Bedrock models and providers
Bedrock exposes seven model families from six providers — Anthropic, Meta, Mistral AI, Cohere, AI21 Labs, Amazon (Nova + Titan), and Stability AI — plus a few smaller embedding-and-rerank-only models from Cohere and Titan. This note is the canonical lookup for model IDs, on-demand pricing (USD / MTok in us-east-1 unless noted), context windows, and regional availability. Bedrock also exposes inference profiles — both system-defined cross-region profiles (route invocations across multiple regions for higher quota and failover) and application inference profiles (user-defined wrappers for cost tagging) — which change the model ID you actually call from your code.
See also
- bedrock-api-and-converse — how to call any model via the unified Converse API
- hidden-tricks-and-gotchas-aws-bedrock — cross-region inference profile quota tricks, provisioned-vs-on-demand crossover math
- claude-models-and-capabilities — the canonical Claude family reference (Bedrock IDs differ slightly from native Anthropic IDs)
- inference-optimization — what the serving layer is doing under the hood
1. Anthropic Claude (the most-used family on Bedrock)
Per docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html and Anthropic’s Bedrock-specific docs.
| Feature | Claude Opus 4.7 | Claude Sonnet 4.6 | Claude Haiku 4.5 | Claude Haiku 3.5 (legacy) |
|---|---|---|---|---|
| Bedrock model ID | anthropic.claude-opus-4-7-20260420-v1:0 | anthropic.claude-sonnet-4-6-20260119-v1:0 | anthropic.claude-haiku-4-5-20251001-v1:0 | anthropic.claude-3-5-haiku-20241022-v1:0 |
| Cross-region profile ID (US) | us.anthropic.claude-opus-4-7-20260420-v1:0 | us.anthropic.claude-sonnet-4-6-20260119-v1:0 | us.anthropic.claude-haiku-4-5-20251001-v1:0 | us.anthropic.claude-3-5-haiku-20241022-v1:0 |
| Input price | $5 / MTok | $3 / MTok | $1 / MTok | $0.80 / MTok |
| Output price | $25 / MTok | $15 / MTok | $5 / MTok | $4 / MTok |
| Cache-write price (5 min) | $6.25 / MTok | $3.75 / MTok | $1.25 / MTok | $1 / MTok |
| Cache-read price | $0.50 / MTok | $0.30 / MTok | $0.10 / MTok | $0.08 / MTok |
| Context window | 1,000,000 tokens | 1,000,000 tokens | 200,000 tokens | 200,000 tokens |
| Max output (sync) | 128k tokens | 64k tokens | 64k tokens | 8k tokens |
| Vision | Yes | Yes | Yes | No |
| Tool use (Converse) | Yes | Yes | Yes | Yes |
| Extended thinking | Adaptive only | Yes | Yes | No |
| Prompt caching | Yes (cachePoint block) | Yes | Yes | Yes |
| Regions | us-east-1/2, us-west-2, eu-central-1, eu-west-1/3, ap-northeast-1, ap-southeast-1/2 | Same | Same | Same |
Pricing note: Bedrock matches Anthropic’s published prices to the dollar — there is no Bedrock markup on per-token pricing for Claude models. Where Bedrock charges extra is when you turn on Guardrails (\$0.15 / 1k text units), Knowledge Base reranking (\$1 / 1k queries with Cohere Rerank 3), or Agent intelligent prompt routing (\$1 / 1k requests).
Sonnet 4.5 (still available) — anthropic.claude-sonnet-4-5-20250929-v1:0 at the same pricing as Sonnet 4.6. Migrate before the inevitable deprecation.
Opus 4.5 (still available) — anthropic.claude-opus-4-5-20251101-v1:0 at \$5 / \$25. Equivalent to 4.7 on most non-coding tasks.
2. Meta Llama
Per aws.amazon.com/bedrock/llama/. Llama 4 ships in three sizes — Scout (17B active / 109B total MoE), Maverick (17B active / 400B total MoE), Behemoth (preview, 288B active). Llama 3.x is still actively maintained.
