Bedrock (LLM inference) costs

Tensor9 BYOC planning comparisons for aws::1.0.0::bedrock, with backend choices shown together. Read how to think about service-adapter costs for price scope and capacity qualification, or return to additional services.

​

Bedrock model inference → Anthropic Messages API

Origin API: aws::1.0.0::bedrock. Target backend: anthropic::1.0.0::messages. Planning estimate with editable assumptions. Unit rates, workload amplification and capacity assumptions are educated guesses awaiting verification. The displayed amounts are planning estimates, not verified provider list-price quotes or benchmark-qualified capacity. Region names identify the authored scenario assumptions.

​

Bedrock model inference · Input tokens per second

Planning estimate with editable assumptions. These authored unit rates and capacity assumptions require provider-price verification and representative benchmarks. They do not constitute verified list-price quotes or evidence that an adapter is available. Estimated monthly service charges from native source usage; no calculator input is required. Adapter hosting and Tensor9 fees are excluded. Source: Explicit source planning region; target: Explicit target planning region; currency: USD. Exact sampled model outputs in USD/month. Difference means target minus origin; a positive difference means the target costs more. Curve assumptions

• Only this native meter varies; all other source usage and translation assumptions retain the displayed defaults. Editable authored planning guesses, not verified provider tariffs, benchmark measurements or a commercial quote. Other native meters retain their explicitly displayed default quantities.
• Planning estimate · editable authored rates and sizing assumptions dated 2026-10-18; not verified provider prices. Explicit source planning region → Explicit target planning region, USD/month.
• Source prices are reference charges, not an invoice. Target lines cover selected service usage/configuration only; adapter hosting and Tensor9 fees are excluded.
• Explicit tariff samples are not performance measurements or capacity qualification. No interpolation or break-even guarantee is implied.
• Variant assumptions show the first axis sample; any axis-dependent configuration is described by this curve’s workload note.
• Editable authored planning guesses, not verified provider tariffs, benchmark measurements or a commercial quote.
• Default-zero rates are explicit assumptions, not evidence that the deployed service or resource is free.
• Provisioned-unit minimums use an editable approximate allocation floor. Modeled target service cost is max(usage/allocation, minimum), with billable network, durable staging and dependent sinks added separately; actual RU/TU sizing, scaling increments and throughput remain unqualified.
• Durable staging is priced once: provisioned targets include adapter state in their selected allocation; native targets add a separate staging allocation when required. Adapter hosting is a separate allocation and must exclude resources already priced as staging, workers or target capacity.
• A declared adapter mapping and cost model do not establish implementation availability or service equivalence.
• This is a declared directed mapping; a planning estimate does not establish deployment or request-serving support.
• All default unit prices and capacity coefficients are editable authored planning guesses, not measured capacity or a provider quote.
• Source and target tariffs name no asserted current model SKU. Select model-specific rates before using the estimate.
• Input and output meters and token expansion remain independent. A cheaper model is not automatically equivalent in capability or quality.
• All target rates are editable authored planning guesses, not verified current list prices, customer discounts or benchmark evidence.
• Input and output token tariffs remain distinct. These illustrative rates name no selected model SKU and establish no equivalent output quality or tokenizer.

Cost scope: Modeled target native service and explicitly modeled state allocation; hosting and Tensor9 fees only when supplied. Excluded costs and workload features:

• Prompt caching, batch discounts, context tiers, grounding, tools, agents, embeddings, search, guardrails and dedicated inference hardware.
• Taxes, discounts, credits and free-tier allowances unless explicitly reflected in edited rates.
• Unmodeled dependent services, task execution and operations outside the selected workload family.

Planning assumptions authored: 2026-10-18. Model: plan-ccde7cd673441e8ba203e027d2e5f895e072eb7c / 2026-10-18.planning.1. Curve: workload-1.

​

Bedrock model inference · Output tokens per second

Planning estimate with editable assumptions. These authored unit rates and capacity assumptions require provider-price verification and representative benchmarks. They do not constitute verified list-price quotes or evidence that an adapter is available. Estimated monthly service charges from native source usage; no calculator input is required. Adapter hosting and Tensor9 fees are excluded. Source: Explicit source planning region; target: Explicit target planning region; currency: USD. Exact sampled model outputs in USD/month. Difference means target minus origin; a positive difference means the target costs more. Curve assumptions

• Only this native meter varies; all other source usage and translation assumptions retain the displayed defaults. Editable authored planning guesses, not verified provider tariffs, benchmark measurements or a commercial quote. Other native meters retain their explicitly displayed default quantities.
• Planning estimate · editable authored rates and sizing assumptions dated 2026-10-18; not verified provider prices. Explicit source planning region → Explicit target planning region, USD/month.
• Source prices are reference charges, not an invoice. Target lines cover selected service usage/configuration only; adapter hosting and Tensor9 fees are excluded.
• Explicit tariff samples are not performance measurements or capacity qualification. No interpolation or break-even guarantee is implied.
• Variant assumptions show the first axis sample; any axis-dependent configuration is described by this curve’s workload note.
• Editable authored planning guesses, not verified provider tariffs, benchmark measurements or a commercial quote.
• Default-zero rates are explicit assumptions, not evidence that the deployed service or resource is free.
• Provisioned-unit minimums use an editable approximate allocation floor. Modeled target service cost is max(usage/allocation, minimum), with billable network, durable staging and dependent sinks added separately; actual RU/TU sizing, scaling increments and throughput remain unqualified.
• Durable staging is priced once: provisioned targets include adapter state in their selected allocation; native targets add a separate staging allocation when required. Adapter hosting is a separate allocation and must exclude resources already priced as staging, workers or target capacity.
• A declared adapter mapping and cost model do not establish implementation availability or service equivalence.
• This is a declared directed mapping; a planning estimate does not establish deployment or request-serving support.
• All default unit prices and capacity coefficients are editable authored planning guesses, not measured capacity or a provider quote.
• Source and target tariffs name no asserted current model SKU. Select model-specific rates before using the estimate.
• Input and output meters and token expansion remain independent. A cheaper model is not automatically equivalent in capability or quality.
• All target rates are editable authored planning guesses, not verified current list prices, customer discounts or benchmark evidence.
• Input and output token tariffs remain distinct. These illustrative rates name no selected model SKU and establish no equivalent output quality or tokenizer.

Cost scope: Modeled target native service and explicitly modeled state allocation; hosting and Tensor9 fees only when supplied. Excluded costs and workload features:

• Prompt caching, batch discounts, context tiers, grounding, tools, agents, embeddings, search, guardrails and dedicated inference hardware.
• Taxes, discounts, credits and free-tier allowances unless explicitly reflected in edited rates.
• Unmodeled dependent services, task execution and operations outside the selected workload family.

Planning assumptions authored: 2026-10-18. Model: plan-ccde7cd673441e8ba203e027d2e5f895e072eb7c / 2026-10-18.planning.1. Curve: workload-2.

​

Bedrock model inference → Azure RAI Content Filter Policy

Origin API: aws::1.0.0::bedrock. Target backend: azure::1.0.0::rai-policy. Planning estimate with editable assumptions. Unit rates, workload amplification and capacity assumptions are educated guesses awaiting verification. The displayed amounts are planning estimates, not verified provider list-price quotes or benchmark-qualified capacity. Region names identify the authored scenario assumptions. Native or deployment mapping. This mapping provisions an Azure content-filter policy. A policy is not a Bedrock inference endpoint; inference adapters have their own operation-specific terms. Cost estimates describe the selected service resources; operation coverage remains separate.

​

Bedrock model inference · Input tokens per second

Planning estimate with editable assumptions. These authored unit rates and capacity assumptions require provider-price verification and representative benchmarks. They do not constitute verified list-price quotes or evidence that an adapter is available. Estimated monthly service charges from native source usage; no calculator input is required. Adapter hosting and Tensor9 fees are excluded. Source: Explicit source planning region; target: Explicit target planning region; currency: USD. Exact sampled model outputs in USD/month. Difference means target minus origin; a positive difference means the target costs more. Estimated allocation from planning assumptions; not benchmark calibrated. Only discrete samples are shown. Unpriced means no target quote or cost difference is available within the sizing policy. Estimated allocation from planning assumptions; not benchmark calibrated. The sizing policy grows compute with translated work and peak headroom, memory with compute and working set, and disk with resident working state and reserve. Monthly usage is distinct from resident data; each workload’s assumptions define the translation. HA changes pricing, not this policy’s throughput estimate. Unpriced workloads exceed the policy’s configuration range; no silent vertical cap or automatic sharding is assumed.

