AWS
AI/ML
Amazon Bedrock
Amazon Bedrock provides access to foundation models for building generative AI applications. It handles the infrastructure needed to deploy and manage these models, allowing teams to integrate advanced language capabilities directly into their existing AWS environments without managing the underlying model training or hosting themselves.
This service suits organizations already invested in the AWS ecosystem that need scalable model inference. The main friction point is the lack of a free tier, meaning every experiment incurs costs from the start. With pricing starting at $8.75 per 1M tokens, teams must carefully budget for usage since there is no zero-cost entry point for testing or development.
- Free tier No
- Starting price from $8.75 per 1M 1K tokens
- Regions 15 · 6 continents
- SLA uptime 99.99%
- Compliance 13 certifications
- Provider health A
Decision score
59
/100
Computed from catalog breadth, pricing, provider reliability (uptime & SLA), community signal, and ecosystem (compliance & regions). Weighted equally.
Trust & reach via AWS
Compliance
- C5
- CSA STAR
- FedRAMP
- GDPR
- HIPAA
- ISO 27001
- ISO 27017
- ISO 27018
- ISO 9001
- PCI DSS
- SOC 1 Type II
- SOC 2 Type II
SLA uptime
- compute99.99%
- database99.99%
- networking99.99%
- storage99.99%
Global reach
15 regions across 6 continents
- Africa
- Asia
- Europe
- North America
- Oceania
- South America
Pricing tiers 575
| Tier / Plan | Price | Unit | Region |
|---|---|---|---|
| USE1-NovaMicro-cache-read-input-token-count | $8.75 | per 1M 1K tokens | us-east-1 |
| USE1-NovaMicro-cache-read-input-token-count-custom-model | $8.75 | per 1M 1K tokens | us-east-1 |
| USE1-google.gemma-3-4b-it-mantle-input-tokens-flex | $20.00 | per 1M 1K tokens | us-east-1 |
| USE1-Voxtral-Mini-3B-2507-input-tokens-batch | $20.00 | per 1M 1K tokens | us-east-1 |
| USE1-google.gemma-4-e2b-mantle-input-tokens-batch | $20.00 | per 1M 1K tokens | us-east-1 |
| USE1-Voxtral-Mini-3B-2507-output-tokens-batch | $20.00 | per 1M 1K tokens | us-east-1 |
| USE1-mistral.voxtral-mini-3b-2507-mantle-input-tokens-flex | $20.00 | per 1M 1K tokens | us-east-1 |
| USE1-google.gemma-3-4b-it-mantle-input-tokens-batch | $20.00 | per 1M 1K tokens | us-east-1 |
| USE1-Voxtral-Mini-3B-2507-output-tokens-flex | $20.00 | per 1M 1K tokens | us-east-1 |
| USE1-google.gemma-4-e2b-mantle-input-tokens-flex | $20.00 | per 1M 1K tokens | us-east-1 |
| USE1-mistral.voxtral-mini-3b-2507-mantle-output-tokens-flex | $20.00 | per 1M 1K tokens | us-east-1 |
| USE1-nvidia.nemotron-nano-3-30b-mantle-input-tokens-flex | $30.00 | per 1M 1K tokens | us-east-1 |
| USE1-openai.gpt-oss-safeguard-20b-mantle-input-tokens-batch | $30.00 | per 1M 1K tokens | us-east-1 |
| USE1-NovaMultiModalEmbeddings-input-standard-image-batch | $30.00 | per 1M Images Processeds | us-east-1 |
| USE1-openai.gpt-oss-safeguard-20b-mantle-input-tokens-flex | $30.00 | per 1M 1K tokens | us-east-1 |
Show all 575 pricing rows (560 more)
| Tier / Plan | Price | Unit | Region |
|---|---|---|---|
| USE1-GPT-OSS-Safeguard-20B-input-tokens-flex | $30.00 | per 1M 1K tokens | us-east-1 |
| USE1-Nemotron-Nano-3-30B-input-tokens-batch | $30.00 | per 1M 1K tokens | us-east-1 |
| USE1-TitanEmbeddingsG1-Image-input-image-batch | $30.00 | per 1M Images Processeds | us-east-1 |
| USE1-zai.glm-4.7-flash-input-tokens-batch | $35.00 | per 1M 1K tokens | us-east-1 |
| USE1-zai.glm-4.7-flash-input-tokens-flex | $35.00 | per 1M 1K tokens | us-east-1 |
| USE1-zai.glm-4.7-flash-mantle-input-tokens-flex | $35.00 | per 1M 1K tokens | us-east-1 |
| USE1-NovaMicro-input-tokens | $35.00 | per 1M 1K tokens | us-east-1 |
| USE1-NovaMicro-input-tokens-custom-model | $35.00 | per 1M 1K tokens | us-east-1 |
| USE1-openai.gpt-oss-20b-mantle-input-tokens-flex | $35.00 | per 1M 1K tokens | us-east-1 |
| USE1-google.gemma-4-e2b-mantle-output-tokens-flex | $40.00 | per 1M 1K tokens | us-east-1 |
| USE1-Gemma-3-4B-IT-output-tokens-flex | $40.00 | per 1M 1K tokens | us-east-1 |
| USE1-google.gemma-4-e2b-mantle-input-tokens-standard | $40.00 | per 1M 1K tokens | us-east-1 |
| USE1-Gemma-3-4B-IT-input-tokens | $40.00 | per 1M 1K tokens | us-east-1 |
| USE1-google.gemma-3-4b-it-mantle-output-tokens-flex | $40.00 | per 1M 1K tokens | us-east-1 |
| USE1-Voxtral-Mini-3B-2507-output-tokens | $40.00 | per 1M 1K tokens | us-east-1 |
| USE1-Nova2.0Lite-cache-read-input-token-count-flex | $41.25 | per 1M 1K tokens | us-east-1 |
| USE1-Ministral-3-3b-Instruct-output-tokens-batch | $50.00 | per 1M 1K tokens | us-east-1 |
| USE1-mistral.voxtral-small-24b-2507-mantle-input-tokens-batch | $50.00 | per 1M 1K tokens | us-east-1 |
| USE1-Gemma-3-12B-IT-input-tokens-batch | $50.00 | per 1M 1K tokens | us-east-1 |
| USE1-mistral.voxtral-small-24b-2507-mantle-input-tokens-flex | $50.00 | per 1M 1K tokens | us-east-1 |
| USE1-Voxtral-Mini-24B-2507-input-tokens-flex | $50.00 | per 1M 1K tokens | us-east-1 |
| USE1-Gemma-3-12B-IT-input-tokens-flex | $50.00 | per 1M 1K tokens | us-east-1 |
| USE1-Ministral-3-3b-Instruct-input-tokens-flex | $50.00 | per 1M 1K tokens | us-east-1 |
| USE1-Nemotron-Nano-3-30B-input-tokens | $60.00 | per 1M 1K tokens | us-east-1 |
| USE1-Nemotron-Nano-9B-V2-input-tokens | $60.00 | per 1M 1K tokens | us-east-1 |
| USE1-NovaLite-input-tokens-custom-model | $60.00 | per 1M 1K tokens | us-east-1 |
| USE1-NovaSonic-text-input-tokens | $60.00 | per 1M 1K tokens | us-east-1 |
| USE1-openai.gpt-oss-safeguard-20b-mantle-input-tokens-standard | $70.00 | per 1M 1K tokens | us-east-1 |
| USE1-Qwen3Next-80B-A3B-input-tokens-flex | $70.00 | per 1M 1K tokens | us-east-1 |
| USE1-qwen.qwen3-next-80b-a3b-instruct-mantle-input-tokens-batch | $70.00 | per 1M 1K tokens | us-east-1 |
| USE1-mistral.ministral-3-8b-instruct-mantle-output-tokens-batch | $70.00 | per 1M 1K tokens | us-east-1 |
| USE1-zai.glm-4.7-flash-input-tokens | $70.00 | per 1M 1K tokens | us-east-1 |
| USE1-GPT-OSS-Safeguard-120B-input-tokens-batch | $70.00 | per 1M 1K tokens | us-east-1 |
| USE1-google.gemma-4-31b-mantle-input-tokens-flex | $70.00 | per 1M 1K tokens | us-east-1 |
| USE1-mistral.ministral-3-8b-instruct-mantle-input-tokens-batch | $70.00 | per 1M 1K tokens | us-east-1 |
| USE1-Ministral-3-8b-Instruct-output-tokens-batch | $70.00 | per 1M 1K tokens | us-east-1 |
| USE1-openai.gpt-oss-safeguard-120b-mantle-input-tokens-batch | $70.00 | per 1M 1K tokens | us-east-1 |
| USE1-Ministral-3-8b-Instruct-input-tokens-batch | $70.00 | per 1M 1K tokens | us-east-1 |
| USE1-openai.gpt-oss-safeguard-120b-mantle-input-tokens-flex | $70.00 | per 1M 1K tokens | us-east-1 |
| USE1-openai.gpt-oss-20b-mantle-input-tokens-standard | $70.00 | per 1M 1K tokens | us-east-1 |
| USE1-mistral.voxtral-mini-3b-2507-mantle-output-tokens-priority | $70.00 | per 1M 1K tokens | us-east-1 |
