Setting the file. One moment.
Subchapter 27.60
references/shared/pricing-cache.mdMarkdown58 KBView on GitHub
Last updated: 2026-09-03 Region: us-east-1 Currency: USD Accuracy: ±5-10% for infrastructure services (sourced from AWS Price List API), ±15-25% for AI models (sourced from public pricing pages)
Prices may vary by region and change over time. Use for estimation only; there is no live pricing lookup — for the latest rates, check the public AWS pricing pages (e.g. https://aws.amazon.com/bedrock/pricing (opens in a new tab)). Amazon Nova figures in the Bedrock subsection often reference US East (Ohio) and inference mode (global vs geo); other services in this file default to us-east-1 unless noted.
Staleness warning: If today’s date is more than 30 days after the Last updated date above, treat AI model prices as potentially stale (±15-25% accuracy may widen). Infrastructure prices (Fargate, RDS, S3, etc.) change rarely and remain reliable longer. When staleness is detected, keep pricing_source.status: "cached" (the schema enum is cached | cached_fallback | unavailable — there is no cached_stale status) and record the staleness in the dedicated pricing_source.fallback_staleness object: set is_stale: true and staleness_warning: "Pricing cache is more than 30 days old — AI model prices may have changed. Verify against [aws.amazon.com/bedrock/pricing](https://aws.amazon.com/bedrock/pricing/)." Surface that same warning to the user in the estimate output.
Lifecycle is not a cached price field. The Status column below is a dated snapshot, not permission to skip the lifecycle check. Before selecting any model, call GetFoundationModel or ListFoundationModels and read modelLifecycle.status. For a model launched on or after 2026-09-07, also read its model card: its Legacy period may be 45 days rather than 6 months, and it will never appear in the Legacy/EOL table. See vendored/ai/ai-model-lifecycle.md.
| Metric | Rate |
|---|---|
| Per vCPU-hour (x86) | $0.04048 |
| Per GB memory-hour (x86) | $0.004445 |
| Per vCPU-hour (ARM64) | $0.03238 |
| Per GB memory-hour (ARM64) | $0.003556 |
Linux, on-demand. ARM64 (Graviton) is ~20% below x86 per AWS Fargate pricing. Default dev-tier sizing is 0.5 vCPU.
| Metric | Rate |
|---|---|
| Per request | $0.0000002 |
| Per GB-second (x86, first 6B) | $0.0000166667 |
| Per GB-second (x86, over 6B) | $0.000015 |
| Per GB-second (arm64, first 6B) | $0.0000133334 |
| Per GB-second (arm64, over 6B) | $0.000012 |
| Free tier | 1M requests + 400K GB-sec/month |
arm64 (Graviton) is ~20% below x86 per GB-second; per-request price is the same for both architectures.
| Metric | Rate |
|---|---|
| Service fee | $0.00 (free — no additional charge for EB itself) |
Costs are the underlying resources (EC2, ALB, EBS, CloudWatch). Typical estimates:
Profiles below use the Graviton (t4g.*) default that the design phase now emits for EB; for x86 environments use the t3.* equivalents (~15–20% higher).
| Profile | Underlying Resources | Estimated Monthly |
|---|---|---|
| Dev (single instance, t4g.small, no ALB) | EC2 t4g.small | ~$12 |
| Dev + RDS (t4g.small + db.t4g.micro) | EC2 + RDS db.t4g.micro | ~$28–48 |
| Prod (load-balanced, 2× t4g.medium, ALB) | 2× EC2 + ALB + EBS | ~$85–110 |
| Prod + RDS (2× t4g.medium, ALB, db.t4g.medium) | 2× EC2 + ALB + RDS db.t4g.medium | ~$165–210 |
| Metric | Rate |
|---|---|
| Cluster fee per hour | $0.10 |
| Cluster fee per month | $73.00 |
Worker nodes billed separately as EC2 or Fargate.
| Instance | $/hour | $/month |
|---|---|---|
| t3.micro | 0.0104 | 7.58 |
| t3.small | 0.0208 | 15.17 |
| t3.medium | 0.0416 | 30.34 |
| t3.large | 0.0832 | 60.68 |
| m5.large | 0.096 | 70.08 |
| m5.xlarge | 0.192 | 140.16 |
| c5.large | 0.085 | 62.05 |
| c5.xlarge | 0.17 | 124.10 |
~15–20% below the x86 equivalent at the same vCPU/memory. Dev-tier rows cached below; set pricing_source: "unavailable" for any family or size not listed.
| Instance | $/hour | $/month | x86 equivalent |
|---|---|---|---|
| t4g.micro | 0.0084 | 6.13 | t3.micro |
| t4g.small | 0.0168 | 12.26 | t3.small |
| t4g.medium | 0.0336 | 24.53 | t3.medium |
| t4g.large | 0.0672 | 49.06 | t3.large |
| m7g.large | 0.0816 | 59.57 | m5.large |
| m7g.xlarge | 0.1632 | 119.14 | m5.xlarge |
| c7g.large | 0.0725 | 52.93 | c5.large |
| c7g.xlarge | 0.145 | 105.85 | c5.xlarge |
| r7g.large | 0.1071 | 78.18 | r6i.large |
| r7g.xlarge | 0.2142 | 156.37 | r6i.xlarge |
Aurora replicates across 3 AZs by default. Pricing is listed as Single-AZ — do NOT use Multi-AZ filter with MCP.
| Instance | $/hour |
|---|---|
| db.t4g.medium | 0.073 |
| db.t4g.large | 0.146 |
| db.r6g.large | 0.26 |
| db.r6i.large | 0.29 |
| db.r7g.xlarge | 0.553 |
| db.r8g.large | 0.276 |
| db.r8g.xlarge | 0.552 |
| db.r8g.2xlarge | 1.104 |
| db.r8g.4xlarge | 2.208 |
| db.r8g.8xlarge | 4.416 |
| Storage/IO | Rate |
|---|---|
| Storage per GB-month | $0.10 |
| I/O per million requests | $0.20 |
Same Multi-AZ note as Aurora PostgreSQL.
| Instance | $/hour |
|---|---|
| db.t4g.medium | 0.073 |
| db.t4g.large | 0.146 |
Storage and I/O same as Aurora PostgreSQL.