• Authored operation throughput, peak and working-set assumptions are not benchmark-calibrated.
• Stored GiB already includes the origin family’s physical footprint assumptions; no second storage amplification is applied.
• The generic operations/vCPU coefficient supplies a provisional compute requirement alongside explicit resource-hour minima.
• Copies and allocation fractions change cost only; they do not increase modeled primary capacity.

Curve assumptions

• Only this native meter varies; all other source usage and translation assumptions retain the displayed defaults. Editable authored planning guesses, not verified provider tariffs, benchmark measurements or a commercial quote. Other native meters retain their explicitly displayed default quantities.
• Planning estimate · editable authored rates and sizing assumptions dated 2026-10-18; not verified provider prices. Explicit source planning region → Explicit target planning region, USD/month.
• Source prices are reference charges, not an invoice. Target lines cover selected service usage/configuration only; adapter hosting and Tensor9 fees are excluded.
• Explicit tariff samples are not performance measurements or capacity qualification. No interpolation or break-even guarantee is implied.
• Variant assumptions show the first axis sample; any axis-dependent configuration is described by this curve’s workload note.
• Editable authored planning guesses, not verified provider tariffs, benchmark measurements or a commercial quote.
• Default-zero rates are explicit assumptions, not evidence that the deployed service or resource is free.
• Provisioned-unit minimums use an editable approximate allocation floor. Modeled target service cost is max(usage/allocation, minimum), with billable network, durable staging and dependent sinks added separately; actual RU/TU sizing, scaling increments and throughput remain unqualified.
• Durable staging is priced once: provisioned targets include adapter state in their selected allocation; native targets add a separate staging allocation when required. Adapter hosting is a separate allocation and must exclude resources already priced as staging, workers or target capacity.
• A declared adapter mapping and cost model do not establish implementation availability or service equivalence.
• This is a declared directed mapping; a planning estimate does not establish deployment or request-serving support.
• Native/deployment comparison scope: This mapping provisions an Azure content-filter policy. A policy is not a Bedrock inference endpoint; inference adapters have their own operation-specific terms.
• All default unit prices and capacity coefficients are editable authored planning guesses, not measured capacity or a provider quote.
• Source and target tariffs name no asserted current model SKU. Select model-specific rates before using the estimate.
• Input and output meters and token expansion remain independent. A cheaper model is not automatically equivalent in capability or quality.
• All target rates are editable authored planning guesses, not verified current list prices, customer discounts or benchmark evidence.
• Named provisioned target: selected CPU, RAM and physical disk allocation grow with workload. No additional per-database-operation price is assumed. Managed service premiums and dedicated accelerator/model-fit requirements need explicit qualification.
• Authored operation throughput, peak and working-set assumptions are not benchmark-calibrated.
• Stored GiB already includes the origin family’s physical footprint assumptions; no second storage amplification is applied.
• The generic operations/vCPU coefficient supplies a provisional compute requirement alongside explicit resource-hour minima.
• Copies and allocation fractions change cost only; they do not increase modeled primary capacity.

Cost scope: Modeled target native service and explicitly modeled state allocation; hosting and Tensor9 fees only when supplied. Excluded costs and workload features:

• Prompt caching, batch discounts, context tiers, grounding, tools, agents, embeddings, search, guardrails and dedicated inference hardware.
• Taxes, discounts, credits and free-tier allowances unless explicitly reflected in edited rates.
• Unmodeled dependent services, task execution and operations outside the selected workload family.

Planning assumptions authored: 2026-10-18. Model: plan-16611989e2e34abf6767c0c4525fdf4ae72b8f64 / 2026-10-18.planning.1. Curve: workload-1.

​

Bedrock model inference · Output tokens per second

Planning estimate with editable assumptions. These authored unit rates and capacity assumptions require provider-price verification and representative benchmarks. They do not constitute verified list-price quotes or evidence that an adapter is available. Estimated monthly service charges from native source usage; no calculator input is required. Adapter hosting and Tensor9 fees are excluded. Source: Explicit source planning region; target: Explicit target planning region; currency: USD. Exact sampled model outputs in USD/month. Difference means target minus origin; a positive difference means the target costs more. Estimated allocation from planning assumptions; not benchmark calibrated. Only discrete samples are shown. Unpriced means no target quote or cost difference is available within the sizing policy. Estimated allocation from planning assumptions; not benchmark calibrated. The sizing policy grows compute with translated work and peak headroom, memory with compute and working set, and disk with resident working state and reserve. Monthly usage is distinct from resident data; each workload’s assumptions define the translation. HA changes pricing, not this policy’s throughput estimate. Unpriced workloads exceed the policy’s configuration range; no silent vertical cap or automatic sharding is assumed.

• Authored operation throughput, peak and working-set assumptions are not benchmark-calibrated.
• Stored GiB already includes the origin family’s physical footprint assumptions; no second storage amplification is applied.
• The generic operations/vCPU coefficient supplies a provisional compute requirement alongside explicit resource-hour minima.
• Copies and allocation fractions change cost only; they do not increase modeled primary capacity.

Curve assumptions

• Only this native meter varies; all other source usage and translation assumptions retain the displayed defaults. Editable authored planning guesses, not verified provider tariffs, benchmark measurements or a commercial quote. Other native meters retain their explicitly displayed default quantities.
• Planning estimate · editable authored rates and sizing assumptions dated 2026-10-18; not verified provider prices. Explicit source planning region → Explicit target planning region, USD/month.
• Source prices are reference charges, not an invoice. Target lines cover selected service usage/configuration only; adapter hosting and Tensor9 fees are excluded.
• Explicit tariff samples are not performance measurements or capacity qualification. No interpolation or break-even guarantee is implied.
• Variant assumptions show the first axis sample; any axis-dependent configuration is described by this curve’s workload note.
• Editable authored planning guesses, not verified provider tariffs, benchmark measurements or a commercial quote.
• Default-zero rates are explicit assumptions, not evidence that the deployed service or resource is free.
• Provisioned-unit minimums use an editable approximate allocation floor. Modeled target service cost is max(usage/allocation, minimum), with billable network, durable staging and dependent sinks added separately; actual RU/TU sizing, scaling increments and throughput remain unqualified.
• Durable staging is priced once: provisioned targets include adapter state in their selected allocation; native targets add a separate staging allocation when required. Adapter hosting is a separate allocation and must exclude resources already priced as staging, workers or target capacity.
• A declared adapter mapping and cost model do not establish implementation availability or service equivalence.
• This is a declared directed mapping; a planning estimate does not establish deployment or request-serving support.
• Native/deployment comparison scope: This mapping provisions an Azure content-filter policy. A policy is not a Bedrock inference endpoint; inference adapters have their own operation-specific terms.
• All default unit prices and capacity coefficients are editable authored planning guesses, not measured capacity or a provider quote.
• Source and target tariffs name no asserted current model SKU. Select model-specific rates before using the estimate.
• Input and output meters and token expansion remain independent. A cheaper model is not automatically equivalent in capability or quality.
• All target rates are editable authored planning guesses, not verified current list prices, customer discounts or benchmark evidence.
• Named provisioned target: selected CPU, RAM and physical disk allocation grow with workload. No additional per-database-operation price is assumed. Managed service premiums and dedicated accelerator/model-fit requirements need explicit qualification.
• Authored operation throughput, peak and working-set assumptions are not benchmark-calibrated.
• Stored GiB already includes the origin family’s physical footprint assumptions; no second storage amplification is applied.
• The generic operations/vCPU coefficient supplies a provisional compute requirement alongside explicit resource-hour minima.
• Copies and allocation fractions change cost only; they do not increase modeled primary capacity.

Cost scope: Modeled target native service and explicitly modeled state allocation; hosting and Tensor9 fees only when supplied. Excluded costs and workload features:

• Prompt caching, batch discounts, context tiers, grounding, tools, agents, embeddings, search, guardrails and dedicated inference hardware.
• Taxes, discounts, credits and free-tier allowances unless explicitly reflected in edited rates.
• Unmodeled dependent services, task execution and operations outside the selected workload family.

Planning assumptions authored: 2026-10-18. Model: plan-16611989e2e34abf6767c0c4525fdf4ae72b8f64 / 2026-10-18.planning.1. Curve: workload-2.

​

Bedrock model inference → OCI Generative AI

Origin API: aws::1.0.0::bedrock. Target backend: oci::1.0.0::genai. Planning estimate with editable assumptions. Unit rates, workload amplification and capacity assumptions are educated guesses awaiting verification. The displayed amounts are planning estimates, not verified provider list-price quotes or benchmark-qualified capacity. Region names identify the authored scenario assumptions.