| USE1-Gemma-3-4B-IT-input-tokens-priority | $70.00 | per 1M 1K tokens | us-east-1 |
| USE1-GPT-OSS-Safeguard-120B-input-tokens-flex | $70.00 | per 1M 1K tokens | us-east-1 |
| USE1-Ministral-3-8b-Instruct-output-tokens-flex | $70.00 | per 1M 1K tokens | us-east-1 |
| USE1-writer.palmyra-vision-7b-mantle-input-tokens-flex | $75.00 | per 1M 1K tokens | us-east-1 |
| USE1-writer.palmyra-vision-7b-mantle-input-tokens-batch | $75.00 | per 1M 1K tokens | us-east-1 |
| USE1-qwen.qwen3-32b-mantle-input-tokens-flex | $75.00 | per 1M 1K tokens | us-east-1 |
| USE1-openai.gpt-oss-120b-mantle-input-tokens-flex | $75.00 | per 1M 1K tokens | us-east-1 |
| USE1-Qwen3Coder-30B-A3B-input-tokens-batch | $75.00 | per 1M 1K tokens | us-east-1 |
| USE1-writer.palmyra-vision-7b-input-tokens-batch | $75.00 | per 1M 1K tokens | us-east-1 |
| USE1-qwen.qwen3-coder-30b-a3b-instruct-mantle-input-tokens-batch | $75.00 | per 1M 1K tokens | us-east-1 |
| USE1-Nova2.0Lite-cache-read-input-token-count-custom-model | $75.00 | per 1M 1K tokens | us-east-1 |
| USE1-Qwen3-32B-input-tokens-batch | $75.00 | per 1M 1K tokens | us-east-1 |
| USE1-writer.palmyra-vision-7b-input-tokens-flex | $75.00 | per 1M 1K tokens | us-east-1 |
| USE1-qwen.qwen3-32b-mantle-input-tokens-batch | $75.00 | per 1M 1K tokens | us-east-1 |
| USE1-gpt-oss-120b-input-tokens-flex | $75.00 | per 1M 1K tokens | us-east-1 |
| USE1-gpt-oss-120b-input-tokens-batch | $75.00 | per 1M 1K tokens | us-east-1 |
| USE1-nvidia.nemotron-super-3-120b-input-tokens-batch | $75.00 | per 1M 1K tokens | us-east-1 |
| USE1-qwen.qwen3-coder-30b-a3b-instruct-mantle-input-tokens-flex | $75.00 | per 1M 1K tokens | us-east-1 |
| USE1-Gemma-3-4B-IT-output-tokens | $80.00 | per 1M 1K tokens | us-east-1 |
| USE1-GuardrailChecks-PromptAttackCheckUnitsConsumed | $80.00 | per 1M Text Units | us-east-1 |
| USE1-google.gemma-3-4b-it-mantle-output-tokens-standard | $80.00 | per 1M 1K tokens | us-east-1 |
| USE1-Llama4-Scout-17B-input-tokens-batch | $85.00 | per 1M 1K tokens | us-east-1 |
| USE1-Gemma-3-12B-IT-input-tokens | $90.00 | per 1M 1K tokens | us-east-1 |
| USE1-nvidia.nemotron-nano-12b-v2-mantle-input-tokens-batch | $0.0001 | per 1K tokens | us-east-1 |
| USE1-Nemotron-Nano-12B-V2-VL-BF16-input-tokens-flex | $0.0001 | per 1K tokens | us-east-1 |
| USE1-mistral.ministral-3-14b-instruct-mantle-output-tokens-batch | $0.0001 | per 1K tokens | us-east-1 |
| USE1-GPT-OSS-Safeguard-20B-output-tokens-batch | $0.0001 | per 1K tokens | us-east-1 |
| USE1-mistral.ministral-3-14b-instruct-mantle-input-tokens-batch | $0.0001 | per 1K tokens | us-east-1 |
| USE1-Ministral-3-3b-Instruct-input-tokens | $0.0001 | per 1K tokens | us-east-1 |
| USE1-NovaPro-cache-read-input-token-count-flex | $0.0001 | per 1K tokens | us-east-1 |
| USE1-Guardrail-ContextualGroundingPolicyUnitsConsumed | $0.0001 | Text Unit | us-east-1 |
| USE1-Ministral-3-14b-Instruct-input-tokens-flex | $0.0001 | per 1K tokens | us-east-1 |
| USE1-TitanEmbeddingsG1-Text-input-tokens | $0.0001 | per 1K tokens | us-east-1 |
| USE1-Llama3-2-1B-output-tokens | $0.0001 | per 1K tokens | us-east-1 |
| USE1-openai.gpt-oss-safeguard-20b-mantle-output-tokens-batch | $0.0001 | per 1K tokens | us-east-1 |
| USE1-mistral.ministral-3-14b-instruct-mantle-output-tokens-flex | $0.0001 | per 1K tokens | us-east-1 |
| USE1-Llama3-2-1B-input-tokens | $0.0001 | per 1K tokens | us-east-1 |
| USE1-Ministral-3-14b-Instruct-input-tokens-batch | $0.0001 | per 1K tokens | us-east-1 |
| USE1-mistral.voxtral-small-24b-2507-mantle-input-tokens-standard | $0.0001 | per 1K tokens | us-east-1 |
| USE1-Llama3-1-8B-output-tokens-batch | $0.00011 | per 1K tokens | us-east-1 |
| USE1-Llama3-1-8B-input-tokens-batch | $0.00011 | per 1K tokens | us-east-1 |
| USE1-Nemotron-Nano-3-30B-input-tokens-priority | $0.00011 | per 1K tokens | us-east-1 |
| USE1-qwen.qwen3-235b-a22b-2507-mantle-input-tokens-batch | $0.00011 | per 1K tokens | us-east-1 |
| USE1-NovaMultiModalEmbeddings-input-audio-second-batch | $0.000112 | per second | us-east-1 |
| USE1-Nemotron-Nano-3-30B-output-tokens-batch | $0.00012 | per 1K tokens | us-east-1 |
| USE1-nvidia.nemotron-nano-3-30b-mantle-output-tokens-batch | $0.00012 | per 1K tokens | us-east-1 |
| USE1-google.gemma-3-27b-it-mantle-input-tokens-batch | $0.00012 | per 1K tokens | us-east-1 |
| USE1-Llama4-Maverick-17B-input-tokens-batch | $0.00012 | per 1K tokens | us-east-1 |
| USE1-Nemotron-Nano-3-30B-output-tokens-flex | $0.00012 | per 1K tokens | us-east-1 |
| USE1-nvidia.nemotron-nano-9b-v2-mantle-output-tokens-batch | $0.00012 | per 1K tokens | us-east-1 |
| USE1-NovaLite-output-tokens-batch | $0.00012 | per 1K tokens | us-east-1 |
| USE1-Gemma-3-27B-IT-input-tokens-flex | $0.00012 | per 1K tokens | us-east-1 |
| USE1-google.gemma-3-27b-it-mantle-input-tokens-flex | $0.00012 | per 1K tokens | us-east-1 |
| USE1-openai.gpt-oss-safeguard-20b-mantle-input-tokens-priority | $0.00012 | per 1K tokens | us-east-1 |
| USE1-Gemma-3-27B-IT-input-tokens-batch | $0.00012 | per 1K tokens | us-east-1 |
| USE1-gpt-oss-20b-input-tokens-priority | $0.000122 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Lite-cache-read-input-token-count-priority-cross-region-global | $0.000131 | per 1K tokens | us-east-1 |
| USE1-Gemma-3-4B-IT-output-tokens-priority | $0.00014 | per 1K tokens | us-east-1 |
| USE1-NovaMicro-output-tokens | $0.00014 | per 1K tokens | us-east-1 |
| USE1-google.gemma-4-31b-mantle-input-tokens-standard | $0.00014 | per 1K tokens | us-east-1 |
| USE1-google.gemma-3-4b-it-mantle-output-tokens-priority | $0.00014 | per 1K tokens | us-east-1 |
| USE1-NovaMultiModalEmbeddings-input-audio-second | $0.00014 | per second | us-east-1 |
| USE1-Nova2.0Lite-cache-read-input-token-count-priority | $0.000144 | per 1K tokens | us-east-1 |
| USE1-writer.palmyra-vision-7b-mantle-input-tokens-standard | $0.00015 | per 1K tokens | us-east-1 |
| USE1-google.gemma-3-12b-it-mantle-output-tokens-batch | $0.00015 | per 1K tokens | us-east-1 |
| USE1-writer.palmyra-vision-7b-input-tokens | $0.00015 | per 1K tokens | us-east-1 |
| USE1-Guardrail-ContentPolicyUnitsConsumed | $0.00015 | Text Unit | us-east-1 |
| USE1-openai.gpt-oss-20b-mantle-output-tokens-flex | $0.00015 | per 1K tokens | us-east-1 |
| USE1-Ministral-3-8b-Instruct-input-tokens | $0.00015 | per 1K tokens | us-east-1 |
| USE1-gpt-oss-120b-input-tokens | $0.00015 | per 1K tokens | us-east-1 |
| USE1-Voxtral-Mini-24B-2507-output-tokens-batch | $0.00015 | per 1K tokens | us-east-1 |
| USE1-Ministral-3-8b-Instruct-output-tokens | $0.00015 | per 1K tokens | us-east-1 |
| USE1-qwen.qwen3-coder-30b-a3b-instruct-mantle-input-tokens-standard | $0.00015 | per 1K tokens | us-east-1 |
| USE1-Llama3-2-3B-output-tokens | $0.00015 | per 1K tokens | us-east-1 |
| USE1-mistral.voxtral-small-24b-2507-mantle-output-tokens-batch | $0.00015 | per 1K tokens | us-east-1 |