Scales between min and max ACU. Both PostgreSQL and MySQL cost the same per ACU.
| Metric | Rate |
|---|---|
| Standard per ACU-hour | $0.12 |
| I/O Optimized per ACU-hour | $0.16 |
| Storage per GB-month | $0.10 |
| I/O per million requests | $0.20 |
Min ACU = 0.5, scales to 256 ACU.
| Instance | $/hour |
|---|---|
| db.t4g.micro | 0.032 |
| db.t4g.small | 0.065 |
| db.t4g.medium | 0.129 |
| db.t4g.large | 0.258 |
| db.t4g.xlarge | 0.517 |
| db.t4g.2xlarge | 1.034 |
| Storage | Rate |
|---|---|
| Per GB-month | $0.23 |
For Multi-AZ, approximately double these rates.
| Instance | $/hour | $/month |
|---|---|---|
| db.t3.small | 0.034 | 24.82 |
| db.t3.medium | 0.068 | 49.64 |
| db.t3.large | 0.136 | 99.28 |
| db.t4g.micro | 0.016 | 11.68 |
| db.t4g.small | 0.032 | 23.36 |
| db.t4g.medium | 0.065 | 47.45 |
| db.m5.large | 0.171 | 124.83 |
| Storage | Rate |
|---|---|
| Per GB-month | $0.23 |
| Backup per GB-month | $0.023 |
| Metric | Rate |
|---|---|
| Read per million RRU | $0.125 |
| Write per million WRU | $0.625 |
| Storage per GB-month | $0.25 |
Single-AZ pricing. For Multi-AZ, approximately double.
| Node | $/hour | $/month |
|---|---|---|
| cache.t3.micro | 0.017 | 12.41 |
| cache.t3.small | 0.034 | 24.82 |
| cache.t3.medium | 0.068 | 49.64 |
| cache.t4g.micro | 0.016 | — |
| cache.t4g.small | 0.032 | — |
| cache.t4g.medium | 0.065 | — |
| cache.r6g.large | 0.206 | 150.38 |
| Tier | Rate per GB-month |
|---|---|
| Standard (first 50 TB) | $0.023 |
| Standard (next 450 TB) | $0.022 |
| Standard (over 500 TB) | $0.021 |
| Standard-IA | $0.0125 |
| Glacier Flexible Retrieval | $0.0036 |
| Requests | Rate |
|---|---|
| PUT per 1K | $0.005 |
| GET per 1K | $0.0004 |
| S3-IA retrieval per GB | $0.01 |
| Glacier retrieval per GB | $0.01 |
| Metric | Rate |
|---|---|
| Per ALB-hour | $0.0225 |
| Per LCU-hour | $0.008 |
| Monthly fixed | $16.43 |
| Metric | Rate |
|---|---|
| Per NLB-hour | $0.0225 |
| Per LCU-hour | $0.006 |
| Monthly fixed | $16.43 |
| Metric | Rate |
|---|---|
| Per hour | $0.045 |
| Per GB processed | $0.045 |
| Monthly fixed | $32.85 |
VPC itself is free. Add-ons:
| Component | Rate |
|---|---|
| VPN connection per hour | $0.05 |
| VPN monthly | $36.50 |
| Interface endpoint per hour | $0.01 |
| Interface endpoint monthly | $7.30 |
| Metric | Rate |
|---|---|
| Hosted zone per month | $0.50 |
| Per million standard queries | $0.40 |
| Per million latency queries | $0.60 |
| Health check per month | $0.50 |
| Metric | Rate |
|---|---|
| Per GB transfer (first 10 TB) | $0.085 |
| Per 10K HTTPS requests | $0.01 |
| Free tier | 1 TB transfer/month |
| Metric | Rate |
|---|---|
| Per secret per month | $0.40 |
| Per 10K API calls | $0.05 |
| Metric | Rate | Notes |
|---|---|---|
| Log ingestion per GB (Standard) | $0.50 | |
| Log ingestion per GB (Infrequent Access) | $0.25 | 50% cheaper than Standard; no Live Tail, subscription filters, or metric filters |
| Log storage per GB-month | $0.03 | Same for both Standard and Infrequent Access |
| Insights query per GB scanned | $0.005 | Same for both log classes |
| Custom metric per month (≤10K) | $0.30 | Flat rate at startup scale; $0.10 for 10K–250K, $0.05 for 250K+ |
| Standard alarm per month | $0.10 | |
| High-resolution alarm per month | $0.30 | |
| Dashboard per month (first 3 free) | $3.00 |
Free tier (not subtracted in estimates — startup apps often exceed quickly):
| Metric | Rate | Notes |
|---|---|---|
| Traces recorded per million | $5.00 | First 100K free/month |
| Traces retrieved per million | $0.50 | First 1M free/month |
| Traces scanned per million | $0.50 | First 1M free/month |
| Metric | Rate | Notes |
|---|---|---|
| Per-task performance log/GB | $0.50 | Same as standard log ingestion |
| Cluster/service/task metrics | $0.30 | Per custom metric — can accumulate quickly |
| Metric | Rate |
|---|---|
| Standard per million requests | $0.40 |
| FIFO per million requests | $0.50 |
| Free tier | 1M requests/month |
| Metric | Rate |
|---|---|
| Per million publishes | $0.50 |
| SQS delivery per million | $0.00 |
| HTTP delivery per million | $0.60 |
| Free tier | 1M publishes/month |
| Metric | Rate |
|---|---|
| Per million events | $1.00 |
| Metric | Rate |
|---|---|
| Per RPU-hour | $0.375 |
| Storage per GB-month | $0.024 |
Minimum 8 RPU base capacity.
| Metric | Rate |
|---|---|
| Per TB scanned | $5.00 |
Columnar formats (Parquet, ORC) and partitioning reduce scan volume.
| Training Instance | $/hour |
|---|---|
| ml.m5.large | 0.115 |
| ml.m5.xlarge | 0.23 |
| ml.g4dn.xlarge (GPU) | 0.736 |
| Inference Instance | $/hour | $/month |
|---|---|---|
| ml.t3.medium | 0.05 | 36.50 |
| ml.m5.large | 0.115 | 83.95 |
Serverless inference: $0.0000200 per second per GB memory.