​

Bedrock model inference · Input tokens per second

Planning estimate with editable assumptions. These authored unit rates and capacity assumptions require provider-price verification and representative benchmarks. They do not constitute verified list-price quotes or evidence that an adapter is available. Estimated monthly service charges from native source usage; no calculator input is required. Adapter hosting and Tensor9 fees are excluded. Source: Explicit source planning region; target: Explicit target planning region; currency: USD. Exact sampled model outputs in USD/month. Difference means target minus origin; a positive difference means the target costs more. Curve assumptions

• Only this native meter varies; all other source usage and translation assumptions retain the displayed defaults. Editable authored planning guesses, not verified provider tariffs, benchmark measurements or a commercial quote. Other native meters retain their explicitly displayed default quantities.
• Planning estimate · editable authored rates and sizing assumptions dated 2026-10-18; not verified provider prices. Explicit source planning region → Explicit target planning region, USD/month.
• Source prices are reference charges, not an invoice. Target lines cover selected service usage/configuration only; adapter hosting and Tensor9 fees are excluded.
• Explicit tariff samples are not performance measurements or capacity qualification. No interpolation or break-even guarantee is implied.
• Variant assumptions show the first axis sample; any axis-dependent configuration is described by this curve’s workload note.
• Editable authored planning guesses, not verified provider tariffs, benchmark measurements or a commercial quote.
• Default-zero rates are explicit assumptions, not evidence that the deployed service or resource is free.
• Provisioned-unit minimums use an editable approximate allocation floor. Modeled target service cost is max(usage/allocation, minimum), with billable network, durable staging and dependent sinks added separately; actual RU/TU sizing, scaling increments and throughput remain unqualified.
• Durable staging is priced once: provisioned targets include adapter state in their selected allocation; native targets add a separate staging allocation when required. Adapter hosting is a separate allocation and must exclude resources already priced as staging, workers or target capacity.
• A declared adapter mapping and cost model do not establish implementation availability or service equivalence.
• This is a declared directed mapping; a planning estimate does not establish deployment or request-serving support.
• All default unit prices and capacity coefficients are editable authored planning guesses, not measured capacity or a provider quote.
• Source and target tariffs name no asserted current model SKU. Select model-specific rates before using the estimate.
• Input and output meters and token expansion remain independent. A cheaper model is not automatically equivalent in capability or quality.
• All target rates are editable authored planning guesses, not verified current list prices, customer discounts or benchmark evidence.
• Input and output token tariffs remain distinct. These illustrative rates name no selected model SKU and establish no equivalent output quality or tokenizer.

Cost scope: Modeled target native service and explicitly modeled state allocation; hosting and Tensor9 fees only when supplied. Excluded costs and workload features:

• Prompt caching, batch discounts, context tiers, grounding, tools, agents, embeddings, search, guardrails and dedicated inference hardware.
• Taxes, discounts, credits and free-tier allowances unless explicitly reflected in edited rates.
• Unmodeled dependent services, task execution and operations outside the selected workload family.

Planning assumptions authored: 2026-10-18. Model: plan-867e301a8e1fa800d4506aa97b8132fa27fdb26a / 2026-10-18.planning.1. Curve: workload-1.

​

Bedrock model inference · Output tokens per second

Planning estimate with editable assumptions. These authored unit rates and capacity assumptions require provider-price verification and representative benchmarks. They do not constitute verified list-price quotes or evidence that an adapter is available. Estimated monthly service charges from native source usage; no calculator input is required. Adapter hosting and Tensor9 fees are excluded. Source: Explicit source planning region; target: Explicit target planning region; currency: USD. Exact sampled model outputs in USD/month. Difference means target minus origin; a positive difference means the target costs more. Curve assumptions

• Only this native meter varies; all other source usage and translation assumptions retain the displayed defaults. Editable authored planning guesses, not verified provider tariffs, benchmark measurements or a commercial quote. Other native meters retain their explicitly displayed default quantities.
• Planning estimate · editable authored rates and sizing assumptions dated 2026-10-18; not verified provider prices. Explicit source planning region → Explicit target planning region, USD/month.
• Source prices are reference charges, not an invoice. Target lines cover selected service usage/configuration only; adapter hosting and Tensor9 fees are excluded.
• Explicit tariff samples are not performance measurements or capacity qualification. No interpolation or break-even guarantee is implied.
• Variant assumptions show the first axis sample; any axis-dependent configuration is described by this curve’s workload note.
• Editable authored planning guesses, not verified provider tariffs, benchmark measurements or a commercial quote.
• Default-zero rates are explicit assumptions, not evidence that the deployed service or resource is free.
• Provisioned-unit minimums use an editable approximate allocation floor. Modeled target service cost is max(usage/allocation, minimum), with billable network, durable staging and dependent sinks added separately; actual RU/TU sizing, scaling increments and throughput remain unqualified.
• Durable staging is priced once: provisioned targets include adapter state in their selected allocation; native targets add a separate staging allocation when required. Adapter hosting is a separate allocation and must exclude resources already priced as staging, workers or target capacity.
• A declared adapter mapping and cost model do not establish implementation availability or service equivalence.
• This is a declared directed mapping; a planning estimate does not establish deployment or request-serving support.
• All default unit prices and capacity coefficients are editable authored planning guesses, not measured capacity or a provider quote.
• Source and target tariffs name no asserted current model SKU. Select model-specific rates before using the estimate.
• Input and output meters and token expansion remain independent. A cheaper model is not automatically equivalent in capability or quality.
• All target rates are editable authored planning guesses, not verified current list prices, customer discounts or benchmark evidence.
• Input and output token tariffs remain distinct. These illustrative rates name no selected model SKU and establish no equivalent output quality or tokenizer.

Cost scope: Modeled target native service and explicitly modeled state allocation; hosting and Tensor9 fees only when supplied. Excluded costs and workload features:

• Prompt caching, batch discounts, context tiers, grounding, tools, agents, embeddings, search, guardrails and dedicated inference hardware.
• Taxes, discounts, credits and free-tier allowances unless explicitly reflected in edited rates.
• Unmodeled dependent services, task execution and operations outside the selected workload family.

Planning assumptions authored: 2026-10-18. Model: plan-867e301a8e1fa800d4506aa97b8132fa27fdb26a / 2026-10-18.planning.1. Curve: workload-2.

​

Bedrock model inference → OpenAI Chat Completions

Origin API: aws::1.0.0::bedrock. Target backend: openai::1.0.0::chat. Planning estimate with editable assumptions. Unit rates, workload amplification and capacity assumptions are educated guesses awaiting verification. The displayed amounts are planning estimates, not verified provider list-price quotes or benchmark-qualified capacity. Region names identify the authored scenario assumptions.

​

Bedrock model inference · Input tokens per second

Planning estimate with editable assumptions. These authored unit rates and capacity assumptions require provider-price verification and representative benchmarks. They do not constitute verified list-price quotes or evidence that an adapter is available. Estimated monthly service charges from native source usage; no calculator input is required. Adapter hosting and Tensor9 fees are excluded. Source: Explicit source planning region; target: Explicit target planning region; currency: USD. Exact sampled model outputs in USD/month. Difference means target minus origin; a positive difference means the target costs more. Curve assumptions

• Only this native meter varies; all other source usage and translation assumptions retain the displayed defaults. Editable authored planning guesses, not verified provider tariffs, benchmark measurements or a commercial quote. Other native meters retain their explicitly displayed default quantities.
• Planning estimate · editable authored rates and sizing assumptions dated 2026-10-18; not verified provider prices. Explicit source planning region → Explicit target planning region, USD/month.
• Source prices are reference charges, not an invoice. Target lines cover selected service usage/configuration only; adapter hosting and Tensor9 fees are excluded.
• Explicit tariff samples are not performance measurements or capacity qualification. No interpolation or break-even guarantee is implied.
• Variant assumptions show the first axis sample; any axis-dependent configuration is described by this curve’s workload note.
• Editable authored planning guesses, not verified provider tariffs, benchmark measurements or a commercial quote.
• Default-zero rates are explicit assumptions, not evidence that the deployed service or resource is free.
• Provisioned-unit minimums use an editable approximate allocation floor. Modeled target service cost is max(usage/allocation, minimum), with billable network, durable staging and dependent sinks added separately; actual RU/TU sizing, scaling increments and throughput remain unqualified.
• Durable staging is priced once: provisioned targets include adapter state in their selected allocation; native targets add a separate staging allocation when required. Adapter hosting is a separate allocation and must exclude resources already priced as staging, workers or target capacity.
• A declared adapter mapping and cost model do not establish implementation availability or service equivalence.
• This is a declared directed mapping; a planning estimate does not establish deployment or request-serving support.
• All default unit prices and capacity coefficients are editable authored planning guesses, not measured capacity or a provider quote.
• Source and target tariffs name no asserted current model SKU. Select model-specific rates before using the estimate.
• Input and output meters and token expansion remain independent. A cheaper model is not automatically equivalent in capability or quality.
• All target rates are editable authored planning guesses, not verified current list prices, customer discounts or benchmark evidence.
• Input and output token tariffs remain distinct. These illustrative rates name no selected model SKU and establish no equivalent output quality or tokenizer.