| USE1-Guardrail-TopicPolicyUnitsConsumed | $0.00015 | Text Unit | us-east-1 |
| USE1-Mistral7B-input-tokens | $0.00015 | per 1K tokens | us-east-1 |
| USE1-mistral.ministral-3-8b-instruct-mantle-output-tokens-standard | $0.00015 | per 1K tokens | us-east-1 |
| USE1-Qwen3Coder-30B-A3B-input-tokens | $0.00015 | per 1K tokens | us-east-1 |
| USE1-TitanTextG1-Lite-input-tokens | $0.00015 | per 1K tokens | us-east-1 |
| USE1-Gemma-3-12B-IT-output-tokens-flex | $0.00015 | per 1K tokens | us-east-1 |
| USE1-gpt-oss-20b-output-tokens-flex | $0.00015 | per 1K tokens | us-east-1 |
| USE1-Minimax-M2-input-tokens-batch | $0.00015 | per 1K tokens | us-east-1 |
| USE1-minimax.minimax-m2.1-input-tokens-batch | $0.00015 | per 1K tokens | us-east-1 |
| USE1-openai.gpt-oss-safeguard-120b-mantle-input-tokens-standard | $0.00015 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Lite-input-tokens-flex-cross-region-global | $0.00015 | per 1K tokens | us-east-1 |
| USE1-Llama3-2-11B-input-tokens | $0.00016 | per 1K tokens | us-east-1 |
| USE1-Gemma-3-12B-IT-input-tokens-priority | $0.00016 | per 1K tokens | us-east-1 |
| USE1-google.gemma-3-12b-it-mantle-input-tokens-priority | $0.00016 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Lite-input-tokens-flex | $0.000165 | per 1K tokens | us-east-1 |
| USE1-Llama4-Scout-17B-input-tokens | $0.00017 | per 1K tokens | us-east-1 |
| USE1-mistral.ministral-3-3b-instruct-mantle-output-tokens-priority | $0.00017 | per 1K tokens | us-east-1 |
| USE1-Voxtral-Mini-24B-2507-input-tokens-priority | $0.00017 | per 1K tokens | us-east-1 |
| USE1-Guardrail-AutomatedReasoningPolicyUnitsConsumed | $0.00017 | Text Unit | us-east-1 |
| USE1-Ministral-3-3b-Instruct-output-tokens-priority | $0.00017 | per 1K tokens | us-east-1 |
| USE1-mistral.voxtral-small-24b-2507-mantle-input-tokens-priority | $0.00017 | per 1K tokens | us-east-1 |
| USE1-Ministral-3-3b-Instruct-input-tokens-priority | $0.00017 | per 1K tokens | us-east-1 |
| USE1-google.gemma-3-27b-it-mantle-output-tokens-flex | $0.00019 | per 1K tokens | us-east-1 |
| USE1-Gemma-3-27B-IT-output-tokens-batch | $0.00019 | per 1K tokens | us-east-1 |
| USE1-google.gemma-3-27b-it-mantle-output-tokens-batch | $0.00019 | per 1K tokens | us-east-1 |
| USE1-Gemma-3-27B-IT-output-tokens-flex | $0.00019 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Omni-text-input-tokens-batch | $0.0002 | per 1K tokens | us-east-1 |
| USE1-TitanEmbeddingsG1-Image-Customization-Training | $0.0002 | Images Processed | us-east-1 |
| USE1-mistral.ministral-3-14b-instruct-mantle-input-tokens-standard | $0.0002 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Omni-input-video-token-count-cross-region-global-batch | $0.0002 | per 1K tokens | us-east-1 |
| USE1-NovaPro-cache-read-input-token-count-custom-model | $0.0002 | per 1K tokens | us-east-1 |
| USE1-google.gemma-4-31b-mantle-output-tokens-flex | $0.0002 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Omni-input-image-token-count-flex | $0.0002 | per 1K tokens | us-east-1 |
| USE1-Ministral-3-14b-Instruct-output-tokens | $0.0002 | per 1K tokens | us-east-1 |
| USE1-openai.gpt-oss-safeguard-20b-mantle-output-tokens-standard | $0.0002 | per 1K tokens | us-east-1 |
| USE1-TitanTextG1-Express-input-tokens | $0.0002 | per 1K tokens | us-east-1 |
| USE1-google.gemma-4-26b-a4b-mantle-output-tokens-batch | $0.0002 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Omni-input-video-token-count-flex-cross-region-global | $0.0002 | per 1K tokens | us-east-1 |
| USE1-NovaPro-cache-read-input-token-count | $0.0002 | per 1K tokens | us-east-1 |
| USE1-mistral.devstral-2-123b-mantle-input-tokens-flex | $0.0002 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Omni-input-image-token-count-flex-cross-region-global | $0.0002 | per 1K tokens | us-east-1 |
| USE1-qwen.qwen3-coder-480b-a35b-instruct-mantle-input-tokens-batch | $0.000225 | per 1K tokens | us-east-1 |
| USE1-Nemotron-Nano-9B-V2-output-tokens | $0.00023 | per 1K tokens | us-east-1 |
| USE1-Nemotron-Nano-3-30B-output-tokens | $0.00024 | per 1K tokens | us-east-1 |
| USE1-NovaSonic-text-output-tokens | $0.00024 | per 1K tokens | us-east-1 |
| USE1-Llama4-Maverick-17B-input-tokens | $0.00024 | per 1K tokens | us-east-1 |
| USE1-NovaLite-output-tokens-custom-model | $0.00024 | per 1K tokens | us-east-1 |
| USE1-qwen.qwen3-coder-next-mantle-input-tokens-flex | $0.00025 | per 1K tokens | us-east-1 |
| USE1-Mistral-Large-3-675b-Instruct-input-tokens-flex | $0.00025 | per 1K tokens | us-east-1 |
| USE1-Magistral-Small-2509-input-tokens-batch | $0.00025 | per 1K tokens | us-east-1 |
| USE1-Claude3Haiku-input-tokens | $0.00025 | per 1K tokens | us-east-1 |
| USE1-mistral.mistral-large-3-675b-instruct-mantle-input-tokens-batch | $0.00025 | per 1K tokens | us-east-1 |
| USE1-Mistral-Large-3-675b-Instruct-input-tokens-batch | $0.00025 | per 1K tokens | us-east-1 |
| USE1-xai.grok-4.7-mantle-cache-read-tokens-global-flex | $0.00025 | per 1K tokens | us-east-1 |
| USE1-qwen.qwen3-coder-next-input-tokens-flex | $0.00025 | per 1K tokens | us-east-1 |
| USE1-qwen.qwen3-coder-next-input-tokens-batch | $0.00025 | per 1K tokens | us-east-1 |
| USE1-qwen.qwen3-vl-235b-a22b-instruct-mantle-input-tokens-flex | $0.00026 | per 1K tokens | us-east-1 |
| USE1-Qwen3Next-80B-A3B-input-tokens-priority | $0.00026 | per 1K tokens | us-east-1 |
| USE1-Ministral-3-8b-Instruct-input-tokens-priority | $0.00026 | per 1K tokens | us-east-1 |
| USE1-GPT-OSS-Safeguard-120B-input-tokens-priority | $0.00026 | per 1K tokens | us-east-1 |
| USE1-qwen.qwen3-next-80b-a3b-instruct-mantle-input-tokens-priority | $0.00026 | per 1K tokens | us-east-1 |
| USE1-Qwen3-VL-235B-A22B-input-tokens-batch | $0.00026 | per 1K tokens | us-east-1 |
| USE1-mistral.ministral-3-8b-instruct-mantle-input-tokens-priority | $0.00026 | per 1K tokens | us-east-1 |
| USE1-gpt-oss-120b-input-tokens-priority | $0.000262 | per 1K tokens | us-east-1 |
| USE1-Qwen3Coder-30B-A3B-input-tokens-priority | $0.000262 | per 1K tokens | us-east-1 |
| USE1-Qwen3-32B-input-tokens-priority | $0.000262 | per 1K tokens | us-east-1 |
| USE1-nvidia.nemotron-super-3-120b-input-tokens-priority | $0.000262 | per 1K tokens | us-east-1 |
| USE1-openai.gpt-oss-120b-mantle-input-tokens-priority | $0.000262 | per 1K tokens | us-east-1 |
| USE1-writer.palmyra-vision-7b-input-tokens-priority | $0.000262 | per 1K tokens | us-east-1 |
| USE1-deepseek.v3.1-mantle-input-tokens-batch | $0.00029 | per 1K tokens | us-east-1 |
| USE1-google.gemma-3-12b-it-mantle-output-tokens-standard | $0.00029 | per 1K tokens | us-east-1 |
| USE1-deepseek.v3.1-mantle-input-tokens-flex | $0.00029 | per 1K tokens | us-east-1 |
| USE1-writer.palmyra-vision-7b-mantle-output-tokens-batch | $0.0003 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Lite-input-tokens-cross-region-global | $0.0003 | per 1K tokens | us-east-1 |
