Amazon Bedrock

  • Model Pricing

  • Model Pricing

    Pricing is dependent on the modality, provider, and model. Please select the model provider to see detailed pricing.

    Amazon Bedrock supports a variety of tiers including Standard, Flex, Priority, and Reserved tiers. Click to learn more about service tiers.

    Amazon Bedrock offers select foundation models (FMs) from leading AI providers like Anthropic, Meta, Mistral AI, and Amazon for batch inference at a 50% lower price compared to on-demand inference pricing. To learn more about Batch, click here. Please refer to model list here. 

    • AI21 Labs

    • AI21 Labs

      On-Demand pricing

    • Amazon
      • Amazon Nova

      • Amazon Nova

        Pricing for Understanding Models

        Global Cross-region Inference

        Geo Cross-region inference and in-region

        Built-In-Tools

        Pricing for Creative Content Generation models

        Pricing for Speech Understanding and Generation Models

        On-Demand pricing for speech to speech foundation models

        Note: *The text tokens input and output pricing applies to specific use cases such as speech-to-text transcription, tool calls for task completion or knowledge grounding, adding conversation history to the session etc. 

        On-demand inference for custom Nova models is priced the same as base Nova inference.

        Pricing for Embedding models

      • Amazon Titan

      • Amazon Titan

      • Other Amazon
    • Anthropic

    • **Non-GA Models: Access to Claude Mythos 5 and Claude Mythos Preview is gated and requires approval. Contact your Anthropic account team to request access on Bedrock.

      Anthropic

      On-Demand and Batch pricing

      Models with extended access

      Provider Model Name Regions Price per 1M input tokens Price per 1M output tokens Price per 1M input tokens (batch) Price per 1M output tokens (batch) Price per 1M input tokens (cache write) Price per 1M input tokens (cache read)
       Anthropic  Claude 3.5 Sonnet (Public Extended Access, Effective 1 Dec 2025) US East (N. Virginia), US East (Ohio), US West (Oregon), Europe (Frankfurt), Europe (Ireland), Europe (Zurich), Europe (Paris) $6.00 $30.00 $3.00 $15.00 N/A N/A
      Anthropic  Claude 3.5 Sonnet v2  (Public Extended Access, Effective 1 Dec 2025) US East (N. Virginia), US East (Ohio), US West (Oregon) $6.00 $30.00 $3.00 $15.00 $7.50 $0.60

      Reserved Tier Pricing

      Latency Optimized Inference

      Provisioned Throughput Pricing

      For Provisioned Throughput pricing, please reach out to your account team.

    • Cohere

    • Cohere

      On-Demand pricing

      Cohere models Price per 1,000 queries**
      Rerank 3.5 $2.00
      **You are charged for number of queries where a query can contain up to 100 document chunks. If the query contains more than 100 document chunks, it is counted as multiple queries. For example, if a request contains 350 documents, it will be treated as 4 queries. Please note that each document can only contain upto 500 tokens (inclusive of the query and document’s total tokens), and if the token length is higher than 512 tokens, it is broken down into multiple documents.

      *Total tokens trained = number of tokens in training data corpus x number of epochs

      Provisioned Throughput pricing

      Cohere models Price per hour per model 
      with no commitment      		 Price per hour per model unit for 1-month commitment

      Price per hour per model unit for 6-month commitment

      Cohere Command

      		 $49.50

      $39.60

      $23.77
      Cohere Command - Light $8.56

      $6.85

      		 $4.11
      Embed 3 English $7.12

      $6.76

      		 $6.41
      Embed 3 Multilingual $7.12

      $6.76

      		 $6.41

      Please reach out to your AWS account or sales team for more details on model units. 

    • DeepSeek

    • DeepSeek

      On-Demand pricing

      • Standard

      • Regions: US East (N. Virginia), US East (Ohio) and US West (Oregon)

        DeepSeek models Price per 1M input tokens Price per 1M output tokens
        DeepSeek v3.2 $ 0.62 $ 1.85

        Regions: Asia Pacific (Mumbai), South America (São Paulo), Asia Pacific (Jakarta), Asia Pacific (Tokyo) and Europe (Stockholm)

        DeepSeek models Price per 1M input tokens Price per 1M output tokens
        DeepSeek v3.2 $ 0.74 $ 2.22

        Region: Asia Pacific (Sydney)

        DeepSeek models Price per 1M input tokens Price per 1M output tokens
        DeepSeek v3.1 $ 0.5974 $ 1.7304
        DeepSeek v3.2 $ 0.6386 $ 1.9055
      • Priority

      • Region: Asia Pacific (Sydney)

        DeepSeek models Price per 1M input tokens Price per 1M output tokens
        DeepSeek v3.1 $ 1.0455 $ 3.0282
      • Flex

      • Region: Asia Pacific (Sydney)

        DeepSeek models Price per 1M input tokens Price per 1M output tokens
        DeepSeek v3.1 $ 0.2987 $ 0.8652
    • Google

    • Google

      On-Demand pricing

      Regions: US East (N. Virginia), US East (Ohio) and US West (Oregon)

      Google models Price per 1M input tokens Price per 1M output tokens
      Gemma 4 31B $0.14 $0.40
      Gemma 4 26B A4B $0.13 $0.40
      Gemma 4 E2B $0.04 $ 0.08
      Gemma 3 4B $ 0.04 $ 0.08
      Gemma 3 12B $ 0.09 $ 0.29
      Gemma 3 27B $ 0.23 $ 0.38

      Regions: Europe (Frankfurt) 

      Google models Price per 1M input tokens Price per 1M output tokens
      Gemma 4 31B $ 0.17 $ 0.48
      Gemma 4 26B A4B $ 0.16 $ 0.48
      Gemma 4 E2B $ 0.05 $ 0.10

      Regions: Asia Pacific (Mumbai), Europe (Ireland) and Europe (Milan)

      Google models Price per 1M input tokens Price per 1M output tokens
      Gemma 3 4B $ 0.05 $ 0.09
      Gemma 3 12B $ 0.11 $ 0.34
      Gemma 3 27B $ 0.27 $ 0.45

      Regions: South America (Sao Paulo) and Asia Pacific (Tokyo)

      Google models Price per 1M input tokens Price per 1M output tokens
      Gemma 3 4B $ 0.05 $ 0.10
      Gemma 3 12B $ 0.11 $ 0.35
      Gemma 3 27B $ 0.28 $ 0.46

      Region: Europe (London) 

      Google models Price per 1M input tokens Price per 1M output tokens
      Gemma 3 4B $ 0.06 $ 0.12
      Gemma 3 12B $ 0.14 $ 0.45
      Gemma 3 27B $ 0.36 $ 0.59

      Region: Asia Pacific (Sydney)

      Google models Price per 1M input tokens Price per 1M output tokens
      Gemma 3 4B $ 0.0412 $ 0.0824
      Gemma 3 12B $ 0.0927 $ 0.2987
      Gemma 3 27B $ 0.2369 $ 0.3914

      * Priority tier pricing is at 75% premium to Standard tier pricing
      * Flex tier pricing is at 50% discount to Standard tier pricing

    • Luma AI