Cost scope: Modeled target native service and explicitly modeled state allocation; hosting and Tensor9 fees only when supplied. Excluded costs and workload features:

• Prompt caching, batch discounts, context tiers, grounding, tools, agents, embeddings, search, guardrails and dedicated inference hardware.
• Taxes, discounts, credits and free-tier allowances unless explicitly reflected in edited rates.
• Unmodeled dependent services, task execution and operations outside the selected workload family.

Planning assumptions authored: 2026-10-18. Model: plan-24a146500f73787fcd1f2436716bcced0f4263b3 / 2026-10-18.planning.1. Curve: workload-1.

​

Bedrock model inference · Output tokens per second

Planning estimate with editable assumptions. These authored unit rates and capacity assumptions require provider-price verification and representative benchmarks. They do not constitute verified list-price quotes or evidence that an adapter is available. Estimated monthly service charges from native source usage; no calculator input is required. Adapter hosting and Tensor9 fees are excluded. Source: Explicit source planning region; target: Explicit target planning region; currency: USD. Exact sampled model outputs in USD/month. Difference means target minus origin; a positive difference means the target costs more. Curve assumptions

• Only this native meter varies; all other source usage and translation assumptions retain the displayed defaults. Editable authored planning guesses, not verified provider tariffs, benchmark measurements or a commercial quote. Other native meters retain their explicitly displayed default quantities.
• Planning estimate · editable authored rates and sizing assumptions dated 2026-10-18; not verified provider prices. Explicit source planning region → Explicit target planning region, USD/month.
• Source prices are reference charges, not an invoice. Target lines cover selected service usage/configuration only; adapter hosting and Tensor9 fees are excluded.
• Explicit tariff samples are not performance measurements or capacity qualification. No interpolation or break-even guarantee is implied.
• Variant assumptions show the first axis sample; any axis-dependent configuration is described by this curve’s workload note.
• Editable authored planning guesses, not verified provider tariffs, benchmark measurements or a commercial quote.
• Default-zero rates are explicit assumptions, not evidence that the deployed service or resource is free.
• Provisioned-unit minimums use an editable approximate allocation floor. Modeled target service cost is max(usage/allocation, minimum), with billable network, durable staging and dependent sinks added separately; actual RU/TU sizing, scaling increments and throughput remain unqualified.
• Durable staging is priced once: provisioned targets include adapter state in their selected allocation; native targets add a separate staging allocation when required. Adapter hosting is a separate allocation and must exclude resources already priced as staging, workers or target capacity.
• A declared adapter mapping and cost model do not establish implementation availability or service equivalence.
• This is a declared directed mapping; a planning estimate does not establish deployment or request-serving support.
• All default unit prices and capacity coefficients are editable authored planning guesses, not measured capacity or a provider quote.
• Source and target tariffs name no asserted current model SKU. Select model-specific rates before using the estimate.
• Input and output meters and token expansion remain independent. A cheaper model is not automatically equivalent in capability or quality.
• All target rates are editable authored planning guesses, not verified current list prices, customer discounts or benchmark evidence.
• Input and output token tariffs remain distinct. These illustrative rates name no selected model SKU and establish no equivalent output quality or tokenizer.

Cost scope: Modeled target native service and explicitly modeled state allocation; hosting and Tensor9 fees only when supplied. Excluded costs and workload features:

• Prompt caching, batch discounts, context tiers, grounding, tools, agents, embeddings, search, guardrails and dedicated inference hardware.
• Taxes, discounts, credits and free-tier allowances unless explicitly reflected in edited rates.
• Unmodeled dependent services, task execution and operations outside the selected workload family.

Planning assumptions authored: 2026-10-18. Model: plan-24a146500f73787fcd1f2436716bcced0f4263b3 / 2026-10-18.planning.1. Curve: workload-2.

​

Bedrock model inference → Scaleway Managed Inference

Origin API: aws::1.0.0::bedrock. Target backend: scaleway::1.0.0::inference. Planning estimate with editable assumptions. Unit rates, workload amplification and capacity assumptions are educated guesses awaiting verification. The displayed amounts are planning estimates, not verified provider list-price quotes or benchmark-qualified capacity. Region names identify the authored scenario assumptions.

​

Bedrock model inference · Input tokens per second

Planning estimate with editable assumptions. These authored unit rates and capacity assumptions require provider-price verification and representative benchmarks. They do not constitute verified list-price quotes or evidence that an adapter is available. Estimated monthly service charges from native source usage; no calculator input is required. Adapter hosting and Tensor9 fees are excluded. Source: Explicit source planning region; target: Explicit target planning region; currency: USD. Exact sampled model outputs in USD/month. Difference means target minus origin; a positive difference means the target costs more. Estimated allocation from planning assumptions; not benchmark calibrated. Only discrete samples are shown. Unpriced means no target quote or cost difference is available within the sizing policy. Estimated allocation from planning assumptions; not benchmark calibrated. The sizing policy grows compute with translated work and peak headroom, memory with compute and working set, and disk with resident working state and reserve. Monthly usage is distinct from resident data; each workload’s assumptions define the translation. HA changes pricing, not this policy’s throughput estimate. Unpriced workloads exceed the policy’s configuration range; no silent vertical cap or automatic sharding is assumed.

• Authored operation throughput, peak and working-set assumptions are not benchmark-calibrated.
• Stored GiB already includes the origin family’s physical footprint assumptions; no second storage amplification is applied.
• The generic operations/vCPU coefficient supplies a provisional compute requirement alongside explicit resource-hour minima.
• Copies and allocation fractions change cost only; they do not increase modeled primary capacity.

Curve assumptions

• Only this native meter varies; all other source usage and translation assumptions retain the displayed defaults. Editable authored planning guesses, not verified provider tariffs, benchmark measurements or a commercial quote. Other native meters retain their explicitly displayed default quantities.
• Planning estimate · editable authored rates and sizing assumptions dated 2026-10-18; not verified provider prices. Explicit source planning region → Explicit target planning region, USD/month.
• Source prices are reference charges, not an invoice. Target lines cover selected service usage/configuration only; adapter hosting and Tensor9 fees are excluded.
• Explicit tariff samples are not performance measurements or capacity qualification. No interpolation or break-even guarantee is implied.
• Variant assumptions show the first axis sample; any axis-dependent configuration is described by this curve’s workload note.
• Editable authored planning guesses, not verified provider tariffs, benchmark measurements or a commercial quote.
• Default-zero rates are explicit assumptions, not evidence that the deployed service or resource is free.
• Provisioned-unit minimums use an editable approximate allocation floor. Modeled target service cost is max(usage/allocation, minimum), with billable network, durable staging and dependent sinks added separately; actual RU/TU sizing, scaling increments and throughput remain unqualified.
• Durable staging is priced once: provisioned targets include adapter state in their selected allocation; native targets add a separate staging allocation when required. Adapter hosting is a separate allocation and must exclude resources already priced as staging, workers or target capacity.
• A declared adapter mapping and cost model do not establish implementation availability or service equivalence.
• This is a declared directed mapping; a planning estimate does not establish deployment or request-serving support.
• All default unit prices and capacity coefficients are editable authored planning guesses, not measured capacity or a provider quote.
• Source and target tariffs name no asserted current model SKU. Select model-specific rates before using the estimate.
• Input and output meters and token expansion remain independent. A cheaper model is not automatically equivalent in capability or quality.
• All target rates are editable authored planning guesses, not verified current list prices, customer discounts or benchmark evidence.
• Named provisioned target: selected CPU, RAM and physical disk allocation grow with workload. No additional per-database-operation price is assumed. Managed service premiums and dedicated accelerator/model-fit requirements need explicit qualification.
• Authored operation throughput, peak and working-set assumptions are not benchmark-calibrated.
• Stored GiB already includes the origin family’s physical footprint assumptions; no second storage amplification is applied.
• The generic operations/vCPU coefficient supplies a provisional compute requirement alongside explicit resource-hour minima.
• Copies and allocation fractions change cost only; they do not increase modeled primary capacity.