| USE1-moonshotai.kimi-k2.5-mantle-input-tokens-batch | $0.0003 | per 1K tokens | us-east-1 |
| USE1-moonshotai.kimi-k2-thinking-mantle-input-tokens-flex | $0.0003 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Omni-text-input-tokens-cross-region-global | $0.0003 | per 1K tokens | us-east-1 |
| USE1-writer.palmyra-vision-7b-mantle-output-tokens-flex | $0.0003 | per 1K tokens | us-east-1 |
| USE1-openai.gpt-oss-20b-mantle-output-tokens-standard | $0.0003 | per 1K tokens | us-east-1 |
| USE1-Qwen3-32B-output-tokens-batch | $0.0003 | per 1K tokens | us-east-1 |
| USE1-Qwen3-32B-output-tokens-flex | $0.0003 | per 1K tokens | us-east-1 |
| USE1-openai.gpt-oss-safeguard-120b-mantle-output-tokens-batch | $0.0003 | per 1K tokens | us-east-1 |
| USE1-openai.gpt-oss-120b-mantle-output-tokens-batch | $0.0003 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Omni-input-video-token-count-cross-region-global | $0.0003 | per 1K tokens | us-east-1 |
| USE1-qwen.qwen3-coder-30b-a3b-instruct-mantle-output-tokens-batch | $0.0003 | per 1K tokens | us-east-1 |
| USE1-zai.glm-4.7-input-tokens-flex | $0.0003 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Omni-input-image-token-count | $0.0003 | per 1K tokens | us-east-1 |
| USE1-gpt-oss-120b-output-tokens-batch | $0.0003 | per 1K tokens | us-east-1 |
| USE1-Nemotron-Nano-12B-V2-VL-BF16-output-tokens-batch | $0.0003 | per 1K tokens | us-east-1 |
| USE1-writer.palmyra-vision-7b-output-tokens-flex | $0.0003 | per 1K tokens | us-east-1 |
| USE1-Qwen3Coder-30B-A3B-output-tokens-batch | $0.0003 | per 1K tokens | us-east-1 |
| USE1-zai.glm-4.7-mantle-input-tokens-batch | $0.0003 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Omni-input-video-token-count | $0.0003 | per 1K tokens | us-east-1 |
| USE1-Kimi-K2-Thinking-input-tokens-batch | $0.0003 | per 1K tokens | us-east-1 |
| USE1-moonshotai.kimi-k2.5-input-tokens-flex | $0.0003 | per 1K tokens | us-east-1 |
| USE1-nvidia.nemotron-nano-12b-v2-mantle-output-tokens-batch | $0.0003 | per 1K tokens | us-east-1 |
| USE1-minimax.minimax-m2.1-mantle-input-tokens-standard | $0.0003 | per 1K tokens | us-east-1 |
| USE1-zai.glm-4.7-input-tokens-batch | $0.0003 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Omni-text-input-tokens | $0.0003 | per 1K tokens | us-east-1 |
| USE1-Minimax-M2-input-tokens | $0.0003 | per 1K tokens | us-east-1 |
| USE1-Qwen3Coder-30B-A3B-output-tokens-flex | $0.0003 | per 1K tokens | us-east-1 |
| USE1-deepseek.v3.2-mantle-input-tokens-flex | $0.00031 | per 1K tokens | us-east-1 |
| USE1-deepseek.v3.2-input-tokens-batch | $0.00031 | per 1K tokens | us-east-1 |
| USE1-nvidia.nemotron-super-3-120b-mantle-output-tokens-batch | $0.000325 | per 1K tokens | us-east-1 |
| USE1-nvidia.nemotron-super-3-120b-output-tokens-flex | $0.000325 | per 1K tokens | us-east-1 |
| USE1-NovaSonic2.0-text-input-tokens | $0.00033 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Lite-input-tokens | $0.00033 | per 1K tokens | us-east-1 |
| USE1-mistral.ministral-3-14b-instruct-mantle-output-tokens-priority | $0.00035 | per 1K tokens | us-east-1 |
| USE1-Nemotron-Nano-12B-V2-VL-BF16-input-tokens-priority | $0.00035 | per 1K tokens | us-east-1 |
| USE1-Ministral-3-14b-Instruct-output-tokens-priority | $0.00035 | per 1K tokens | us-east-1 |
| USE1-Llama3-3-70B-input-tokens-batch | $0.00036 | per 1K tokens | us-east-1 |
| USE1-Llama3-1-70B-output-tokens-batch | $0.00036 | per 1K tokens | us-east-1 |
| USE1-Llama3-1-70B-input-tokens-batch | $0.00036 | per 1K tokens | us-east-1 |
| USE1-Gemma-3-27B-IT-output-tokens | $0.00038 | per 1K tokens | us-east-1 |
| USE1-qwen.qwen3-235b-a22b-2507-mantle-input-tokens-priority | $0.000385 | per 1K tokens | us-east-1 |
| USE1-Gemma-3-27B-IT-input-tokens-priority | $0.0004 | per 1K tokens | us-east-1 |
| USE1-TitanEmbeddingsG1-Image-input-tokens-batch | $0.0004 | per 1K tokens | us-east-1 |
| USE1-TitanTextG1-Lite-Customization-Training | $0.0004 | per 1K tokens | us-east-1 |
| USE1-NovaPro-input-tokens-batch | $0.0004 | per 1K tokens | us-east-1 |
| USE1-nvidia.nemotron-nano-9b-v2-mantle-output-tokens-priority | $0.0004 | per 1K tokens | us-east-1 |
| USE1-NovaPro-input-tokens-flex | $0.0004 | per 1K tokens | us-east-1 |
| USE1-Nemotron-Nano-3-30B-output-tokens-priority | $0.00042 | per 1K tokens | us-east-1 |
| USE1-qwen.qwen3-235b-a22b-2507-mantle-output-tokens-flex | $0.00044 | per 1K tokens | us-east-1 |
| USE1-qwen.qwen3-235b-a22b-2507-mantle-output-tokens-batch | $0.00044 | per 1K tokens | us-east-1 |
| USE1-qwen.qwen3-coder-480b-a35b-instruct-mantle-input-tokens-standard | $0.00045 | per 1K tokens | us-east-1 |
| USE1-Mixtral8x7B-input-tokens | $0.00045 | per 1K tokens | us-east-1 |
| USE1-NovaMultiModalEmbeddings-input-document-image-batch | $0.00048 | Images Processed | us-east-1 |
| USE1-Llama4-Maverick-17B-output-tokens-batch | $0.000485 | per 1K tokens | us-east-1 |
| USE1-mistral.mistral-large-3-675b-instruct-mantle-input-tokens-standard | $0.0005 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Omni-input-audio-token-count-cross-region-global-batch | $0.0005 | per 1K tokens | us-east-1 |
| USE1-DataAutomation-Custom-PagesProcessed-AddOnFields | $0.0005 | Fields per Page Processed | us-east-1 |
| USE1-zai.glm5-mantle-input-tokens-batch | $0.0005 | per 1K tokens | us-east-1 |
| USE1-MistralSmall-input-tokens-batch | $0.0005 | per 1K tokens | us-east-1 |
| USE1-DataAutomation-Custom-ImagesProcessed-AddOnFields | $0.0005 | Fields per Image Processed | us-east-1 |
| USE1-DataAutomation-Custom-AudioMinutesProcessed-AddOnFields | $0.0005 | Fields per Minute Processed | us-east-1 |
| USE1-mistral.magistral-small-2509-mantle-input-tokens-standard | $0.0005 | per 1K tokens | us-east-1 |
| USE1-TitanText-Premier-input-tokens | $0.0005 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Omni-text-input-tokens-priority-cross-region-global | $0.0005 | per 1K tokens | us-east-1 |
| USE1-qwen.qwen3-coder-next-input-tokens | $0.0005 | per 1K tokens | us-east-1 |
| USE1-zai.glm5-mantle-input-tokens-flex | $0.0005 | per 1K tokens | us-east-1 |
| USE1-xai.grok-4.6-mantle-cache-read-tokens-global-standard | $0.0005 | per 1K tokens | us-east-1 |
| USE1-DataAutomation-Custom-VideoMinutesProcessed-AddOnFields | $0.0005 | Fields per Minute Processed | us-east-1 |
| USE1-Mistral-Large-3-675b-Instruct-input-tokens | $0.0005 | per 1K tokens | us-east-1 |
| USE1-qwen.qwen3-coder-next-mantle-input-tokens-standard | $0.0005 | per 1K tokens | us-east-1 |
| USE1-Voxtral-Mini-24B-2507-output-tokens-priority | $0.00052 | per 1K tokens | us-east-1 |
| USE1-mistral.voxtral-small-24b-2507-mantle-output-tokens-priority | $0.00052 | per 1K tokens | us-east-1 |
| USE1-minimax.minimax-m2-mantle-input-tokens-priority | $0.00052 | per 1K tokens | us-east-1 |