Anthropic Claude (Standard on-demand) figures below match US East (N. Virginia) on Amazon Bedrock pricing (opens in a new tab) as of cache refresh. Recommend defaults (new migrations): Claude Sonnet 5 (flagship), Claude Opus 4.8 (hardest reasoning), Claude Haiku 4.5 (cost/speed). Do not default to any Claude Fable / Mythos frontier model (Fable 5, Fable 5.1, and successors). Claude Fable 5 and Claude Fable 5.1 (GA Sep 1, 2026) are the most expensive Anthropic models at $10/$50 per 1M tokens (Mythos-class); 5.1’s on-demand rate difference is cache read at $0.25 (0.025x) vs $1.00; Bedrock lists no batch rate for either. Both are Anthropic Covered Models: using them requires opting the account into the aws_review data-retention mode, and Fable 5.1 is served commercially only via us./global. CRIS profiles (no in-region — the bare anthropic.claude-fable-5-1 id is not invokable on bedrock-runtime, hence the us. form in the table), with in-region access in AWS GovCloud (US) only. Claude Mythos 5.1 is a gated Preview for vetted cyber/bio research organizations and is not a migration target. Claude Opus 4.8 keeps the same $5/$25 rate as Opus 4.6/4.7. Claude Sonnet 5 launched June 30 at $2/$10; that launch rate became the standard price on Sep 1, 2026 (the scheduled increase to $3/$15 was cancelled), so Sonnet 5 is now both newer and cheaper than Sonnet 4.6 ($3/$15). Claude Opus 4.7 lists the same headline on-demand input/output as Opus 4.6 on that page; confirm batch availability per model (Opus 4.7 batch was not listed on the global cross-region table when this row was added). Claude Opus 4.1 entered Legacy on Jul 8, 2026 (EOL Jan 8, 2027). Batch, prompt cache (5m / 1h write + cache read), and geo / in-region cross-region rows on that page can differ; e.g. US East (Ohio) cross-region inference for Claude Sonnet 4.6 is listed at $3.30 / $16.50 per 1M input/output (≈10% above N. Virginia). Long-context SKUs do not all use the same multiplier: Sonnet 4.6 and Opus 4.6 long-context modes share the same on-demand rates as the non–long-context rows on the standard table; Sonnet 4.5 and Sonnet 4 long-context rows are priced higher on that same table.
See vendored/ai/ai-model-lifecycle.md for lifecycle details. Do not recommend Legacy models for new migrations. Rows whose Status is restricted (…) are never recommended_model / backup_model and never a default (Covered Models, gated previews).
| Model | Model ID | Provider | Input $/1M | Output $/1M | Context | Tier | Status |
|---|---|---|---|---|---|---|---|
| Claude Fable 5 | anthropic.claude-fable-5 | Anthropic | 10.00 | 50.00 | 1M | frontier | restricted (Covered Model; aws_review opt-in) |
| Claude Fable 5.1 | us.anthropic.claude-fable-5-1 | Anthropic | 10.00 | 50.00 | 1M | frontier | restricted (Covered Model; aws_review opt-in; CRIS only) |
| Claude Sonnet 5 | anthropic.claude-sonnet-5 | Anthropic | 2.00 | 10.00 | 1M | flagship | active ($2/$10 made the standard price Sep 1, 2026) |
| Claude Opus 4.8 | anthropic.claude-opus-4-8 | Anthropic | 5.00 | 25.00 | 200K | premium | active |
| Claude Sonnet 4.6 | anthropic.claude-sonnet-4-6 | Anthropic | 3.00 | 15.00 | 200K | flagship | active |
| Claude Sonnet 4.6 — Long Context | anthropic.claude-sonnet-4-6 | Anthropic | 3.00 | 15.00 | 200K+ | flagship | active |
| Claude Opus 4.6 | anthropic.claude-opus-4-6-v1 | Anthropic | 5.00 | 25.00 | 200K | premium | active |
| Claude Opus 4.6 — Long Context | anthropic.claude-opus-4-6-v1 | Anthropic | 5.00 | 25.00 | 200K+ | premium | active |
| Claude Opus 4.5 | — | Anthropic | 5.00 | 25.00 | 200K | premium | active |
| Claude Sonnet 4.5 | — | Anthropic | 3.00 | 15.00 | 200K | flagship | active |
| Claude Sonnet 4.5 — Long Context | — | Anthropic | 6.00 | 22.50 | 200K+ | flagship | active |
| Claude Haiku 4.5 | anthropic.claude-haiku-4-5-20251001-v1:0 | Anthropic | 1.00 | 5.00 | 200K | fast | active |
| Claude Opus 4.1 | anthropic.claude-opus-4-1-20250805-v1:0 | Anthropic | 15.00 | 75.00 | 200K | premium | legacy (EOL Jan 8, 2027) |
| Claude Sonnet 4 | anthropic.claude-sonnet-4-20250514-v1:0 | Anthropic | 3.00 | 15.00 | 200K | flagship | excluded (EOL Oct 14, 2026) |
| Llama 4 Maverick | meta.llama4-maverick-17b-instruct-v1:0 | Meta | 0.24 | 0.97 | 1M | mid | active |
| Llama 4 Scout | meta.llama4-scout-17b-instruct-v1:0 | Meta | 0.17 | 0.66 | 10M | efficient | active |
| Llama 3.3 70B | meta.llama3-3-70b-instruct-v1:0 | Meta | 0.72 | 0.72 | 128K | mid | active |
| Llama 3.2 90B | meta.llama3-2-90b-instruct-v1:0 | Meta | 0.72 | 0.72 | 128K | mid | EOL (Jul 7, 2026) |
| Nova 2 Lite | amazon.nova-2-lite-v1:0 | Amazon | 0.33 | 2.75 | 1M | mid | active |
| Nova 2 Pro (Preview) | amazon.nova-2-pro-v1:0 | Amazon | 1.375 | 11.00 | 1M | flagship | active |
| Nova Pro | amazon.nova-pro-v1:0 | Amazon | 0.80 | 3.20 | 300K | mid | active |
| Nova Pro (latency optimized) | — | Amazon | 1.00 | 4.00 | 300K | mid | active |
| Nova Lite | amazon.nova-lite-v1:0 | Amazon | 0.06 | 0.24 | 300K | fast | active |