Cost scope: Modeled target native service and explicitly modeled state allocation; hosting and Tensor9 fees only when supplied. Excluded costs and workload features:

• Prompt caching, batch discounts, context tiers, grounding, tools, agents, embeddings, search, guardrails and dedicated inference hardware.
• Taxes, discounts, credits and free-tier allowances unless explicitly reflected in edited rates.
• Unmodeled dependent services, task execution and operations outside the selected workload family.

Planning assumptions authored: 2026-10-18. Model: plan-a6f9604e9c2919f36a8bcff1239ddada7e8d8663 / 2026-10-18.planning.1. Curve: workload-1.

​

Bedrock model inference · Output tokens per second

Planning estimate with editable assumptions. These authored unit rates and capacity assumptions require provider-price verification and representative benchmarks. They do not constitute verified list-price quotes or evidence that an adapter is available. Estimated monthly service charges from native source usage; no calculator input is required. Adapter hosting and Tensor9 fees are excluded. Source: Explicit source planning region; target: Explicit target planning region; currency: USD. Exact sampled model outputs in USD/month. Difference means target minus origin; a positive difference means the target costs more. Estimated allocation from planning assumptions; not benchmark calibrated. Only discrete samples are shown. Unpriced means no target quote or cost difference is available within the sizing policy. Estimated allocation from planning assumptions; not benchmark calibrated. The sizing policy grows compute with translated work and peak headroom, memory with compute and working set, and disk with resident working state and reserve. Monthly usage is distinct from resident data; each workload’s assumptions define the translation. HA changes pricing, not this policy’s throughput estimate. Unpriced workloads exceed the policy’s configuration range; no silent vertical cap or automatic sharding is assumed.

• Authored operation throughput, peak and working-set assumptions are not benchmark-calibrated.
• Stored GiB already includes the origin family’s physical footprint assumptions; no second storage amplification is applied.
• The generic operations/vCPU coefficient supplies a provisional compute requirement alongside explicit resource-hour minima.
• Copies and allocation fractions change cost only; they do not increase modeled primary capacity.

Curve assumptions

• Only this native meter varies; all other source usage and translation assumptions retain the displayed defaults. Editable authored planning guesses, not verified provider tariffs, benchmark measurements or a commercial quote. Other native meters retain their explicitly displayed default quantities.
• Planning estimate · editable authored rates and sizing assumptions dated 2026-10-18; not verified provider prices. Explicit source planning region → Explicit target planning region, USD/month.
• Source prices are reference charges, not an invoice. Target lines cover selected service usage/configuration only; adapter hosting and Tensor9 fees are excluded.
• Explicit tariff samples are not performance measurements or capacity qualification. No interpolation or break-even guarantee is implied.
• Variant assumptions show the first axis sample; any axis-dependent configuration is described by this curve’s workload note.
• Editable authored planning guesses, not verified provider tariffs, benchmark measurements or a commercial quote.
• Default-zero rates are explicit assumptions, not evidence that the deployed service or resource is free.
• Provisioned-unit minimums use an editable approximate allocation floor. Modeled target service cost is max(usage/allocation, minimum), with billable network, durable staging and dependent sinks added separately; actual RU/TU sizing, scaling increments and throughput remain unqualified.
• Durable staging is priced once: provisioned targets include adapter state in their selected allocation; native targets add a separate staging allocation when required. Adapter hosting is a separate allocation and must exclude resources already priced as staging, workers or target capacity.
• A declared adapter mapping and cost model do not establish implementation availability or service equivalence.
• This is a declared directed mapping; a planning estimate does not establish deployment or request-serving support.
• All default unit prices and capacity coefficients are editable authored planning guesses, not measured capacity or a provider quote.
• Source and target tariffs name no asserted current model SKU. Select model-specific rates before using the estimate.
• Input and output meters and token expansion remain independent. A cheaper model is not automatically equivalent in capability or quality.
• All target rates are editable authored planning guesses, not verified current list prices, customer discounts or benchmark evidence.
• Named provisioned target: selected CPU, RAM and physical disk allocation grow with workload. No additional per-database-operation price is assumed. Managed service premiums and dedicated accelerator/model-fit requirements need explicit qualification.
• Authored operation throughput, peak and working-set assumptions are not benchmark-calibrated.
• Stored GiB already includes the origin family’s physical footprint assumptions; no second storage amplification is applied.
• The generic operations/vCPU coefficient supplies a provisional compute requirement alongside explicit resource-hour minima.
• Copies and allocation fractions change cost only; they do not increase modeled primary capacity.

Cost scope: Modeled target native service and explicitly modeled state allocation; hosting and Tensor9 fees only when supplied. Excluded costs and workload features:

• Prompt caching, batch discounts, context tiers, grounding, tools, agents, embeddings, search, guardrails and dedicated inference hardware.
• Taxes, discounts, credits and free-tier allowances unless explicitly reflected in edited rates.
• Unmodeled dependent services, task execution and operations outside the selected workload family.

Planning assumptions authored: 2026-10-18. Model: plan-a6f9604e9c2919f36a8bcff1239ddada7e8d8663 / 2026-10-18.planning.1. Curve: workload-2.

​

Bedrock model inference → Vertex AI - Claude

Origin API: aws::1.0.0::bedrock. Target backend: google::1.0.0::vertex::claude. Planning estimate with editable assumptions. Unit rates, workload amplification and capacity assumptions are educated guesses awaiting verification. The displayed amounts are planning estimates, not verified provider list-price quotes or benchmark-qualified capacity. Region names identify the authored scenario assumptions.

​

Bedrock model inference · Input tokens per second

Planning estimate with editable assumptions. These authored unit rates and capacity assumptions require provider-price verification and representative benchmarks. They do not constitute verified list-price quotes or evidence that an adapter is available. Estimated monthly service charges from native source usage; no calculator input is required. Adapter hosting and Tensor9 fees are excluded. Source: Explicit source planning region; target: Explicit target planning region; currency: USD. Exact sampled model outputs in USD/month. Difference means target minus origin; a positive difference means the target costs more. Curve assumptions

• Only this native meter varies; all other source usage and translation assumptions retain the displayed defaults. Editable authored planning guesses, not verified provider tariffs, benchmark measurements or a commercial quote. Other native meters retain their explicitly displayed default quantities.
• Planning estimate · editable authored rates and sizing assumptions dated 2026-10-18; not verified provider prices. Explicit source planning region → Explicit target planning region, USD/month.
• Source prices are reference charges, not an invoice. Target lines cover selected service usage/configuration only; adapter hosting and Tensor9 fees are excluded.
• Explicit tariff samples are not performance measurements or capacity qualification. No interpolation or break-even guarantee is implied.
• Variant assumptions show the first axis sample; any axis-dependent configuration is described by this curve’s workload note.
• Editable authored planning guesses, not verified provider tariffs, benchmark measurements or a commercial quote.
• Default-zero rates are explicit assumptions, not evidence that the deployed service or resource is free.
• Provisioned-unit minimums use an editable approximate allocation floor. Modeled target service cost is max(usage/allocation, minimum), with billable network, durable staging and dependent sinks added separately; actual RU/TU sizing, scaling increments and throughput remain unqualified.
• Durable staging is priced once: provisioned targets include adapter state in their selected allocation; native targets add a separate staging allocation when required. Adapter hosting is a separate allocation and must exclude resources already priced as staging, workers or target capacity.
• A declared adapter mapping and cost model do not establish implementation availability or service equivalence.
• This is a declared directed mapping; a planning estimate does not establish deployment or request-serving support.
• All default unit prices and capacity coefficients are editable authored planning guesses, not measured capacity or a provider quote.
• Source and target tariffs name no asserted current model SKU. Select model-specific rates before using the estimate.
• Input and output meters and token expansion remain independent. A cheaper model is not automatically equivalent in capability or quality.
• All target rates are editable authored planning guesses, not verified current list prices, customer discounts or benchmark evidence.
• Input and output token tariffs remain distinct. These illustrative rates name no selected model SKU and establish no equivalent output quality or tokenizer.

Cost scope: Modeled target native service and explicitly modeled state allocation; hosting and Tensor9 fees only when supplied. Excluded costs and workload features:

• Prompt caching, batch discounts, context tiers, grounding, tools, agents, embeddings, search, guardrails and dedicated inference hardware.
• Taxes, discounts, credits and free-tier allowances unless explicitly reflected in edited rates.
• Unmodeled dependent services, task execution and operations outside the selected workload family.

Planning assumptions authored: 2026-10-18. Model: plan-48c312b989270b8c0eaf604ff9da8bb4641b8a7b / 2026-10-18.planning.1. Curve: workload-1.