| USE1-openai.gpt-oss-20b-mantle-output-tokens-priority | $0.000525 | per 1K tokens | us-east-1 |
| USE1-minimax.minimax-m2.5-mantle-input-tokens-priority | $0.000525 | per 1K tokens | us-east-1 |
| USE1-minimax.minimax-m2.5-input-tokens-priority | $0.000525 | per 1K tokens | us-east-1 |
| USE1-minimax.minimax-m2.1-input-tokens-priority | $0.000525 | per 1K tokens | us-east-1 |
| USE1-qwen.qwen3-vl-235b-a22b-instruct-mantle-input-tokens-standard | $0.00053 | per 1K tokens | us-east-1 |
| USE1-Qwen3-VL-235B-A22B-input-tokens | $0.00053 | per 1K tokens | us-east-1 |
| USE1-xai.grok-4.6-mantle-cache-read-tokens-standard | $0.00055 | per 1K tokens | us-east-1 |
| USE1-NovaMultiModalEmbeddings-input-video-second-batch | $0.00056 | per second | us-east-1 |
| USE1-moonshotai.kimi-k3-mantle-cache-read-tokens-priority | $0.000577 | per 1K tokens | us-east-1 |
| USE1-deepseek.v3.1-mantle-input-tokens-standard | $0.00058 | per 1K tokens | us-east-1 |
| USE1-moonshotai.kimi-k2.5-input-tokens | $0.0006 | per 1K tokens | us-east-1 |
| USE1-gpt-oss-120b-output-tokens | $0.0006 | per 1K tokens | us-east-1 |
| USE1-Qwen3-32B-output-tokens | $0.0006 | per 1K tokens | us-east-1 |
| USE1-qwen.qwen3-coder-next-mantle-output-tokens-flex | $0.0006 | per 1K tokens | us-east-1 |
| USE1-minimax.minimax-m2.5-output-tokens-batch | $0.0006 | per 1K tokens | us-east-1 |
| USE1-openai.gpt-oss-120b-mantle-output-tokens-standard | $0.0006 | per 1K tokens | us-east-1 |
| USE1-zai.glm-4.7-input-tokens | $0.0006 | per 1K tokens | us-east-1 |
| USE1-minimax.minimax-m2.1-mantle-output-tokens-flex | $0.0006 | per 1K tokens | us-east-1 |
| USE1-qwen.qwen3-coder-next-mantle-output-tokens-batch | $0.0006 | per 1K tokens | us-east-1 |
| USE1-qwen.qwen3-coder-next-output-tokens-flex | $0.0006 | per 1K tokens | us-east-1 |
| USE1-qwen.qwen3-next-80b-a3b-instruct-mantle-output-tokens-flex | $0.0006 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Omni-text-input-tokens-priority | $0.0006 | per 1K tokens | us-east-1 |
| USE1-minimax.minimax-m2.5-mantle-output-tokens-batch | $0.0006 | per 1K tokens | us-east-1 |
| USE1-Llama3-8B-output-tokens | $0.0006 | per 1K tokens | us-east-1 |
| USE1-Kimi-K2-Thinking-input-tokens | $0.0006 | per 1K tokens | us-east-1 |
| USE1-Qwen3Next-80B-A3B-output-tokens-flex | $0.0006 | per 1K tokens | us-east-1 |
| USE1-qwen.qwen3-coder-next-output-tokens-batch | $0.0006 | per 1K tokens | us-east-1 |
| USE1-TitanTextG1-Express-output-tokens | $0.0006 | per 1K tokens | us-east-1 |
| USE1-moonshotai.kimi-k2.5-mantle-input-tokens-standard | $0.0006 | per 1K tokens | us-east-1 |
| USE1-minimax.minimax-m2.1-output-tokens-batch | $0.0006 | per 1K tokens | us-east-1 |
| USE1-NovaMultiModalEmbeddings-input-document-image | $0.0006 | Images Processed | us-east-1 |
| USE1-openai.gpt-oss-safeguard-120b-mantle-output-tokens-standard | $0.0006 | per 1K tokens | us-east-1 |
| USE1-moonshotai.kimi-k2-thinking-mantle-input-tokens-standard | $0.0006 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Omni-input-audio-token-count-batch | $0.0006 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Omni-input-image-token-count-priority | $0.0006 | per 1K tokens | us-east-1 |
| USE1-Qwen3Coder-30B-A3B-output-tokens | $0.0006 | per 1K tokens | us-east-1 |
| USE1-Minimax-M2-output-tokens-batch | $0.0006 | per 1K tokens | us-east-1 |
| USE1-deepseek.v3.2-mantle-input-tokens-standard | $0.00062 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Pro-text-input-tokens-cross-region-global-batch | $0.000625 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Pro-input-video-token-count-flex-cross-region-global | $0.000625 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Pro-input-audio-token-count-cross-region-global-batch | $0.000625 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Pro-input-image-token-count-cross-region-global-batch | $0.000625 | per 1K tokens | us-east-1 |
| USE1-nvidia.nemotron-super-3-120b-mantle-output-tokens-standard | $0.00065 | per 1K tokens | us-east-1 |
| USE1-Llama4-Scout-17B-output-tokens | $0.00066 | per 1K tokens | us-east-1 |
| USE1-Gemma-3-27B-IT-output-tokens-priority | $0.00067 | per 1K tokens | us-east-1 |
| USE1-google.gemma-3-27b-it-mantle-output-tokens-priority | $0.00067 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Pro-input-image-token-count-flex | $0.000687 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Pro-input-video-token-count-batch | $0.000687 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Pro-input-video-token-count-flex | $0.000687 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Pro-text-input-tokens-flex | $0.000687 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Pro-text-input-tokens-batch | $0.000687 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Pro-input-image-token-count-batch | $0.000687 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Pro-input-audio-token-count-batch | $0.000687 | per 1K tokens | us-east-1 |
| USE1-Mixtral8x7B-output-tokens | $0.0007 | per 1K tokens | us-east-1 |
| USE1-google.gemma-4-26b-a4b-mantle-output-tokens-priority | $0.0007 | per 1K tokens | us-east-1 |
| USE1-NovaMultiModalEmbeddings-input-video-second | $0.0007 | per second | us-east-1 |
| USE1-zai.glm-4.7-flash-mantle-output-tokens-priority | $0.0007 | per 1K tokens | us-east-1 |
| USE1-zai.glm-4.7-flash-output-tokens-priority | $0.0007 | per 1K tokens | us-east-1 |
| USE1-Llama3-3-70B-input-tokens | $0.00072 | per 1K tokens | us-east-1 |
| USE1-Llama3-2-90B-output-tokens | $0.00072 | per 1K tokens | us-east-1 |
| USE1-Llama3-2-90B-input-tokens | $0.00072 | per 1K tokens | us-east-1 |
| USE1-Llama3-3-70B-output-tokens | $0.00072 | per 1K tokens | us-east-1 |
| USE1-Llama3-1-70B-input-tokens | $0.00072 | per 1K tokens | us-east-1 |
| USE1-Mistral-Large-3-675b-Instruct-output-tokens-batch | $0.00075 | per 1K tokens | us-east-1 |
| USE1-Mistral-Large-3-675b-Instruct-output-tokens-flex | $0.00075 | per 1K tokens | us-east-1 |
| USE1-mistral.mistral-large-3-675b-instruct-mantle-output-tokens-flex | $0.00075 | per 1K tokens | us-east-1 |
| USE1-qwen.qwen3-coder-480b-a35b-instruct-mantle-input-tokens-priority | $0.000788 | per 1K tokens | us-east-1 |
| USE1-TitanEmbeddingsG1-Image-input-tokens | $0.0008 | per 1K tokens | us-east-1 |
| USE1-NovaPro-input-tokens-custom-model | $0.0008 | per 1K tokens | us-east-1 |
| USE1-NovaPro-input-tokens | $0.0008 | per 1K tokens | us-east-1 |
| USE1-deepseek.v3.1-mantle-output-tokens-flex | $0.00084 | per 1K tokens | us-east-1 |
| USE1-deepseek.v3.1-mantle-output-tokens-batch | $0.00084 | per 1K tokens | us-east-1 |
| USE1-xai.grok-4.7-mantle-cache-read-tokens-global-priority | $0.000875 | per 1K tokens | us-east-1 |
| USE1-qwen.qwen3-coder-next-mantle-input-tokens-priority | $0.000875 | per 1K tokens | us-east-1 |
| USE1-xai.grok-4.6-mantle-cache-read-tokens-global-priority | $0.000875 | per 1K tokens | us-east-1 |