| Model | Bedrock ID | Input / Output (USD/MTok) | Context |
|---|---|---|---|
| Llama 4 Maverick 17B Instruct | meta.llama4-maverick-17b-instruct-v1:0 | $0.24 / $0.97 | 1,000,000 |
| Llama 4 Scout 17B Instruct | meta.llama4-scout-17b-instruct-v1:0 | $0.17 / $0.66 | 10,000,000 |
| Llama 3.3 70B Instruct | meta.llama3-3-70b-instruct-v1:0 | $0.72 / $0.72 | 128,000 |
| Llama 3.2 90B Instruct (vision) | meta.llama3-2-90b-instruct-v1:0 | $2 / $2 | 128,000 |
| Llama 3.2 11B Instruct (vision) | meta.llama3-2-11b-instruct-v1:0 | $0.16 / $0.16 | 128,000 |
| Llama 3.2 3B Instruct | meta.llama3-2-3b-instruct-v1:0 | $0.15 / $0.15 | 128,000 |
| Llama 3.2 1B Instruct | meta.llama3-2-1b-instruct-v1:0 | $0.10 / $0.10 | 128,000 |
| Llama 3.1 405B Instruct | meta.llama3-1-405b-instruct-v1:0 | $5.32 / $16 | 128,000 |
| Llama 3.1 70B Instruct | meta.llama3-1-70b-instruct-v1:0 | $0.72 / $0.72 | 128,000 |
| Llama 3.1 8B Instruct | meta.llama3-1-8b-instruct-v1:0 | $0.22 / $0.22 | 128,000 |
Tool use: All Llama 3.1+ models support tool use via Converse API — the runtime injects Meta’s tool-call template behind the scenes.
Scout’s 10M context is on paper; in practice quality degrades past ~1M tokens. Use cross-region inference profiles to access Scout — it’s only available via profile ID us.meta.llama4-scout-17b-instruct-v1:0 (no direct on-demand in single regions).
3. Mistral AI
Per aws.amazon.com/bedrock/mistral/.
| Model | Bedrock ID | Input / Output (USD/MTok) | Context |
|---|---|---|---|
| Mistral Large 2 (24.11) | mistral.mistral-large-2411-v1:0 | $2 / $6 | 128,000 |
| Mistral Large (24.02) | mistral.mistral-large-2402-v1:0 | $4 / $12 | 32,000 |
| Mistral Small (24.02) | mistral.mistral-small-2402-v1:0 | $1 / $3 | 32,000 |
| Mistral 7B Instruct | mistral.mistral-7b-instruct-v0:2 | $0.15 / $0.20 | 32,000 |
| Mixtral 8x7B Instruct | mistral.mixtral-8x7b-instruct-v0:1 | $0.45 / $0.70 | 32,000 |
| Pixtral Large (image+text) | mistral.pixtral-large-2502-v1:0 | $2 / $6 | 128,000 |
Mistral Large 2 is the pick for the family — same intelligence-tier as Llama 3.3 70B but with stronger structured output and tool use.
4. Cohere
Per aws.amazon.com/bedrock/cohere/.
| Model | Bedrock ID | Input / Output (USD/MTok) | Context |
|---|---|---|---|
| Command R+ (08-2024) | cohere.command-r-plus-v1:0 | $2.50 / $10 | 128,000 |
| Command R (08-2024) | cohere.command-r-v1:0 | $0.15 / $0.60 | 128,000 |
| Command (legacy) | cohere.command-text-v14 | $1.50 / $2 | 4,096 |
| Embed English v3 | cohere.embed-english-v3 | $0.10 / MTok (input only) | 512 |
| Embed Multilingual v3 | cohere.embed-multilingual-v3 | $0.10 / MTok (input only) | 512 |
| Rerank 3.5 (reranker) | cohere.rerank-v3-5:0 | $1 / 1k queries | 4,096 docs/query |
Command R+ is the RAG-purpose-built generation model — it has native citation support in its output schema, which downstream tools can parse. Rerank 3.5 is the only non-OpenSearch reranker available inside Bedrock Knowledge Bases (per the Knowledge Bases docs).
5. AI21 Labs
| Model | Bedrock ID | Input / Output (USD/MTok) | Context |
|---|---|---|---|
| Jamba 1.5 Large | ai21.jamba-1-5-large-v1:0 | $2 / $8 | 256,000 |
| Jamba 1.5 Mini | ai21.jamba-1-5-mini-v1:0 | $0.20 / $0.40 | 256,000 |
| Jamba Instruct (legacy) | ai21.jamba-instruct-v1:0 | $0.50 / $0.70 | 256,000 |
Jamba is a hybrid Transformer–Mamba architecture, which gives it ~3× the throughput of pure-transformer models at the same parameter count for very long contexts. Useful for “extract structured data from this 200-page contract” workloads where you need the throughput.