​

Bedrock model inference · Output tokens per second

Planning estimate with editable assumptions. These authored unit rates and capacity assumptions require provider-price verification and representative benchmarks. They do not constitute verified list-price quotes or evidence that an adapter is available. Estimated monthly service charges from native source usage; no calculator input is required. Adapter hosting and Tensor9 fees are excluded. Source: Explicit source planning region; target: Explicit target planning region; currency: USD. Exact sampled model outputs in USD/month. Difference means target minus origin; a positive difference means the target costs more. Curve assumptions

• Only this native meter varies; all other source usage and translation assumptions retain the displayed defaults. Editable authored planning guesses, not verified provider tariffs, benchmark measurements or a commercial quote. Other native meters retain their explicitly displayed default quantities.
• Planning estimate · editable authored rates and sizing assumptions dated 2026-10-18; not verified provider prices. Explicit source planning region → Explicit target planning region, USD/month.
• Source prices are reference charges, not an invoice. Target lines cover selected service usage/configuration only; adapter hosting and Tensor9 fees are excluded.
• Explicit tariff samples are not performance measurements or capacity qualification. No interpolation or break-even guarantee is implied.
• Variant assumptions show the first axis sample; any axis-dependent configuration is described by this curve’s workload note.
• Editable authored planning guesses, not verified provider tariffs, benchmark measurements or a commercial quote.
• Default-zero rates are explicit assumptions, not evidence that the deployed service or resource is free.
• Provisioned-unit minimums use an editable approximate allocation floor. Modeled target service cost is max(usage/allocation, minimum), with billable network, durable staging and dependent sinks added separately; actual RU/TU sizing, scaling increments and throughput remain unqualified.
• Durable staging is priced once: provisioned targets include adapter state in their selected allocation; native targets add a separate staging allocation when required. Adapter hosting is a separate allocation and must exclude resources already priced as staging, workers or target capacity.
• A declared adapter mapping and cost model do not establish implementation availability or service equivalence.
• This is a declared directed mapping; a planning estimate does not establish deployment or request-serving support.
• All default unit prices and capacity coefficients are editable authored planning guesses, not measured capacity or a provider quote.
• Source and target tariffs name no asserted current model SKU. Select model-specific rates before using the estimate.
• Input and output meters and token expansion remain independent. A cheaper model is not automatically equivalent in capability or quality.
• All target rates are editable authored planning guesses, not verified current list prices, customer discounts or benchmark evidence.
• Input and output token tariffs remain distinct. These illustrative rates name no selected model SKU and establish no equivalent output quality or tokenizer.

Cost scope: Modeled target native service and explicitly modeled state allocation; hosting and Tensor9 fees only when supplied. Excluded costs and workload features:

• Prompt caching, batch discounts, context tiers, grounding, tools, agents, embeddings, search, guardrails and dedicated inference hardware.
• Taxes, discounts, credits and free-tier allowances unless explicitly reflected in edited rates.
• Unmodeled dependent services, task execution and operations outside the selected workload family.

Planning assumptions authored: 2026-10-18. Model: plan-48c312b989270b8c0eaf604ff9da8bb4641b8a7b / 2026-10-18.planning.1. Curve: workload-2.

​

Bedrock model inference → Vertex AI - Gemini

Origin API: aws::1.0.0::bedrock. Target backend: google::1.0.0::vertex::gemini. Planning estimate with editable assumptions. Unit rates, workload amplification and capacity assumptions are educated guesses awaiting verification. The displayed amounts are planning estimates, not verified provider list-price quotes or benchmark-qualified capacity. Region names identify the authored scenario assumptions.

​

Bedrock model inference · Input tokens per second

Planning estimate with editable assumptions. These authored unit rates and capacity assumptions require provider-price verification and representative benchmarks. They do not constitute verified list-price quotes or evidence that an adapter is available. Estimated monthly service charges from native source usage; no calculator input is required. Adapter hosting and Tensor9 fees are excluded. Source: Explicit source planning region; target: Explicit target planning region; currency: USD. Exact sampled model outputs in USD/month. Difference means target minus origin; a positive difference means the target costs more. Curve assumptions

• Only this native meter varies; all other source usage and translation assumptions retain the displayed defaults. Editable authored planning guesses, not verified provider tariffs, benchmark measurements or a commercial quote. Other native meters retain their explicitly displayed default quantities.
• Planning estimate · editable authored rates and sizing assumptions dated 2026-10-18; not verified provider prices. Explicit source planning region → Explicit target planning region, USD/month.
• Source prices are reference charges, not an invoice. Target lines cover selected service usage/configuration only; adapter hosting and Tensor9 fees are excluded.
• Explicit tariff samples are not performance measurements or capacity qualification. No interpolation or break-even guarantee is implied.
• Variant assumptions show the first axis sample; any axis-dependent configuration is described by this curve’s workload note.
• Editable authored planning guesses, not verified provider tariffs, benchmark measurements or a commercial quote.
• Default-zero rates are explicit assumptions, not evidence that the deployed service or resource is free.
• Provisioned-unit minimums use an editable approximate allocation floor. Modeled target service cost is max(usage/allocation, minimum), with billable network, durable staging and dependent sinks added separately; actual RU/TU sizing, scaling increments and throughput remain unqualified.
• Durable staging is priced once: provisioned targets include adapter state in their selected allocation; native targets add a separate staging allocation when required. Adapter hosting is a separate allocation and must exclude resources already priced as staging, workers or target capacity.
• A declared adapter mapping and cost model do not establish implementation availability or service equivalence.
• This is a declared directed mapping; a planning estimate does not establish deployment or request-serving support.
• All default unit prices and capacity coefficients are editable authored planning guesses, not measured capacity or a provider quote.
• Source and target tariffs name no asserted current model SKU. Select model-specific rates before using the estimate.
• Input and output meters and token expansion remain independent. A cheaper model is not automatically equivalent in capability or quality.
• All target rates are editable authored planning guesses, not verified current list prices, customer discounts or benchmark evidence.
• Input and output token tariffs remain distinct. These illustrative rates name no selected model SKU and establish no equivalent output quality or tokenizer.

Cost scope: Modeled target native service and explicitly modeled state allocation; hosting and Tensor9 fees only when supplied. Excluded costs and workload features:

• Prompt caching, batch discounts, context tiers, grounding, tools, agents, embeddings, search, guardrails and dedicated inference hardware.
• Taxes, discounts, credits and free-tier allowances unless explicitly reflected in edited rates.
• Unmodeled dependent services, task execution and operations outside the selected workload family.

Planning assumptions authored: 2026-10-18. Model: plan-4c72ad085195d9377822f40afb60d644ed875746 / 2026-10-18.planning.1. Curve: workload-1.

​

Bedrock model inference · Output tokens per second

Planning estimate with editable assumptions. These authored unit rates and capacity assumptions require provider-price verification and representative benchmarks. They do not constitute verified list-price quotes or evidence that an adapter is available. Estimated monthly service charges from native source usage; no calculator input is required. Adapter hosting and Tensor9 fees are excluded. Source: Explicit source planning region; target: Explicit target planning region; currency: USD. Exact sampled model outputs in USD/month. Difference means target minus origin; a positive difference means the target costs more. Curve assumptions

• Only this native meter varies; all other source usage and translation assumptions retain the displayed defaults. Editable authored planning guesses, not verified provider tariffs, benchmark measurements or a commercial quote. Other native meters retain their explicitly displayed default quantities.
• Planning estimate · editable authored rates and sizing assumptions dated 2026-10-18; not verified provider prices. Explicit source planning region → Explicit target planning region, USD/month.
• Source prices are reference charges, not an invoice. Target lines cover selected service usage/configuration only; adapter hosting and Tensor9 fees are excluded.
• Explicit tariff samples are not performance measurements or capacity qualification. No interpolation or break-even guarantee is implied.
• Variant assumptions show the first axis sample; any axis-dependent configuration is described by this curve’s workload note.
• Editable authored planning guesses, not verified provider tariffs, benchmark measurements or a commercial quote.
• Default-zero rates are explicit assumptions, not evidence that the deployed service or resource is free.
• Provisioned-unit minimums use an editable approximate allocation floor. Modeled target service cost is max(usage/allocation, minimum), with billable network, durable staging and dependent sinks added separately; actual RU/TU sizing, scaling increments and throughput remain unqualified.
• Durable staging is priced once: provisioned targets include adapter state in their selected allocation; native targets add a separate staging allocation when required. Adapter hosting is a separate allocation and must exclude resources already priced as staging, workers or target capacity.
• A declared adapter mapping and cost model do not establish implementation availability or service equivalence.
• This is a declared directed mapping; a planning estimate does not establish deployment or request-serving support.
• All default unit prices and capacity coefficients are editable authored planning guesses, not measured capacity or a provider quote.
• Source and target tariffs name no asserted current model SKU. Select model-specific rates before using the estimate.
• Input and output meters and token expansion remain independent. A cheaper model is not automatically equivalent in capability or quality.
• All target rates are editable authored planning guesses, not verified current list prices, customer discounts or benchmark evidence.
• Input and output token tariffs remain distinct. These illustrative rates name no selected model SKU and establish no equivalent output quality or tokenizer.