| USE1-mistral.mistral-large-3-675b-instruct-mantle-input-tokens-priority | $0.00088 | per 1K tokens | us-east-1 |
| USE1-Mistral-Large-3-675b-Instruct-input-tokens-priority | $0.00088 | per 1K tokens | us-east-1 |
| USE1-mistral.magistral-small-2509-mantle-input-tokens-priority | $0.00088 | per 1K tokens | us-east-1 |
| USE1-qwen.qwen3-coder-480b-a35b-instruct-mantle-output-tokens-flex | $0.0009 | per 1K tokens | us-east-1 |
| USE1-Llama3-1-70B-input-tokens-latency-optimized | $0.0009 | per 1K tokens | us-east-1 |
| USE1-deepseek.v3.2-output-tokens-flex | $0.000925 | per 1K tokens | us-east-1 |
| USE1-deepseek.v3.2-mantle-output-tokens-batch | $0.000925 | per 1K tokens | us-east-1 |
| USE1-deepseek.v3.2-mantle-output-tokens-flex | $0.000925 | per 1K tokens | us-east-1 |
| USE1-qwen.qwen3-vl-235b-a22b-instruct-mantle-input-tokens-priority | $0.00093 | per 1K tokens | us-east-1 |
| USE1-Llama4-Maverick-17B-output-tokens | $0.00097 | per 1K tokens | us-east-1 |
| USE1-xai.grok-4.6-mantle-input-tokens-global-flex | $0.001 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Omni-input-audio-token-count-cross-region-global | $0.001 | per 1K tokens | us-east-1 |
| USE1-zai.glm5-input-tokens | $0.001 | per 1K tokens | us-east-1 |
| USE1-mistral.devstral-2-123b-output-tokens-flex | $0.001 | per 1K tokens | us-east-1 |
| USE1-MistralSmall-input-tokens | $0.001 | per 1K tokens | us-east-1 |
| USE1-mistral.devstral-2-123b-mantle-output-tokens-batch | $0.001 | per 1K tokens | us-east-1 |
| USE1-gpt-oss-120b-output-tokens-priority | $0.00105 | per 1K tokens | us-east-1 |
| USE1-Kimi-K2-Thinking-input-tokens-priority | $0.00105 | per 1K tokens | us-east-1 |
| USE1-Qwen3-32B-output-tokens-priority | $0.00105 | per 1K tokens | us-east-1 |
| USE1-nvidia.nemotron-nano-12b-v2-mantle-output-tokens-priority | $0.00105 | per 1K tokens | us-east-1 |
| USE1-Qwen3Coder-30B-A3B-output-tokens-priority | $0.00105 | per 1K tokens | us-east-1 |
| USE1-openai.gpt-oss-120b-mantle-output-tokens-priority | $0.00105 | per 1K tokens | us-east-1 |
| USE1-moonshotai.kimi-k2.5-input-tokens-priority | $0.00105 | per 1K tokens | us-east-1 |
| USE1-openai.gpt-oss-safeguard-120b-mantle-output-tokens-priority | $0.00105 | per 1K tokens | us-east-1 |
| USE1-qwen.qwen3-32b-mantle-output-tokens-priority | $0.00105 | per 1K tokens | us-east-1 |
| USE1-zai.glm-4.7-mantle-input-tokens-priority | $0.00105 | per 1K tokens | us-east-1 |
| USE1-moonshotai.kimi-k2-thinking-mantle-input-tokens-priority | $0.00105 | per 1K tokens | us-east-1 |
| USE1-deepseek.v3.2-input-tokens-priority | $0.00109 | per 1K tokens | us-east-1 |
| USE1-deepseek.v3.2-mantle-input-tokens-priority | $0.00109 | per 1K tokens | us-east-1 |
| USE1-zai.glm-4.7-mantle-output-tokens-batch | $0.0011 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Omni-input-audio-token-count | $0.0011 | per 1K tokens | us-east-1 |
| USE1-zai.glm-4.7-output-tokens-batch | $0.0011 | per 1K tokens | us-east-1 |
| USE1-zai.glm-4.7-mantle-output-tokens-flex | $0.0011 | per 1K tokens | us-east-1 |
| USE1-Llama3-1-405B-output-tokens-batch | $0.0012 | per 1K tokens | us-east-1 |
| USE1-Minimax-M2-output-tokens | $0.0012 | per 1K tokens | us-east-1 |
| USE1-qwen.qwen3-coder-next-output-tokens | $0.0012 | per 1K tokens | us-east-1 |
| USE1-qwen.qwen3-next-80b-a3b-instruct-mantle-output-tokens-standard | $0.0012 | per 1K tokens | us-east-1 |
| USE1-minimax.minimax-m2.1-output-tokens | $0.0012 | per 1K tokens | us-east-1 |
| USE1-Llama3-1-405B-input-tokens-batch | $0.0012 | per 1K tokens | us-east-1 |
| USE1-minimax.minimax-m2-mantle-output-tokens-standard | $0.0012 | per 1K tokens | us-east-1 |
| USE1-NovaPremier-input-tokens-flex | $0.00125 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Pro-input-image-token-count-cross-region-global | $0.00125 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Lite-output-tokens-flex-cross-region-global | $0.00125 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Pro-text-input-tokens-cross-region-global | $0.00125 | per 1K tokens | us-east-1 |
| USE1-moonshotai.kimi-k2-thinking-mantle-output-tokens-flex | $0.00125 | per 1K tokens | us-east-1 |
| USE1-moonshotai.kimi-k2-thinking-mantle-output-tokens-batch | $0.00125 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Pro-input-video-token-count-cross-region-global | $0.00125 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Pro-input-audio-token-count-cross-region-global | $0.00125 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Omni-text-output-tokens-cross-region-global-batch | $0.0013 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Omni-text-output-tokens-flex-cross-region-global | $0.0013 | per 1K tokens | us-east-1 |
| USE1-Qwen3-VL-235B-A22B-output-tokens-flex | $0.00133 | per 1K tokens | us-east-1 |
| USE1-DeepSeek-R1-input-tokens | $0.00135 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Pro-input-image-token-count | $0.00137 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Lite-output-tokens-batch | $0.00137 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Pro-text-input-tokens | $0.00137 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Lite-output-tokens-flex | $0.00137 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Pro-input-audio-token-count | $0.00137 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Omni-text-output-tokens-flex | $0.0014 | per 1K tokens | us-east-1 |
| USE1-NovaPro-input-tokens-priority | $0.0014 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Omni-text-output-tokens-batch | $0.0014 | per 1K tokens | us-east-1 |
| USE1-moonshotai.kimi-k2.5-output-tokens-flex | $0.0015 | per 1K tokens | us-east-1 |
| USE1-moonshotai.kimi-k3-mantle-input-tokens-global-flex | $0.0015 | per 1K tokens | us-east-1 |
| USE1-moonshotai.kimi-k2.5-output-tokens-batch | $0.0015 | per 1K tokens | us-east-1 |
| USE1-TitanText-Premier-output-tokens | $0.0015 | per 1K tokens | us-east-1 |
| USE1-MistralSmall-output-tokens-batch | $0.0015 | per 1K tokens | us-east-1 |
| USE1-qwen.qwen3-235b-a22b-2507-mantle-output-tokens-priority | $0.00154 | per 1K tokens | us-east-1 |
| USE1-zai.glm5-mantle-output-tokens-batch | $0.0016 | per 1K tokens | us-east-1 |
| USE1-zai.glm5-mantle-output-tokens-flex | $0.0016 | per 1K tokens | us-east-1 |
| USE1-NovaPro-output-tokens-flex | $0.0016 | per 1K tokens | us-east-1 |
| USE1-moonshotai.kimi-k3-mantle-input-tokens-flex | $0.00165 | per 1K tokens | us-east-1 |
| USE1-moonshotai.kimi-k3-mantle-input-tokens-batch | $0.00165 | per 1K tokens | us-east-1 |
| USE1-deepseek.v3.1-mantle-output-tokens-standard | $0.00168 | per 1K tokens | us-east-1 |
| USE1-zai.glm5-input-tokens-priority | $0.00175 | per 1K tokens | us-east-1 |