6. Amazon Nova
Amazon’s own foundation models, released at re:Invent 2024 and refreshed at re:Invent 2025. Per docs.aws.amazon.com/nova/.
| Model | Bedrock ID | Input / Output (USD/MTok) | Context | Modalities |
|---|---|---|---|---|
| Nova Premier | amazon.nova-premier-v1:0 | $2.50 / $12.50 | 1,000,000 | Text + image + video → text |
| Nova Pro | amazon.nova-pro-v1:0 | $0.80 / $3.20 | 300,000 | Text + image + video → text |
| Nova Lite | amazon.nova-lite-v1:0 | $0.06 / $0.24 | 300,000 | Text + image + video → text |
| Nova Micro | amazon.nova-micro-v1:0 | $0.035 / $0.14 | 128,000 | Text → text |
| Nova Canvas (image generation) | amazon.nova-canvas-v1:0 | $0.04–$0.08 / image | 1024 prompt tokens | Text → image |
| Nova Reel (video generation) | amazon.nova-reel-v1:0 | $0.08 / second of video | 1024 prompt tokens | Text + image → video (6s) |
| Nova Sonic (real-time speech) | amazon.nova-sonic-v1:0 | $0.0034 / 1k speech tokens in, $0.0136 / 1k speech tokens out | Streaming | Speech ↔ speech |
Nova Micro at $0.035/MTok is the cheapest competitive LLM on Bedrock — useful for high-throughput classification, summarization, or as a draft-generator in a draft-and-review pipeline with Sonnet or Opus reviewing.
Nova Pro and Premier both handle video natively — pass an mp4 block in Converse and the model can answer questions about its content. No other Bedrock model does this (except Pixtral Large for image-only inputs).
7. Amazon Titan (legacy, embeddings-focused)
Most Titan generation models are deprecated (or pinned at low quality compared to Nova / Llama). The embedding models are still actively used.
| Model | Bedrock ID | Price | Use |
|---|---|---|---|
| Titan Text Embeddings V2 | amazon.titan-embed-text-v2:0 | $0.02 / MTok | 1024-dim embeddings, default for Knowledge Bases |
| Titan Text Embeddings V1 | amazon.titan-embed-text-v1 | $0.10 / MTok | 1536-dim, legacy |
| Titan Multimodal Embeddings G1 | amazon.titan-embed-image-v1 | $0.06 / MTok + $0.00006 / image | 1024-dim, image+text |
| Titan Image Generator G1 | amazon.titan-image-generator-v1 | $0.008–$0.10 / image | Superseded by Nova Canvas |
| Titan Text Lite / Express | amazon.titan-text-*-v1 | $0.15–$1.30 / MTok | Superseded by Nova |
8. Stability AI
| Model | Bedrock ID | Price | Notes |
|---|---|---|---|
| Stable Diffusion 3.5 Large | stability.sd3-5-large-v1:0 | $0.08 / image | Premium quality |
| Stable Diffusion 3.5 Medium | stability.sd3-5-medium-v1:0 | $0.04 / image | Default |
| Stable Image Ultra | stability.stable-image-ultra-v1:0 | $0.14 / image | Photorealistic |
| Stable Image Core | stability.stable-image-core-v1:0 | $0.03 / image | Cheap |
| Stable Diffusion XL (legacy) | stability.stable-diffusion-xl-v1 | $0.04–$0.08 / image | Legacy |
9. Regional availability matrix (top models, 2026-05)
Per docs.aws.amazon.com/bedrock/latest/userguide/models-regions.html. Most models launch in us-east-1 + us-west-2 first, with EU and APAC following 1–3 months later.
| Model | us-east-1 | us-west-2 | eu-central-1 | eu-west-3 | ap-northeast-1 | ap-southeast-2 |
|---|---|---|---|---|---|---|
| Claude Opus 4.7 | Yes | Yes | Yes | Yes | Yes | Yes |
| Claude Sonnet 4.6 | Yes | Yes | Yes | Yes | Yes | Yes |
| Claude Haiku 4.5 | Yes | Yes | Yes | Yes | Yes | Yes |
| Llama 4 Maverick | Profile-only | Profile-only | Profile-only | No | No | No |
| Llama 3.3 70B | Yes | Yes | Yes | Yes | No | Yes |
| Mistral Large 2 | Yes | Yes | Yes | No | No | No |
| Cohere Command R+ | Yes | Yes | Yes | No | No | Yes |
| Nova Pro | Yes | Yes | Yes | Yes | Yes | Yes |
| Nova Lite | Yes | Yes | Yes | Yes | Yes | Yes |
| Nova Micro | Yes | Yes | Yes | Yes | Yes | Yes |
When a model is “profile-only”, it means you must use a cross-region inference profile (e.g. us.meta.llama4-maverick-17b-instruct-v1:0) — the on-demand single-region invocation will return ValidationException.