Cost scope: Modeled target native service and explicitly modeled state allocation; hosting and Tensor9 fees only when supplied. Excluded costs and workload features:

• Prompt caching, batch discounts, context tiers, grounding, tools, agents, embeddings, search, guardrails and dedicated inference hardware.
• Taxes, discounts, credits and free-tier allowances unless explicitly reflected in edited rates.
• Unmodeled dependent services, task execution and operations outside the selected workload family.

Planning assumptions authored: 2026-10-18. Model: plan-4c72ad085195d9377822f40afb60d644ed875746 / 2026-10-18.planning.1. Curve: workload-2.

​

Bedrock model inference → Vertex AI - Llama

Origin API: aws::1.0.0::bedrock. Target backend: google::1.0.0::vertex::llama. Planning estimate with editable assumptions. Unit rates, workload amplification and capacity assumptions are educated guesses awaiting verification. The displayed amounts are planning estimates, not verified provider list-price quotes or benchmark-qualified capacity. Region names identify the authored scenario assumptions.

​

Bedrock model inference · Input tokens per second

Planning estimate with editable assumptions. These authored unit rates and capacity assumptions require provider-price verification and representative benchmarks. They do not constitute verified list-price quotes or evidence that an adapter is available. Estimated monthly service charges from native source usage; no calculator input is required. Adapter hosting and Tensor9 fees are excluded. Source: Explicit source planning region; target: Explicit target planning region; currency: USD. Exact sampled model outputs in USD/month. Difference means target minus origin; a positive difference means the target costs more. Curve assumptions

• Only this native meter varies; all other source usage and translation assumptions retain the displayed defaults. Editable authored planning guesses, not verified provider tariffs, benchmark measurements or a commercial quote. Other native meters retain their explicitly displayed default quantities.
• Planning estimate · editable authored rates and sizing assumptions dated 2026-10-18; not verified provider prices. Explicit source planning region → Explicit target planning region, USD/month.
• Source prices are reference charges, not an invoice. Target lines cover selected service usage/configuration only; adapter hosting and Tensor9 fees are excluded.
• Explicit tariff samples are not performance measurements or capacity qualification. No interpolation or break-even guarantee is implied.
• Variant assumptions show the first axis sample; any axis-dependent configuration is described by this curve’s workload note.
• Editable authored planning guesses, not verified provider tariffs, benchmark measurements or a commercial quote.
• Default-zero rates are explicit assumptions, not evidence that the deployed service or resource is free.
• Provisioned-unit minimums use an editable approximate allocation floor. Modeled target service cost is max(usage/allocation, minimum), with billable network, durable staging and dependent sinks added separately; actual RU/TU sizing, scaling increments and throughput remain unqualified.
• Durable staging is priced once: provisioned targets include adapter state in their selected allocation; native targets add a separate staging allocation when required. Adapter hosting is a separate allocation and must exclude resources already priced as staging, workers or target capacity.
• A declared adapter mapping and cost model do not establish implementation availability or service equivalence.
• This is a declared directed mapping; a planning estimate does not establish deployment or request-serving support.
• All default unit prices and capacity coefficients are editable authored planning guesses, not measured capacity or a provider quote.
• Source and target tariffs name no asserted current model SKU. Select model-specific rates before using the estimate.
• Input and output meters and token expansion remain independent. A cheaper model is not automatically equivalent in capability or quality.
• All target rates are editable authored planning guesses, not verified current list prices, customer discounts or benchmark evidence.
• Input and output token tariffs remain distinct. These illustrative rates name no selected model SKU and establish no equivalent output quality or tokenizer.

Cost scope: Modeled target native service and explicitly modeled state allocation; hosting and Tensor9 fees only when supplied. Excluded costs and workload features:

• Prompt caching, batch discounts, context tiers, grounding, tools, agents, embeddings, search, guardrails and dedicated inference hardware.
• Taxes, discounts, credits and free-tier allowances unless explicitly reflected in edited rates.
• Unmodeled dependent services, task execution and operations outside the selected workload family.

Planning assumptions authored: 2026-10-18. Model: plan-5c6a290efb8ab2af09754f01caf66263075fec9b / 2026-10-18.planning.1. Curve: workload-1.

​

Bedrock model inference · Output tokens per second

Planning estimate with editable assumptions. These authored unit rates and capacity assumptions require provider-price verification and representative benchmarks. They do not constitute verified list-price quotes or evidence that an adapter is available. Estimated monthly service charges from native source usage; no calculator input is required. Adapter hosting and Tensor9 fees are excluded. Source: Explicit source planning region; target: Explicit target planning region; currency: USD. Exact sampled model outputs in USD/month. Difference means target minus origin; a positive difference means the target costs more. Curve assumptions

• Only this native meter varies; all other source usage and translation assumptions retain the displayed defaults. Editable authored planning guesses, not verified provider tariffs, benchmark measurements or a commercial quote. Other native meters retain their explicitly displayed default quantities.
• Planning estimate · editable authored rates and sizing assumptions dated 2026-10-18; not verified provider prices. Explicit source planning region → Explicit target planning region, USD/month.
• Source prices are reference charges, not an invoice. Target lines cover selected service usage/configuration only; adapter hosting and Tensor9 fees are excluded.
• Explicit tariff samples are not performance measurements or capacity qualification. No interpolation or break-even guarantee is implied.
• Variant assumptions show the first axis sample; any axis-dependent configuration is described by this curve’s workload note.
• Editable authored planning guesses, not verified provider tariffs, benchmark measurements or a commercial quote.
• Default-zero rates are explicit assumptions, not evidence that the deployed service or resource is free.
• Provisioned-unit minimums use an editable approximate allocation floor. Modeled target service cost is max(usage/allocation, minimum), with billable network, durable staging and dependent sinks added separately; actual RU/TU sizing, scaling increments and throughput remain unqualified.
• Durable staging is priced once: provisioned targets include adapter state in their selected allocation; native targets add a separate staging allocation when required. Adapter hosting is a separate allocation and must exclude resources already priced as staging, workers or target capacity.
• A declared adapter mapping and cost model do not establish implementation availability or service equivalence.
• This is a declared directed mapping; a planning estimate does not establish deployment or request-serving support.
• All default unit prices and capacity coefficients are editable authored planning guesses, not measured capacity or a provider quote.
• Source and target tariffs name no asserted current model SKU. Select model-specific rates before using the estimate.
• Input and output meters and token expansion remain independent. A cheaper model is not automatically equivalent in capability or quality.
• All target rates are editable authored planning guesses, not verified current list prices, customer discounts or benchmark evidence.
• Input and output token tariffs remain distinct. These illustrative rates name no selected model SKU and establish no equivalent output quality or tokenizer.

Cost scope: Modeled target native service and explicitly modeled state allocation; hosting and Tensor9 fees only when supplied. Excluded costs and workload features:

• Prompt caching, batch discounts, context tiers, grounding, tools, agents, embeddings, search, guardrails and dedicated inference hardware.
• Taxes, discounts, credits and free-tier allowances unless explicitly reflected in edited rates.
• Unmodeled dependent services, task execution and operations outside the selected workload family.

Planning assumptions authored: 2026-10-18. Model: plan-5c6a290efb8ab2af09754f01caf66263075fec9b / 2026-10-18.planning.1. Curve: workload-2.

​

Bedrock model inference → vLLM / Ollama

Origin API: aws::1.0.0::bedrock. Target backend: tensor9::1.0.0::emu::aws/1.0.0/bedrock::incluster. Planning estimate with editable assumptions. Unit rates, workload amplification and capacity assumptions are educated guesses awaiting verification. The displayed amounts are planning estimates, not verified provider list-price quotes or benchmark-qualified capacity. Region names identify the authored scenario assumptions.