| USE1-zai.glm5-mantle-input-tokens-priority | $0.00175 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Omni-input-audio-token-count-priority-cross-region-global | $0.0018 | per 1K tokens | us-east-1 |
| USE1-qwen.qwen3-coder-480b-a35b-instruct-mantle-output-tokens-standard | $0.0018 | per 1K tokens | us-east-1 |
| USE1-deepseek.v3.2-output-tokens | $0.00185 | per 1K tokens | us-east-1 |
| USE1-deepseek.v3.2-mantle-output-tokens-standard | $0.00185 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Omni-input-audio-token-count-priority | $0.0019 | per 1K tokens | us-east-1 |
| USE1-GenerateSQL-StructuredRetrieve | $0.002 | per request | us-east-1 |
| USE1-mistral.devstral-2-123b-output-tokens | $0.002 | per 1K tokens | us-east-1 |
| USE1-NovaLite-Customization-Training | $0.002 | per 1K tokens | us-east-1 |
| USE1-mistral.devstral-2-123b-mantle-output-tokens-standard | $0.002 | per 1K tokens | us-east-1 |
| USE1-xai.grok-4.6-mantle-input-tokens-global-standard | $0.002 | per 1K tokens | us-east-1 |
| USE1-minimax.minimax-m2.1-output-tokens-priority | $0.0021 | per 1K tokens | us-east-1 |
| USE1-qwen.qwen3-next-80b-a3b-instruct-mantle-output-tokens-priority | $0.0021 | per 1K tokens | us-east-1 |
| USE1-Minimax-M2-output-tokens-priority | $0.0021 | per 1K tokens | us-east-1 |
| USE1-minimax.minimax-m2.1-mantle-output-tokens-priority | $0.0021 | per 1K tokens | us-east-1 |
| USE1-qwen.qwen3-coder-next-output-tokens-priority | $0.0021 | per 1K tokens | us-east-1 |
| USE1-Qwen3Next-80B-A3B-output-tokens-priority | $0.0021 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Pro-input-audio-token-count-priority-cross-region-global | $0.00219 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Pro-text-input-tokens-priority-cross-region-global | $0.00219 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Pro-input-image-token-count-priority-cross-region-global | $0.00219 | per 1K tokens | us-east-1 |
| USE1-zai.glm-4.7-output-tokens | $0.0022 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Pro-input-audio-token-count-priority | $0.00241 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Pro-text-input-tokens-priority | $0.00241 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Pro-input-video-token-count-priority | $0.00241 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Omni-text-output-tokens-cross-region-global | $0.0025 | per 1K tokens | us-east-1 |
| USE1-moonshotai.kimi-k2-thinking-mantle-output-tokens-standard | $0.0025 | per 1K tokens | us-east-1 |
| USE1-Qwen3-VL-235B-A22B-output-tokens | $0.00266 | per 1K tokens | us-east-1 |
| USE1-qwen.qwen3-vl-235b-a22b-instruct-mantle-output-tokens-standard | $0.00266 | per 1K tokens | us-east-1 |
| USE1-NovaSonic2.5-text-output-tokens | $0.00275 | per 1K tokens | us-east-1 |
| USE1-deepseek.v3.1-mantle-output-tokens-priority | $0.00294 | per 1K tokens | us-east-1 |
| USE1-moonshotai.kimi-k3-mantle-input-tokens-global-standard | $0.003 | per 1K tokens | us-east-1 |
| USE1-DataAutomation-Standard-ImagesProcessed | $0.003 | Images Processed | us-east-1 |
| USE1-moonshotai.kimi-k2.5-output-tokens | $0.003 | per 1K tokens | us-east-1 |
| USE1-xai.grok-4.6-mantle-output-tokens-global-flex | $0.003 | per 1K tokens | us-east-1 |
| USE1-NovaSonic2.0-speech-input-tokens | $0.003 | per 1K tokens | us-east-1 |
| USE1-MistralSmall-output-tokens | $0.003 | per 1K tokens | us-east-1 |
| USE1-xai.grok-4.7-mantle-output-tokens-global-flex | $0.003 | per 1K tokens | us-east-1 |
| USE1-moonshotai.kimi-k2.5-mantle-output-tokens-standard | $0.003 | per 1K tokens | us-east-1 |
| USE1-zai.glm5-mantle-output-tokens-standard | $0.0032 | per 1K tokens | us-east-1 |
| USE1-NovaPro-output-tokens | $0.0032 | per 1K tokens | us-east-1 |
| USE1-deepseek.v3.2-mantle-output-tokens-priority | $0.00324 | per 1K tokens | us-east-1 |
| USE1-xai.grok-4.6-mantle-output-tokens-flex | $0.0033 | per 1K tokens | us-east-1 |
| USE1-moonshotai.kimi-k3-mantle-input-tokens-standard | $0.0033 | per 1K tokens | us-east-1 |
| USE1-xai.grok-4.7-mantle-output-tokens-batch | $0.0033 | per 1K tokens | us-east-1 |
| USE1-xai.grok-4.7-mantle-input-tokens-global-priority | $0.0035 | per 1K tokens | us-east-1 |
| USE1-mistral.devstral-2-123b-output-tokens-priority | $0.0035 | per 1K tokens | us-east-1 |
| USE1-moonshotai.kimi-k3-mantle-cache-write-tokens-30m-global-standard | $0.00375 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Lite-Customization-Training | $0.00378 | per 1K tokens | us-east-1 |
| USE1-zai.glm-4.7-mantle-output-tokens-priority | $0.00385 | per 1K tokens | us-east-1 |
| USE1-MistralLarge-input-tokens | $0.004 | per 1K tokens | us-east-1 |
| USE1-moonshotai.kimi-k3-mantle-cache-write-tokens-30m-standard | $0.00413 | per 1K tokens | us-east-1 |
| USE1-moonshotai.kimi-k2-thinking-mantle-output-tokens-priority | $0.00438 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Omni-text-output-tokens-priority-cross-region-global | $0.0044 | per 1K tokens | us-east-1 |
| USE1-Qwen3-VL-235B-A22B-output-tokens-priority | $0.00466 | per 1K tokens | us-east-1 |
| USE1-qwen.qwen3-vl-235b-a22b-instruct-mantle-output-tokens-priority | $0.00466 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Omni-text-output-tokens-priority | $0.0048 | per 1K tokens | us-east-1 |
| USE1-DataAutomation-Custom-ImagesProcessed | $0.005 | Images Processed | us-east-1 |
| USE1-Nova2.0Pro-text-output-tokens-cross-region-global-batch | $0.005 | per 1K tokens | us-east-1 |
| USE1-moonshotai.kimi-k3-mantle-input-tokens-global-priority | $0.00525 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Pro-text-output-tokens-batch | $0.0055 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Pro-text-output-tokens-flex | $0.0055 | per 1K tokens | us-east-1 |
| USE1-PixtralLarge2502-output-tokens | $0.006 | per 1K tokens | us-east-1 |
| USE1-NovaPremier-output-tokens-batch | $0.00625 | per 1K tokens | us-east-1 |
| USE1-NovaPremier-output-tokens-flex | $0.00625 | per 1K tokens | us-east-1 |
| USE1-moonshotai.kimi-k3-mantle-cache-write-tokens-30m-global-priority | $0.00656 | per 1K tokens | us-east-1 |
| USE1-xai.grok-4.6-mantle-output-tokens-standard | $0.0066 | per 1K tokens | us-east-1 |
| USE1-TitanImageGeneratorV2-I2I-512-Standard | $0.008 | image | us-east-1 |
| USE1-TitanImageGeneratorG1-I2I-512-Standard | $0.008 | image | us-east-1 |
| USE1-Claude2.1-input-tokens | $0.008 | per 1K tokens | us-east-1 |
| USE1-TitanImageGeneratorG1-T2I-512-Standard | $0.008 | image | us-east-1 |
| USE1-NovaPro-Customization-Training | $0.008 | per 1K tokens | us-east-1 |
| USE1-Claude2.0-input-tokens | $0.008 | per 1K tokens | us-east-1 |
| USE1-TitanImageGeneratorV2-I2I-1024-Standard | $0.0100 | image | us-east-1 |
| USE1-TitanImageGeneratorV2-T2I-1024-Standard | $0.0100 | image | us-east-1 |
| USE1-DataAutomation-Standard-PagesProcessed | $0.0100 | Pages Processed | us-east-1 |
| USE1-TitanImageGeneratorG1-T2I-1024-Standard | $0.0100 | image | us-east-1 |
