = number of tokens in training data corpus x number of epochs
Provisioned Throughput pricing:
| Amazon Titan models | Price per hour per model with no commitment* | Price per hour per model unit for 1-month commitment** | Price per hour for 6-month commitment** |
|---|---|---|---|
Titan Text– Lite | $7.10 | $6.40 | $5.10 |
Titan Text – Express | $20.50 | $18.40 | $14.80 |
Titan Embeddings | N/A | $6.40 | $5.10 |
*Custom model inference is limited to 1 model unit in the no-commit option. **Includes inference for base and custom models. You can buy 2+ model units.
Anthropic
On-Demand pricing:
| Anthropic models | Price for 1000 input tokens | Price for 1000 output tokens |
|---|---|---|
Claude Instant | $0.00163 | $0.00551 |
Claude | $0.01102 | $0.03268 |
Provisioned Throughput pricing:
| Anthropic models | Price per hour per model unit for 1-month commitment* | Price per hour for 6-month commitment* |
|---|---|---|
Claude Instant | $39.60 | $22.00 |
Claude | $63.00 | $35.00 |
*Includes inference for base and custom models.
Cohere
On-Demand pricing:
| Cohere models | Price for 1000 input tokens | Price for 1000 output tokens |
|---|---|---|
Command | $0.0015 | $0.0020 |
Currently, model customization (fine-tuning) and Provisioned Throughput are not supported for Cohere models on Amazon Bedrock.
Stability AI
On-Demand pricing. Image models offered by Stability are priced per image, depending on step count and image resolution:
| Stability AI model | Image resolution | Standard quality (<51 steps) | Premium quality (>51 steps) |
|---|---|---|---|
Titan Text– Lite | 512x512 or smaller | $0.018 per image | $0.036 per image |
Larger than 512x512 | $0.036 per image | $0.072 per image |
Provisioned Throughput pricing:
| Stability AI model | Price per hour per model unit for 1-month commitment* | Price per hour for 6-month commitment* |
|---|---|---|
SDXL1.0 | $49.86 | $46.18 |
*Includes inference for base and custom models. Currently, model customization (fine-tuning) is not supported for Stability AI models on Amazon Bedrock.
Pricing examples
An application developer makes the following API calls to Amazon Bedrock: A request to AI21’s Jurrasic-2 Mid model to summarize an input of 10K tokens of input text to an output of 2K tokens.
Total cost incurred is = 10K tokens/1000 * $0.0125 + 2K tokens/1000 * $0.0125 = $0.15
On-Demand pricing
An application developer makes the following API calls to Amazon Bedrock: A request to Amazon Titan Text – Lite model to summarize an input of 8K tokens of input text to an output of 2K tokens.
Total cost incurred is = 8K tokens/1000 * $0.0003 + 2K tokens/1000 * $0.0004 = $0.0032
Provisioned Throughput pricing
An application developer, buys two model units of Titan Text – Express with 1-month commitment for their text summarization use case.
Total monthly cost incurred is = 2 model units * $18.40/hour * 24 hours * 31 days = $27,279.20
On-Demand pricing
An application developer makes the following API calls to Amazon Bedrock: A request to Anthropic’s Claude model to summarize an input of 11K tokens of input text to an output of 4K tokens.
Total cost incurred is = 11K tokens/1000 * $0.01102 + 4K tokens/1000 * $0.03268 = $0.25
Provisioned Throughput pricing
An application developer, buys one model unit of Anthropic Claude Instant with 1-month commitment for their text summarization use case.
Total monthly cost incurred is 1 model unit * $39.60 * 24 hours * 31 days = $29,462.40
An application developer makes the following API calls to Amazon Bedrock: A request to Cohere’s Command model to summarize an input of 6K tokens of input text to an output of 2K tokens.
Total cost incurred is = 6K tokens/1000 * $0.00150 + 2K tokens/1000 * $0.0020 = $0.013
On-Demand pricing
An application developer makes the following API calls to Amazon Bedrock: A request to SDXL model to generate an image of 512 x 512 in size of step size of 70 (premium quality)
Total cost incurred = 1 image * $0.036 per image = $0.036
Provisioned Throughput pricing
An application developer buys one model unit of SDXL1.0 with 1-month commitment.
Total cost incurred = 1 * $49.86 * 24 hours * 31 days = $37,095.84