​

Bedrock model inference · Input tokens per second

Planning estimate with editable assumptions. These authored unit rates and capacity assumptions require provider-price verification and representative benchmarks. They do not constitute verified list-price quotes or evidence that an adapter is available. Estimated monthly service charges from native source usage; no calculator input is required. Adapter hosting and Tensor9 fees are excluded. Source: Explicit source planning region; target: Explicit target planning region; currency: USD. Exact sampled model outputs in USD/month. Difference means target minus origin; a positive difference means the target costs more. Estimated allocation from planning assumptions; not benchmark calibrated. Only discrete samples are shown. Unpriced means no target quote or cost difference is available within the sizing policy. Estimated allocation from planning assumptions; not benchmark calibrated. The sizing policy grows compute with translated work and peak headroom, memory with compute and working set, and disk with resident working state and reserve. Monthly usage is distinct from resident data; each workload’s assumptions define the translation. HA changes pricing, not this policy’s throughput estimate. Unpriced workloads exceed the policy’s configuration range; no silent vertical cap or automatic sharding is assumed.

• Authored operation throughput, peak and working-set assumptions are not benchmark-calibrated.
• Stored GiB already includes the origin family’s physical footprint assumptions; no second storage amplification is applied.
• The generic operations/vCPU coefficient supplies a provisional compute requirement alongside explicit resource-hour minima.
• Copies and allocation fractions change cost only; they do not increase modeled primary capacity.

Curve assumptions

• Only this native meter varies; all other source usage and translation assumptions retain the displayed defaults. Editable authored planning guesses, not verified provider tariffs, benchmark measurements or a commercial quote. Other native meters retain their explicitly displayed default quantities.
• Planning estimate · editable authored rates and sizing assumptions dated 2026-10-18; not verified provider prices. Explicit source planning region → Explicit target planning region, USD/month.
• Source prices are reference charges, not an invoice. Target lines cover selected service usage/configuration only; adapter hosting and Tensor9 fees are excluded.
• Explicit tariff samples are not performance measurements or capacity qualification. No interpolation or break-even guarantee is implied.
• Variant assumptions show the first axis sample; any axis-dependent configuration is described by this curve’s workload note.
• Editable authored planning guesses, not verified provider tariffs, benchmark measurements or a commercial quote.
• Default-zero rates are explicit assumptions, not evidence that the deployed service or resource is free.
• Provisioned-unit minimums use an editable approximate allocation floor. Modeled target service cost is max(usage/allocation, minimum), with billable network, durable staging and dependent sinks added separately; actual RU/TU sizing, scaling increments and throughput remain unqualified.
• Durable staging is priced once: provisioned targets include adapter state in their selected allocation; native targets add a separate staging allocation when required. Adapter hosting is a separate allocation and must exclude resources already priced as staging, workers or target capacity.
• A declared adapter mapping and cost model do not establish implementation availability or service equivalence.
• This is a declared directed mapping; a planning estimate does not establish deployment or request-serving support.
• All default unit prices and capacity coefficients are editable authored planning guesses, not measured capacity or a provider quote.
• Source and target tariffs name no asserted current model SKU. Select model-specific rates before using the estimate.
• Input and output meters and token expansion remain independent. A cheaper model is not automatically equivalent in capability or quality.
• All target rates are editable authored planning guesses, not verified current list prices, customer discounts or benchmark evidence.
• Named provisioned target: selected CPU, RAM and physical disk allocation grow with workload. No additional per-database-operation price is assumed. Managed service premiums and dedicated accelerator/model-fit requirements need explicit qualification.
• Authored operation throughput, peak and working-set assumptions are not benchmark-calibrated.
• Stored GiB already includes the origin family’s physical footprint assumptions; no second storage amplification is applied.
• The generic operations/vCPU coefficient supplies a provisional compute requirement alongside explicit resource-hour minima.
• Copies and allocation fractions change cost only; they do not increase modeled primary capacity.

Cost scope: Modeled target native service and explicitly modeled state allocation; hosting and Tensor9 fees only when supplied. Excluded costs and workload features:

• Prompt caching, batch discounts, context tiers, grounding, tools, agents, embeddings, search, guardrails and dedicated inference hardware.
• Taxes, discounts, credits and free-tier allowances unless explicitly reflected in edited rates.
• Unmodeled dependent services, task execution and operations outside the selected workload family.

Planning assumptions authored: 2026-10-18. Model: plan-952508c3bf76f8b345ea3c168617029855c8f41f / 2026-10-18.planning.1. Curve: workload-1.

​

Bedrock model inference · Output tokens per second

Planning estimate with editable assumptions. These authored unit rates and capacity assumptions require provider-price verification and representative benchmarks. They do not constitute verified list-price quotes or evidence that an adapter is available. Estimated monthly service charges from native source usage; no calculator input is required. Adapter hosting and Tensor9 fees are excluded. Source: Explicit source planning region; target: Explicit target planning region; currency: USD. Exact sampled model outputs in USD/month. Difference means target minus origin; a positive difference means the target costs more. Estimated allocation from planning assumptions; not benchmark calibrated. Only discrete samples are shown. Unpriced means no target quote or cost difference is available within the sizing policy. Estimated allocation from planning assumptions; not benchmark calibrated. The sizing policy grows compute with translated work and peak headroom, memory with compute and working set, and disk with resident working state and reserve. Monthly usage is distinct from resident data; each workload’s assumptions define the translation. HA changes pricing, not this policy’s throughput estimate. Unpriced workloads exceed the policy’s configuration range; no silent vertical cap or automatic sharding is assumed.

• Authored operation throughput, peak and working-set assumptions are not benchmark-calibrated.
• Stored GiB already includes the origin family’s physical footprint assumptions; no second storage amplification is applied.
• The generic operations/vCPU coefficient supplies a provisional compute requirement alongside explicit resource-hour minima.
• Copies and allocation fractions change cost only; they do not increase modeled primary capacity.

Curve assumptions

• Only this native meter varies; all other source usage and translation assumptions retain the displayed defaults. Editable authored planning guesses, not verified provider tariffs, benchmark measurements or a commercial quote. Other native meters retain their explicitly displayed default quantities.
• Planning estimate · editable authored rates and sizing assumptions dated 2026-10-18; not verified provider prices. Explicit source planning region → Explicit target planning region, USD/month.
• Source prices are reference charges, not an invoice. Target lines cover selected service usage/configuration only; adapter hosting and Tensor9 fees are excluded.
• Explicit tariff samples are not performance measurements or capacity qualification. No interpolation or break-even guarantee is implied.
• Variant assumptions show the first axis sample; any axis-dependent configuration is described by this curve’s workload note.
• Editable authored planning guesses, not verified provider tariffs, benchmark measurements or a commercial quote.
• Default-zero rates are explicit assumptions, not evidence that the deployed service or resource is free.
• Provisioned-unit minimums use an editable approximate allocation floor. Modeled target service cost is max(usage/allocation, minimum), with billable network, durable staging and dependent sinks added separately; actual RU/TU sizing, scaling increments and throughput remain unqualified.
• Durable staging is priced once: provisioned targets include adapter state in their selected allocation; native targets add a separate staging allocation when required. Adapter hosting is a separate allocation and must exclude resources already priced as staging, workers or target capacity.
• A declared adapter mapping and cost model do not establish implementation availability or service equivalence.
• This is a declared directed mapping; a planning estimate does not establish deployment or request-serving support.
• All default unit prices and capacity coefficients are editable authored planning guesses, not measured capacity or a provider quote.
• Source and target tariffs name no asserted current model SKU. Select model-specific rates before using the estimate.
• Input and output meters and token expansion remain independent. A cheaper model is not automatically equivalent in capability or quality.
• All target rates are editable authored planning guesses, not verified current list prices, customer discounts or benchmark evidence.
• Named provisioned target: selected CPU, RAM and physical disk allocation grow with workload. No additional per-database-operation price is assumed. Managed service premiums and dedicated accelerator/model-fit requirements need explicit qualification.
• Authored operation throughput, peak and working-set assumptions are not benchmark-calibrated.
• Stored GiB already includes the origin family’s physical footprint assumptions; no second storage amplification is applied.
• The generic operations/vCPU coefficient supplies a provisional compute requirement alongside explicit resource-hour minima.
• Copies and allocation fractions change cost only; they do not increase modeled primary capacity.

Cost scope: Modeled target native service and explicitly modeled state allocation; hosting and Tensor9 fees only when supplied. Excluded costs and workload features:

• Prompt caching, batch discounts, context tiers, grounding, tools, agents, embeddings, search, guardrails and dedicated inference hardware.
• Taxes, discounts, credits and free-tier allowances unless explicitly reflected in edited rates.
• Unmodeled dependent services, task execution and operations outside the selected workload family.

Planning assumptions authored: 2026-10-18. Model: plan-952508c3bf76f8b345ea3c168617029855c8f41f / 2026-10-18.planning.1. Curve: workload-2. See the service catalog for operation coverage, supported directions and backend limitations.