10. Inference profiles — what changes vs raw model IDs
Per docs.aws.amazon.com/bedrock/latest/userguide/inference-profiles.html.
Two kinds:
-
System-defined cross-region profiles (created by AWS): IDs like
us.anthropic.claude-sonnet-4-6-20260119-v1:0,eu.anthropic.claude-sonnet-4-6-20260119-v1:0,apac.amazon.nova-pro-v1:0. Routes requests across multiple regions in that geography for higher throughput + automatic failover. Quota is the union of underlying regions — e.g.us.Claude profiles aggregate the per-region quotas of us-east-1, us-east-2, us-west-2, and us-east-2. -
Application inference profiles (user-defined): wraps a foundation-model or system-defined profile ARN with custom tags. The ARN looks like
arn:aws:bedrock:us-east-1:123456789012:application-inference-profile/abc123. Use them for cost tagging — every invocation through the profile carries the tag, so you can break down spend by application, team, or environment in Cost Explorer.
import boto3
bedrock = boto3.client("bedrock", region_name="us-east-1")
runtime = boto3.client("bedrock-runtime", region_name="us-east-1")
# Create an application inference profile that wraps a cross-region profile
resp = bedrock.create_inference_profile(
inferenceProfileName="prod-customer-chat",
description="Production customer-chat workload",
modelSource={
"copyFrom": "arn:aws:bedrock:us-east-1::inference-profile/us.anthropic.claude-sonnet-4-6-20260119-v1:0"
},
tags=[
{"key": "Environment", "value": "production"},
{"key": "Application", "value": "customer-chat"},
{"key": "CostCenter", "value": "CS-1234"},
],
)
profile_arn = resp["inferenceProfileArn"]
# Invoke through the profile — looks the same as invoking a model
response = runtime.converse(
modelId=profile_arn, # the ARN replaces the model ID
messages=[{"role": "user", "content": [{"text": "Hello!"}]}],
)The same pattern in TypeScript:
import {
BedrockRuntimeClient,
ConverseCommand,
} from "@aws-sdk/client-bedrock-runtime";
const client = new BedrockRuntimeClient({ region: "us-east-1" });
const response = await client.send(
new ConverseCommand({
modelId: "arn:aws:bedrock:us-east-1:123456789012:application-inference-profile/abc123",
messages: [{ role: "user", content: [{ text: "Hello!" }] }],
}),
);11. Service tiers — Standard, Flex, Priority, Reserved
Per docs.aws.amazon.com/bedrock/latest/userguide/service-tiers-inference.html.
| Tier | Pricing modifier | SLA / latency | Use |
|---|---|---|---|
| Standard (default) | 1× base | Best-effort | Default. Single per-request invocations. |
| Flex | 0.5× base (50% discount) | Best-effort, may queue minutes | Asynchronous / batchable work where latency doesn’t matter. |
| Priority | 1.75× base (75% premium) | Lower TTFT, guaranteed throughput | Latency-sensitive production (real-time chat). |
| Reserved (Provisioned Throughput) | Hourly fixed price per model unit | Guaranteed dedicated capacity | High-volume steady-state workloads where dedicated capacity wins on $/token. |
Specify with the serviceTier field on the Converse request:
response = runtime.converse(
modelId="anthropic.claude-sonnet-4-6-20260119-v1:0",
messages=[...],
serviceTier={"type": "flex"}, # or "priority", "default", "reserved"
)Provisioned Throughput pricing for Claude Sonnet 4.6 is ~$50/hour per “model unit” (1 MU = ~5k tokens/sec sustained). The breakeven vs on-demand at 100% utilization is around ~60 GTok/month of sustained throughput. Below that, on-demand wins.
12. Selection heuristics
- Pure coding agent — Claude Sonnet 4.6 or Opus 4.7. Nothing else on Bedrock competes on agentic coding quality.
- High-throughput classification / extraction — Nova Micro ($0.035 / MTok) or Llama 3.2 3B Instruct ($0.15 / MTok). Use Cohere Embed V3 for embeddings.
- Long-context document analysis — Llama 4 Scout (10M context, $0.17 / MTok input) or Claude Sonnet 4.6 (1M, $3 / MTok) depending on whether you need the deeper reasoning.
- RAG — Cohere Command R+ + Cohere Embed V3 + Cohere Rerank 3.5 if you want a coherent stack from one provider; or Sonnet/Haiku + Titan Embeddings V2 if you want AWS-native.
- Image generation — Nova Canvas ($0.04/image) is the default; Stability Stable Image Ultra ($0.14/image) for photorealism.
- Real-time speech — Nova Sonic is the only Bedrock option for bidirectional speech-to-speech.