| Nova Micro | amazon.nova-micro-v1:0 | Amazon | 0.035 | 0.14 | 128K | budget | active |
| Nova Premier | amazon.nova-premier-v1:0 | Amazon | 2.50 | 12.50 | 1M | reasoning | EOL (2026-09-14) |
| Mistral Large 3 | mistral.mistral-large-3-675b-instruct | Mistral | 0.50 | 1.50 | 256K | flagship | active |
| DeepSeek-R1 | deepseek.r1-v1:0 | DeepSeek | 1.35 | 5.40 | 128K | reasoning | active |
| DeepSeek-V3.1 | — | DeepSeek | 0.58 | 1.68 | — | mid | active (Sydney only) |
| gpt-oss-20b | openai.gpt-oss-20b-1:0 | OpenAI | 0.07 | 0.30 | 128K | budget | active |
| gpt-oss-120b | openai.gpt-oss-120b-1:0 | OpenAI | 0.15 | 0.60 | 128K | efficient | active |
| GPT-5.6 Sol | openai.gpt-5.6-sol | OpenAI | 4.40 | 22.00 | 272K | frontier | active (mantle in-region + runtime CRIS; 1M tier 8.80/33.00) |
| GPT-5.6 Terra | openai.gpt-5.6-terra | OpenAI | 2.20 | 13.20 | 272K | flagship | active (mantle in-region + runtime CRIS; 1M tier 4.40/19.80) |
| GPT-5.6 Luna | openai.gpt-5.6-luna | OpenAI | 0.22 | 1.32 | 272K | fast | active (mantle in-region + runtime CRIS; 1M tier 0.44/1.98) |
| GPT-5.5 | openai.gpt-5.5 | OpenAI | 5.50 | 33.00 | 272K | frontier | active (mantle only; no 1M tier) |
| GPT-5.4 | openai.gpt-5.4 | OpenAI | 2.75 | 16.50 | 272K | flagship | active (mantle only; no 1M tier) |
| Gemma 4 31B | google.gemma-4-31b | 0.14 | 0.40 | 256K | mid | active (Mantle only) | |
| Gemma 4 26B-A4B | google.gemma-4-26b-a4b | 0.13 | 0.40 | 256K | efficient | active (Mantle only) | |
| Gemma 4 E2B | google.gemma-4-e2b | 0.04 | 0.08 | 128K | budget | active (Mantle only) | |
| Gemma 3 4B IT | google.gemma-3-4b-it | 0.04 | 0.08 | 128K | budget | active | |
| Gemma 3 12B IT | google.gemma-3-12b-it | 0.09 | 0.29 | 128K | budget | active | |
| Gemma 3 27B IT | google.gemma-3-27b-it | 0.23 | 0.38 | 128K | efficient | active | |
| MiniMax M2 | minimax.minimax-m2 | MiniMax | 0.30 | 1.20 | 1M | mid | active |
| MiniMax M2.1 | minimax.minimax-m2.1 | MiniMax | 0.30 | 1.20 | 196K | mid | active |
| MiniMax M2.5 | minimax.minimax-m2.5 | MiniMax | 0.30 | 1.20 | 196K | mid | active |
| Jamba 1.5 Large | ai21.jamba-1-5-large-v1:0 | AI21 Labs | 2.00 | 8.00 | — | mid | excluded (EOL 2026-11-26) |
| Jamba 1.5 Mini | ai21.jamba-1-5-mini-v1:0 | AI21 Labs | 0.20 | 0.40 | — | efficient | excluded (EOL 2026-11-26) |
| Jurassic-2 Mid | — | AI21 Labs | 12.50 | 12.50 | — | legacy | legacy |
| Jurassic-2 Ultra | — | AI21 Labs | 18.80 | 18.80 | — | legacy | legacy |
| Jamba-Instruct | — | AI21 Labs | 0.50 | 0.70 | — | mid | active |
Active image generation models on Bedrock. Priced per image (not per token). Use for image_generation capability workloads.
| Model | Model ID | Price/image | Resolution | Tier | Status |
|---|---|---|---|---|---|
| Stable Image Ultra | stability.stable-image-ultra-v1:0 | $0.08 | up to 4MP | premium | active |
| Stable Diffusion 3.5 Large | stability.sd3-5-large-v1:0 | $0.065 | up to 1MP | flagship | active |
| Stable Image Core | stability.stable-image-core-v1:0 | $0.04 | up to 1MP | fast | active |
Image editing services (inpaint, erase, upscale, etc.) are priced at $0.03–$0.60/operation. See Bedrock pricing (opens in a new tab) for full list.
Cost comparison note: DALL-E 3 (OpenAI) charges $0.04–$0.12/image depending on resolution. Google Imagen charges per character of prompt. When comparing, use per-image cost directly — do not convert Stability AI prices to per-token equivalents.
Per 1M tokens unless noted. See Bedrock pricing (opens in a new tab) for full regional and tier tables.
Batch support verified 2026-09-02 against the supported Regions and models for batch inference (opens in a new tab) table: Opus 4.6, Sonnet 4.6, Opus 4.5, Sonnet 4.5, Sonnet 4.5 — LC, and Haiku 4.5 are listed (via cross-region inference profiles; batch is 50% of on-demand per the pricing page, matching the rows below). Fable 5, Sonnet 5, and Opus 4.8 are NOT on that table — Sonnet 5 and Opus 4.8’s batch cells below are unverified (‡): do not build a batch-discount TCO on them; price on-demand and note batch as a possible future saving pending the docs table listing them. Fable 5 / 5.1 instead carry N/A per the separate pricing-page verification below. Prompt-cache columns are unaffected (caching support is independent of batch). Batch rate vs. cross-region inference (CRIS): the confirmed rows show 50% of the N. Virginia on-demand price. Where batch is only reachable through a CRIS profile that lists above N. Virginia (e.g. Sonnet 4.6 in US East (Ohio) at ≈10% higher — see the on-demand section), the effective batch rate is 50% of that CRIS price, i.e. ≈10% above the cells here. Re-derive from the profile’s on-demand rate for a region-specific quote. Do not cross-check these rows against the AWS Pricing Calculator — as of Sep 2026 the calculator carries no batch metered IDs for Opus 4.6 / Sonnet 4.6 and collapses other batch/cache SKUs (known calculator defect, not a pricing-page signal). The pricing page and the docs table above are the sources of truth.
| Model | Batch in | Batch out | 5m cache write | 1h cache write | Cache read |
|---|---|---|---|---|---|
| Claude Fable 5 | N/A | N/A | 12.50 | 20.00 | 1.00 |
| Claude Fable 5.1 | N/A | N/A | 12.50 | 20.00 | 0.25 |
| Claude Sonnet 5 | 1.00 ‡ | 5.00 ‡ | 2.50 | 4.00 | 0.20 |
| Claude Opus 4.8 | 2.50 ‡ | 12.50 ‡ | 6.25 | 10.00 | 0.50 |
| Claude Sonnet 4.6 (+ LC) | 1.50 | 7.50 | 3.75 | 6.00 | 0.30 |
| Claude Opus 4.6 (+ LC) | 2.50 | 12.50 | 6.25 | 10.00 | 0.50 |
| Claude Opus 4.5 | 2.50 | 12.50 | 6.25 | 10.00 | 0.50 |
| Claude Haiku 4.5 | 0.50 | 2.50 | 1.25 | 2.00 | 0.10 |
| Claude Sonnet 4.5 | 1.50 | 7.50 | 3.75 | 6.00 | 0.30 |
| Claude Sonnet 4.5 — LC | 3.00 | 11.25 | 7.50 | 12.00 | 0.60 |
Batch: the Bedrock pricing page lists N/A for Claude Fable 5 and Fable 5.1 in both the Global and the Geo / In-region Anthropic tables (read 2026-09-03). Anthropic’s first-party API offers a 50% batch discount on these models; Bedrock does not list one — do not assume a batch rate for Fable-class models.
‡ Not listed on the batch-supported models table as of 2026-09-02 — rate is the standard 50%-of-on-demand
projection, not a confirmed SKU. Mark these batch cells _unverified_ in estimate output; the unverified gate in
estimate-ai.md (§ Pricing source caveat) treats any _unverified_ row as blocking for a quoted figure — resolve
from the Bedrock pricing page first.
On-demand, US East (N. Virginia) per Amazon Bedrock pricing (opens in a new tab). Prices per 1M input / output tokens.
| Model | Input $/1M | Output $/1M |
|---|---|---|
| Jamba 1.5 Large | 2.00 | 8.00 |
| Jamba 1.5 Mini | 0.20 | 0.40 |
| Jurassic-2 Mid | 12.50 | 12.50 |
| Jurassic-2 Ultra | 18.80 | 18.80 |
| Jamba-Instruct | 0.50 | 0.70 |
Quick-reference rows use — for model ID and context; resolve in the Bedrock console or AWS model documentation.
Per Amazon Bedrock pricing (opens in a new tab) (Mistral AI). Priority tier ≈ +75% vs Standard; Flex ≈ −50% vs Standard on the same page.
| Model | Input $/1M | Output $/1M | Batch in | Batch out |
|---|---|---|---|---|
| Pixtral Large (25.02) | 2.00 | 6.00 | N/A | N/A |
Prices per 1M input / output tokens.
| Model | Input $/1M | Output $/1M |
|---|---|---|
| Devstral 2 123B | 0.40 | 2.00 |
| Magistral Small 1.2 | 0.50 | 1.50 |
| Voxtral Mini 1.0 | 0.04 | 0.04 |
| Voxtral Small 1.0 | 0.10 | 0.30 |
| Ministral 3B 3.0 | 0.10 | 0.10 |
| Ministral 8B 3.0 | 0.15 | 0.15 |
| Ministral 14B 3.0 | 0.20 | 0.20 |
| Mistral Large 3 | 0.50 | 1.50 |
Rates differ in Asia Pacific (Mumbai), São Paulo, Tokyo, Europe (Ireland/Milan/London), Sydney, Jakarta, Frankfurt, Stockholm (e.g. Mistral Large 3 Mumbai $0.59 / $1.76). Devstral 2 123B appears in Jakarta / Frankfurt / Stockholm at $0.48 / $2.40 on the same page.
Per Amazon Bedrock pricing (opens in a new tab) (DeepSeek).
Note: DeepSeek-V3.1 is no longer listed for US East regions on the Bedrock pricing page as of May 2026. Use DeepSeek-V3.2 for US East deployments. DeepSeek-V3.1 remains available in Asia Pacific (Sydney).
| Model | Input $/1M | Output $/1M |
|---|---|---|
| DeepSeek-R1 | 1.35 | 5.40 |
| Model | Input $/1M | Output $/1M |
|---|---|---|
| DeepSeek v3.2 | 0.62 | 1.85 |
See shared/openai-on-bedrock.md for model IDs, endpoint paths, regions, quotas, and caching rules. Bedrock
in-region is priced at parity with OpenAI’s data residency tier — exactly 1.10x OpenAI’s standard list price — so
a same-model migration costs about 10% MORE, not the same. Do not describe it as cost-neutral.
Regions (mantle): us-east-1 / us-east-2 for all five; us-west-2 additionally carries Terra, Luna and GPT-5.4; AWS GovCloud us-gov-west-1 / us-gov-east-1 carry Terra and Luna, us-gov-west-1 also GPT-5.4 (at its own rate below). Rates reflect the July 30, 2026 reduction (Luna −80%, Terra −20%) and the Aug 21, 2026 Sol reduction (−20% input / −33% output, promotional through at least Nov 21, 2026).
| Model | Input $/1M | Output $/1M | Cache write $/1M | Cache read $/1M |
|---|---|---|---|---|
| GPT-5.6 Sol | 4.40 | 22.00 | 5.50 | 0.44 |
| GPT-5.6 Terra | 2.20 | 13.20 | 2.75 | 0.22 |
| GPT-5.6 Luna | 0.22 | 1.32 | 0.275 | 0.022 |
| GPT-5.5 | 5.50 | 33.00 | — | 0.55 |
| GPT-5.4 | 2.75 | 16.50 | — | 0.275 |
| Model | Input $/1M | Output $/1M |
|---|---|---|
| GPT-5.6 Sol | 8.80 | 33.00 |
| GPT-5.6 Terra | 4.40 | 19.80 |
| GPT-5.6 Luna | 0.44 | 1.98 |
A workload above 272K context must be priced at the long-context tier. GPT-5.5 and GPT-5.4 have no such tier, so
their usable window is 272K. Global CRIS is published at OpenAI’s standard list price (cost parity, GPT-5.6 only —
see openai-on-bedrock.md). GovCloud GPT-5.4 is 3.30 / 19.80.
One source conflict. These models are absent from the AWS Price List API entirely: querying
AmazonBedrockreturns onlygpt-ossand GPT OSS Safeguard, and filtering onGPT-5or agpt-5usage type returns zero rows (price-list publication 2026-08-04). An empty price-list result is not evidence the model is unavailable. (An earlier revision also flagged the AWS News Blog’s Luna 0.20 / 1.20 as conflicting; it is the Global CRIS rate, not an error.)
Prompt caching (GPT-5.6 only): cached input read at a 90% discount, cache write at 1.25x uncached input, minimum 1,024-token prefix, up to 4 breakpoints, ≥30-minute retention. Cached input is exempt from the input-TPM quota. GPT-5.5 and GPT-5.4 do not list prompt caching support.
| Model | Region | Input $/1M | Output $/1M |
|---|---|---|---|
| gpt-oss-20b | US East (Ohio) | 0.07 | 0.30 |
| gpt-oss-120b | US East (Ohio) | 0.15 | 0.60 |
| gpt-oss-20b | Asia Pacific (Sydney) | 0.0721 | 0.3090 |
| gpt-oss-120b | Asia Pacific (Sydney) | 0.1545 | 0.6180 |
The Bedrock page also lists Flex, Priority, Batch, GPT OSS Safeguard, and model customization pricing for other regions.
Per Amazon Bedrock pricing (opens in a new tab) (Meta). Prices per 1M input / output tokens unless noted.
| Model | On-demand in | On-demand out | Batch in | Batch out |
|---|---|---|---|---|
| Llama 4 Maverick 17B | 0.24 | 0.97 | 0.12 | 0.485 |
| Llama 4 Scout 17B | 0.17 | 0.66 | 0.085 | 0.33 |
| Model | On-demand in | On-demand out | Batch in | Batch out |
|---|---|---|---|---|
| Llama 3.3 Instruct (70B) | 0.72 | 0.72 | 0.36 | 0.36 |
Lifecycle note: All Llama 3.2 Instruct models reached EOL on Jul 7, 2026 and are no longer available for inference on Bedrock. Do not select for any migrations. Use Llama 4 Scout / Maverick instead. See
vendored/ai/ai-model-lifecycle.md.
| Model | On-demand in | On-demand out | Batch in | Batch out |
|---|---|---|---|---|
| Llama 3.2 Instruct (1B) | 0.10 | 0.10 | N/A | N/A |
| Llama 3.2 Instruct (3B) | 0.15 | 0.15 | N/A | N/A |
| Llama 3.2 Instruct (11B) | 0.16 | 0.16 | N/A | N/A |
| Llama 3.2 Instruct (90B) | 0.72 | 0.72 | N/A | N/A |
Fine-tuning (per 1M tokens trained / month storage / no-commit PT per model unit-hour):
| Model | Train 1M tokens | Store / month | Infer / unit-hr (no commit) |
|---|---|---|---|
| Llama 3.2 Instruct (1B) | $0.50 | $1.95 | $23.00 |
| Llama 3.2 Instruct (3B) | $1.10 | $1.95 | $23.00 |
| Llama 3.2 Instruct (11B) | $3.50 | $1.95 | $23.00 |
| Llama 3.2 Instruct (90B) | $7.90 | $1.95 | $30.00 |
Provisioned throughput ($/hour per model unit):
| Model | No commit | 1-mo commit | 6-mo commit |
|---|---|---|---|
| Llama 3.2 Instruct (1B) | $23.00 | $20.30 | $12.54 |
| Llama 3.2 Instruct (3B) | $23.00 | $20.30 | $12.54 |
| Llama 3.2 Instruct (11B) | $23.00 | $20.30 | $12.54 |
| Llama 3.2 Instruct (90B) | $30.00 | $26.48 | $16.35 |
Lifecycle note: Llama 3.1 405B Instruct reached EOL on Jul 7, 2026 and is no longer available for inference on Bedrock. Do not select for any migrations. Use Llama 4 Maverick instead. See
vendored/ai/ai-model-lifecycle.md.
| Model | On-demand in | On-demand out | Batch in | Batch out |
|---|---|---|---|---|
| Llama 3.1 Instruct (8B) | 0.22 | 0.22 | 0.11 | 0.11 |
| Llama 3.1 Instruct (70B) | 0.72 | 0.72 | 0.36 | 0.36 |
| Llama 3.1 Instruct (405B) | 2.40 | 2.40 | 1.20 | 1.20 |
| Llama 3.1 Instruct (70B) (latency optimized inf.) | 0.90 | 0.90 | N/A | N/A |
| Llama 3.1 Instruct (405B) (latency optimized inf.) | 3.00 | 3.00 | N/A | N/A |
| Model | Train 1M tokens | Store / month | Infer / unit-hr (no commit) |
|---|---|---|---|
| Llama 3.1 Instruct (8B) | $1.49 | $1.95 | $24.00 |
| Llama 3.1 Instruct (70B) | $7.99 | $1.95 | $24.00 |
| Model | No commit | 1-mo commit | 6-mo commit |
|---|---|---|---|
| Llama 3.1 Instruct (8B) | $24.00 | $21.18 | $13.08 |
| Llama 3.1 Instruct (70B) | $24.00 | $21.18 | $13.08 |
| Model | Input $/1M | Output $/1M |
|---|---|---|
| Llama 3 Instruct (8B) | 0.30 | 0.60 |
| Llama 3 Instruct (70B) | 2.65 | 3.50 |
| Model | Input $/1M | Output $/1M |
|---|---|---|
| Llama 2 Chat (13B) | 0.75 | 1.00 |
| Llama 2 Chat (70B) | 1.95 | 2.56 |
Fine-tuning: Llama 2 Pretrained (13B) $1.49 per 1M tokens trained, $1.95/month storage, $23.50/unit-hr no-commit infer; (70B) $7.99 / $1.95 / $23.50.
Provisioned throughput (per model unit-hour): 13B and 70B — $21.18 (1-mo commit), $13.08 (6-mo commit). Pretrained Llama 2 is provisioned throughput only after customization per AWS.
All figures from Amazon Bedrock pricing (opens in a new tab) (Amazon Nova sections). Nova pricing depends on inference deployment (e.g. Global cross-region vs Geo cross-region and in-region), tier (Standard, Priority, Flex, Batch), modality (text / image / video / audio), and AWS Region. The quick-reference table above uses Geo cross-region inference and in-region, Standard tier, US East (Ohio), text + image + video rates where a single input price applies to all three. Confirm the page before estimates.
Cache read (Nova): AWS states cache read input tokens are 75% below the on-demand input price for the applicable tier/modality.
Per 1M input / output tokens unless noted.
| Model | Input $/1M | Output $/1M |
|---|---|---|
| Amazon Nova 2 Lite | 0.33 | 2.75 |
| Amazon Nova Micro | 0.035 | 0.14 |
| Amazon Nova Lite | 0.06 | 0.24 |
| Amazon Nova Pro | 0.80 | 3.20 |
| Amazon Nova Pro (latency optimized inf.) | 1.00 | 4.00 |
| Amazon Nova Premier | 2.50 | 12.50 |
| Model | Input $/1M | Output $/1M |
|---|---|---|
| Amazon Nova 2 Lite | 0.30 | 2.50 |
Per 1M tokens. Nova 2 Omni and Nova 2 Pro are Preview. Image column is output image pricing where listed.
| Model | Text in | Image in | Video in | Audio in | Text out | Image out |
|---|---|---|---|---|---|---|
| Amazon Nova 2 Omni (Preview) | 0.30 | 0.30 | 0.30 | 1.10 | 2.80 | 44.00 |
| Amazon Nova 2 Pro (Preview) | 1.375 | 1.375 | 1.375 | 1.375 | 11.00 | N/A |
Global cross-region inference (Ohio), Standard uses different multimodal numbers on the same page — e.g. Nova 2 Omni (Preview) audio in $1.00, text out $2.50, image out $40.00 (text/image/video in $0.30 each). Use the Bedrock pricing page for the deployment you select.
| Tier | Input $/1M | Output $/1M |
|---|---|---|
| Standard | 0.30 | 2.50 |
| Priority | 0.525 | 4.375 |
| Flex | 0.15 | 1.25 |
| Batch | 0.15 | 1.25 |
| Tier | Input $/1M | Output $/1M |
|---|---|---|
| Standard | 0.33 | 2.75 |
| Priority | 0.5775 | 4.8125 |
| Flex | 0.165 | 1.375 |
| Batch | 0.1595 | 1.342 |
| Model | Input $/1M | Output $/1M |
|---|---|---|
| Amazon Nova 2 Lite | 0.1595 | 1.342 |
| Amazon Nova Micro | 0.0175 | 0.07 |
| Amazon Nova Lite | 0.03 | 0.12 |
| Amazon Nova Pro | 0.40 | 1.60 |
| Amazon Nova Premier | 1.25 | 6.25 |
| Model | Input $/1M | Cache read $/1M | Output $/1M |
|---|---|---|---|
| Amazon Nova 2.0 Lite | N/A | N/A | N/A |
| Amazon Nova Micro | 0.035 | N/A | 0.14 |
| Amazon Nova Lite | 0.06 | N/A | 0.24 |
| Amazon Nova Pro | 0.80 | N/A | 3.20 |
| Model | Price |
|---|---|
| Amazon Nova 2 Omni (Preview) | $30.00 per 1K requests |
| Amazon Nova 2 Pro (Preview) | $30.00 per 1K requests |
Lifecycle note: Nova Canvas v1 and Nova Reel v1 are excluded — both are Legacy with EOL 2026-09-30, inside the 90-day exclusion zone. Do not list them in recommendation or comparison tables. Rates are retained for users already on them. See
vendored/ai/ai-model-lifecycle.md.
Amazon Nova Canvas (on-demand, per image): up to 1024×1024 — Standard $0.04, Premium $0.06; up to 2048×2048 — Standard $0.06, Premium $0.08.
Model customization (Nova Canvas): $0.005 per image seen; $1.95/month per custom model stored; provisioned inference per model unit per hour (no commit / 1-mo / 6-mo) $60.50 / $55.00 / $30.25.
Amazon Nova Reel (video): 720p, 24 fps — $0.08 per second of video generated.
Lifecycle note: Nova Sonic v1 reached EOL on 2026-09-14 and its requests now fail. Rates are retained only to explain the migration to Nova 2 Sonic. See
vendored/ai/ai-model-lifecycle.md.
Per 1M tokens.
| Model | Modality | Input $/1M | Output $/1M | Status |
|---|---|---|---|---|
| Amazon Nova Sonic | Speech | 3.40 | 13.60 | EOL (2026-09-14) |
| Amazon Nova Sonic | Text | 0.06 | 0.24 | EOL (2026-09-14) |
| Amazon Nova 2 Sonic | Speech | 3.00 | 12.00 | active |
| Amazon Nova 2 Sonic | Text | 0.33 | 2.75 | active |
| Offering | Text $/1M | Std image / doc image / video sec / audio sec |
|---|---|---|
| Amazon Nova Multimodal Embeddings (On-demand) | 0.135 | $0.00006 / $0.0006 / $0.0007 / $0.00014 per unit |
| Amazon Nova Multimodal Embeddings (Batch) | 0.0675 | $0.00003 / $0.00048 / $0.00056 / $0.000112 |
On-demand inference for custom Nova models matches base Nova inference pricing per AWS.
Use alongside Bedrock pricing to calculate migration ROI.
Prices per 1M tokens. Source: ai.google.dev/gemini-api/docs/pricing (opens in a new tab), verified May 2026.
| Model | Input $/1M | Output $/1M | Context | Tier |
|---|---|---|---|---|
| Gemini 3.5 Flash | 1.50 | 9.00 | 1M | flagship |
| Gemini 3.1 Pro | 2.00 | 12.00 | 1M | flagship |
| Gemini 3.1 Flash-Lite | 0.25 | 1.50 | 1M | budget |
| Gemini 2.5 Pro | 1.25 | 10.00 | 1M | flagship |
| Gemini 2.5 Flash | 0.30 | 2.50 | 1M | fast |
| Gemini 2.0 Flash | 0.10 | 0.40 | 1M | fast |
| Gemini 2.0 Flash Lite | 0.075 | 0.30 | 1M | budget |
Gemini 3.1 Pro breakpoint pricing: $4.00/$18.00 per 1M for prompts >200k tokens (vs $2.00/$12.00 for ≤200k). Table above uses ≤200k rates. Gemini 3.5 Flash is now GA and the current flagship Flash model, replacing Gemini 2.5 Flash as the primary Flash-tier recommendation. At $1.50/$9.00 it is 5x more expensive than Gemini 2.5 Flash — the Bedrock cost savings case is significantly stronger against 3.5 Flash.
Prices per 1M tokens. GPT-5.5 and GPT-5.5 Pro use the same breakpoint pricing structure as GPT-5.4 at 272K input tokens. GPT-5.4 and GPT-5.4 Pro use breakpoint pricing at 272K input tokens: rates below are for <272K context; above 272K, input is 2x and output is 1.5x.
Tier note — these rows are OpenAI’s STANDARD tier. Bedrock in-region for the same models is priced at OpenAI’s data residency tier, exactly 1.10x the figures below (see the OpenAI on Bedrock section above). So for GPT-5.6 Sol / Terra / Luna, GPT-5.5 and GPT-5.4 a same-model move is a ~10% increase, not parity — compute it from the Bedrock table, not by assuming these numbers carry over. The rows below are the right source-side baseline for a customer on OpenAI standard, and remain the only figures available for models with no Bedrock equivalent (GPT-5.x Pro, GPT-5.2/5.1, GPT-4.x, o-series).
| Model | Input $/1M | Output $/1M | Context | Tier |
|---|---|---|---|---|
| GPT-5.6 Sol | unverified | unverified | 1M | frontier |
| GPT-5.6 Terra | unverified | unverified | 1M | flagship |
| GPT-5.6 Luna | 0.20 | 1.20 | 1M | fast |
| GPT-5.5 | 5.00 | 30.00 | 1M | flagship |
| GPT-5.5 Pro | 30.00 | 180.00 | 1M | premium |
| GPT-5.4 | 2.50 | 15.00 | 1.05M | flagship |
| GPT-5.4 Mini | 0.75 | 4.50 | — | fast |
| GPT-5.4 Nano | 0.20 | 1.25 | — | budget |
| GPT-5.4 Pro | 30.00 | 180.00 | 1.05M | premium |
| GPT-5.2 | 1.75 | 14.00 | 200K | flagship |
| GPT-5.1 | 1.25 | 10.00 | 200K | flagship |
| GPT-5 Mini | 0.25 | 2.00 | 200K | fast |
| GPT-5 Nano | 0.05 | 0.40 | 128K | budget |
| GPT-4.1 | 2.00 | 8.00 | 1M | flagship |
| GPT-4.1 Mini | 0.40 | 1.60 | 1M | fast |
| GPT-4.1 Nano | 0.10 | 0.40 | 1M | budget |
| GPT-4o | 2.50 | 10.00 | 128K | flagship |
| o3 | 2.00 | 8.00 | 200K | reasoning |
| o4-mini | 1.10 | 4.40 | 200K | reasoning |
Per-unit rates verified via AWS Pricing API for us-east-1 on 2026-05-04. Config pricing effective 2025-09-01; Security Hub pricing effective 2026-03-01. Re-verify if migrating to a non-us-east-1 region or if any of these services re-prices.
| Metric | Rate |
|---|---|
| Management events (first trail per region/type) | $0.00 |
| Management events (additional trails) | $2.00 per 100K events |
| Data events | $0.10 per 100K events (not used by Tier 1) |
| Metric | Rate | Notes |
|---|---|---|
| First 30 days | $0.00 | Free trial per account |
| CloudTrail event analysis | $4.00 per 1M events | First 500M/mo; scales down thereafter |
| VPC Flow Log / DNS analysis | $1.00 per GB | First 500 GB/mo |
| DNS query analysis | $1.00 per 1M queries | |
| Small-startup typical | ~$2–25/mo (typical $14/mo) | After free trial, with ~2M CloudTrail events/mo |
| Metric | Rate | Notes |
|---|---|---|
| Continuous configuration item | $0.003 per item | Records every change |
| Daily configuration item | $0.012 per daily item | Once-per-day snapshot; cheaper for slow-changing accounts, less signal |
| Small-startup typical (continuous) | ~$2–10/mo | 50–300 CIs/mo continuous |
| Source | AWS Pricing API, us-east-1, 2026-05-04 |
| Metric | Rate | Notes |
|---|---|---|
| First 30 days | $0.00 | Free trial per account |
| Security checks | $0.001 per check | First 100K checks/mo; tapers above |
| Per-EC2-hour monitoring | $0.0052083/hr | ~$3.80/mo per instance |
| Per-Lambda-function monitoring | $0.000434/hr | ~$0.32/mo per function |
| Per-container-image scanning | $0.0002894/hr | |
| Small-startup typical | ~$1–15/mo | After trial; Fargate-only startups pay nothing for the EC2 dimension |
| Source | AWS Pricing API, us-east-1, 2026-05-04 |
| Metric | Rate | Notes |
|---|---|---|
| First 2 budgets per account | $0.00 | Free tier |
| Additional budgets | $0.02 per budget per day | Tier 1 emits 1 budget, so effectively free |
This file