| USE1-xai.grok-4.6-mantle-output-tokens-global-priority | $0.0105 | per 1K tokens | us-east-1 |
| USE1-xai.grok-4.7-mantle-output-tokens-global-priority | $0.0105 | per 1K tokens | us-east-1 |
| USE1-xai.grok-4.7-mantle-output-tokens-priority | $0.0115 | per 1K tokens | us-east-1 |
| USE1-Bedrock-Websearch-Queries | $0.0120 | Queries | us-east-1 |
| USE1-NovaSonic2.0-speech-output-tokens | $0.0120 | per 1K tokens | us-east-1 |
| USE1-TitanImageGeneratorG1-T2I-1024-Premium | $0.0120 | image | us-east-1 |
| USE1-MistralLarge-output-tokens | $0.0120 | per 1K tokens | us-east-1 |
| USE1-NovaSonic-speech-output-tokens | $0.0136 | per 1K tokens | us-east-1 |
| USE1-moonshotai.kimi-k3-mantle-output-tokens-standard | $0.0165 | per 1K tokens | us-east-1 |
| USE1-TitanImageGeneratorG1-Custom-T2I-512-Standard | $0.0180 | image | us-east-1 |
| USE1-Nova2.0Omni-output-image-token-count-cross-region-global-batch | $0.0200 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Omni-output-image-token-count-flex-cross-region-global | $0.0200 | per 1K tokens | us-east-1 |
| USE1-TitanImageGeneratorG1-Custom-T2I-1024-Premium | $0.0220 | image | us-east-1 |
| USE1-moonshotai.kimi-k3-mantle-output-tokens-global-priority | $0.0262 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Omni-nova-grounding | $0.0300 | per request | us-east-1 |
| USE1-Nova2.0Lite-nova-grounding | $0.0300 | per request | us-east-1 |
| USE1-APO-v1-optimizePrompt | $0.0300 | per 1K tokens | us-east-1 |
| USE1-NovaPremier-nova-grounding | $0.0300 | per request | us-east-1 |
| USE1-NovaCanvas-T2I-1024-Standard | $0.0400 | image | us-east-1 |
| USE1-DataAutomation-Custom-PagesProcessed | $0.0400 | Pages Processed | us-east-1 |
| USE1-Nova2.0Omni-output-image-token-count-cross-region-global | $0.0400 | per 1K tokens | us-east-1 |
| USE1-Nova2.0Omni-output-image-token-count | $0.0440 | per 1K tokens | us-east-1 |
| USE1-DataAutomation-Standard-VideoMinutesProcessed | $0.0500 | Minutes Processed | us-east-1 |
| USE1-GPTBigCode-CustomModelImport-Inference-v1:0 | $0.0572 | Custom Model Unit per Min | us-east-1 |
| USE1-Mixtral-CustomModelImport-Inference-v1:0 | $0.0572 | Custom Model Unit per Min | us-east-1 |
| USE1-Flan-CustomModelImport-Inference-v1:0 | $0.0572 | Custom Model Unit per Min | us-east-1 |
| USE1-Qwen2VL-CustomModelImport-Inference-v1:0 | $0.0572 | Custom Model Unit per Min | us-east-1 |
| USE1-Llama-CustomModelImport-Inference-v1:0 | $0.0572 | Custom Model Unit per Min | us-east-1 |
| USE1-NovaCanvas-I2I-1024-Premium | $0.0600 | image | us-east-1 |
| USE1-NovaCanvas-T2I-1024-Premium | $0.0600 | image | us-east-1 |
| USE1-NovaCanvas-T2I-2048-Standard | $0.0600 | image | us-east-1 |
| USE1-Nova2.0Omni-output-image-token-count-priority | $0.0770 | per 1K tokens | us-east-1 |
| USE1-NovaReel-I2V-Medfps-HDRes | $0.0800 | video | us-east-1 |
| USE1-NovaCanvas-I2I-2048-Premium | $0.0800 | image | us-east-1 |
| USE1-DataAutomation-Custom-VideoMinutesProcessed | $0.0840 | Minutes Processed | us-east-1 |
| USE1-OSS-CustomModelImport-Inference-v2:0 | $0.1433 | Custom Model Unit per Min | us-east-1 |
| USE1-xai.grok-4.3-mantle-cache-read-tokens-priority | $0.3500 | per 1M tokens | us-east-1 |
| USE1-xai.grok-4.3-mantle-input-tokens-flex | $0.6250 | per 1M tokens | us-east-1 |
| USE1-Prompt-Routing-requests | $1.00 | per 1K requests | us-east-1 |
| USE1-xai.grok-4.3-mantle-output-tokens-batch | $1.25 | per 1M tokens | us-east-1 |
| USE1-xai.grok-4.3-mantle-output-tokens-flex | $1.25 | per 1M tokens | us-east-1 |
| USE1-xai.grok-4.3-mantle-input-tokens-standard | $1.25 | per 1M tokens | us-east-1 |
| USE1-TitanTextG1-Lite-Customization-Storage | $1.95 | Model/month | us-east-1 |
| USE1-TitanImageGeneratorG1-Customization-Storage | $1.95 | Model/month | us-east-1 |
| USE1-TitanTextG1-Express-Customization-Storage | $1.95 | Model/month | us-east-1 |
| USE1-NovaCanvas-Customization-Storage | $1.95 | Model/month | us-east-1 |
| USE1-Qwen2VL-CustomModelImport-Storage-v1:0 | $1.95 | Model/month | us-east-1 |
| USE1-TitanText-Premier-Customization-Storage | $1.95 | Model/month | us-east-1 |
| USE1-TitanEmbeddingsG1-Image-Customization-Storage | $1.95 | Model/month | us-east-1 |
| USE1-OSS-CustomModelImport-Storage-v2:0 | $1.95 | Model/month | us-east-1 |
| USE1-xai.grok-4.3-mantle-input-tokens-priority | $2.19 | per 1M tokens | us-east-1 |
| USE1-xai.grok-4.3-mantle-output-tokens-standard | $2.50 | per 1M tokens | us-east-1 |
| USE1-xai.grok-4.3-mantle-output-tokens-priority | $4.38 | per 1M tokens | us-east-1 |
| USE1-TitanEmbeddingsG1-Text-ProvisionedThroughput-6months-ModelUnits | $5.10 | per hour | us-east-1 |
| USE1-TitanTextG1-Lite-ProvisionedThroughput-1month-ModelUnits | $6.40 | per hour | us-east-1 |
| USE1-TitanEmbeddingsG1-Text-ProvisionedThroughput-1month-ModelUnits | $6.40 | per hour | us-east-1 |
| USE1-TitanEmbeddingsG1-Image-ProvisionedThroughput-NoCommit-ModelUnits | $9.38 | per hour | us-east-1 |
| USE1-TitanTextG1-Express-ProvisionedThroughput-6months-ModelUnits | $14.80 | per hour | us-east-1 |
| USE1-TitanImageGeneratorG1-ProvisionedThroughput-1month-ModelUnits | $16.20 | per hour | us-east-1 |
| USE1-TitanImageGeneratorV2-ProvisionedThroughput-1month-ModelUnits | $16.20 | per hour | us-east-1 |
| USE1-TitanText-Premier-ProvisionedThroughput-Custom-6months-ModelUnits | $16.38 | per hour | us-east-1 |
| USE1-TitanImageGeneratorV2-ProvisionedThroughput-Custom-6months-ModelUnits | $16.85 | per hour | us-east-1 |
| USE1-TitanTextG1-Express-ProvisionedThroughput-NoCommit-ModelUnits | $20.50 | per hour | us-east-1 |
| USE1-TitanImageGeneratorG1-ProvisionedThroughput-Custom-1month-ModelUnits | $21.00 | per hour | us-east-1 |
| USE1-TitanImageGeneratorV2-ProvisionedThroughput-Custom-1month-ModelUnits | $21.00 | per hour | us-east-1 |
| USE1-TitanImageGeneratorG1-ProvisionedThroughput-Custom-NoCommit-ModelUnits | $23.40 | per hour | us-east-1 |
| USE1-TitanText-Premier-ProvisionedThroughput-Custom-1month-ModelUnits | $27.95 | per hour | us-east-1 |
| USE1-Nova2.0Lite-ProvisionedThroughput-6months-ModelUnits | $30.25 | per hour | us-east-1 |
| USE1-TitanText-Premier-ProvisionedThroughput-Custom-NoCommit-ModelUnits | $32.25 | per hour | us-east-1 |
| USE1-NovaLite-ProvisionedThroughput-1month-ModelUnits | $55.00 | per hour | us-east-1 |
| USE1-Nova2.0Lite-ProvisionedThroughput-1month-ModelUnits | $55.00 | per hour | us-east-1 |
| USE1-NovaPro-ProvisionedThroughput-NoCommit-ModelUnits | $60.50 | per hour | us-east-1 |
| USE1-NovaCanvas-ProvisionedThroughput-NoCommit-ModelUnits | $60.50 | per hour | us-east-1 |
Prices in USD. Micro-prices are quoted per 1M units; "< $0.000001" marks rates below our stored precision. Subject to change — check the provider's official page.
Alternatives on other providers
Equivalent services on other clouds: