Amazon BedrockStatusOperational Live status
LLMAPI discountUp to −25%
Models on LLMAPI25
From$0.06 / 1M blended
RegionsGlobal (AWS)
Best uptime (24h)100.00%
Verdict
Amazon Bedrock is AWS's managed service for accessing foundation models from Anthropic, Meta, Mistral, Amazon, and others behind one AWS-native API. Through LLMAPI you reach 12 Amazon Bedrock models on the same OpenAI-compatible endpoint as every other provider, so switching between them is a one-string change.
Good fit for
- Text Generation
- Vision / Image Understanding
- Multimodal (any-to-any)
- Best for High Volume Production
- Best Developer Experience
- Best Uptime & Reliability
Consider another provider for
- No code generation models in this catalog
- No image generation models in this catalog
- No video generation models in this catalog
- No video understanding models in this catalog
Key facts
Where a provider does not document something we say so rather than guess. Everything LLMAPI records about Amazon Bedrock, in one table.
Overview | |
| Provider | Amazon Bedrock |
| Website | aws.amazon.com |
| Best for | AWS-native teams needing many models behind one API |
| Models on LLMAPI | 25 |
| Popular models | Claude Fable 5.1, Claude Opus 5, Claude Opus 5.5, GPT-5.6 Luna, Claude Fable 5, Claude Opus 4.8 |
Access & routing | |
| API compatibility | OpenAI-compatible — /v1/chat/completions |
| Model ID prefix | amazon-bedrock/<model> |
| Regions | Global (AWS) |
| Fallback | Configurable — on 429 or 5xx the router switches to any other model or provider on your list |
| Billing | One invoice across every provider, with per-key spend limits |
| Volume discount | Eligible |
Performance (median across listed models) | |
| Blended price / 1M | $1.4 |
| Uptime (24h) | 99.99% (median across listed models) |
Modality | |
| Tags | |
Price & performance | |
| Tags | |
Deployment | |
| Tags | |
Industry | |
| Tags | |
Workflow | |
| Tags | |
Trust & safety | |
| Tags | |
Audience | |
| Tags | |
Privacy & data | |
| Inference location | Any supported AWS region you choose |
| Data residency | Data stays in the region you call |
| Default retention | Not stored by AWS for model improvement |
| Zero-data retention | Default Prompts and completions are not stored by the service |
| Training on API data | No Inputs are not used to train the base models |
| Human review | No |
Compliance & lifecycle | |
| Certifications | SOC · ISO 27001 · GDPR DPA · HIPAA eligible · FedRAMP |
| Deprecation notice | Not documented by the provider |
| Operational status | Operational Live status |
Prices and context from the OpenRouter public catalogue; uptime and output speed from OpenRouter provider endpoints; quality scores from LiveBench. Refreshed nightly — last updated 2026-09-29. — means no figure is published for that model.
Best Amazon Bedrock models
A quick view of how Amazon Bedrock 's 12 models compare on intelligence, output speed and price — so you can pick the right one for your use case.
Most intelligent
#1Amazon Nova Micro44
#2Amazon Nova Lite40
#3Titan Embeddings G136
#4Claude Haiku 4.534
Intelligence index · 12 models
Fastest
#1Claude Haiku 4.5459 t/s
#2Amazon Nova Pro432 t/s
#3Amazon Nova Premier417 t/s
#4Claude Opus 4.1393 t/s
Output tokens / second · 12 models
Lowest price
#1Claude Haiku 4.5$1.13
#2DeepSeek R1$1.17
#3Amazon Nova Pro$1.96
#4Amazon Nova Micro$2.28
Blended price per 1M tokens · 12 models
Compared with other hosts
How Amazon Bedrock sits against the rest of the catalog, using the same measurements shown on every provider page.
- Price. Median blended price of $3.87 per 1M tokens — 37% below the $6.13 median across all 50 providers in the catalog.
- Throughput. Median output speed of 360 tokens/s, 4% faster than the 348 tok/s catalog median.
- Catalog depth. 12 models listed, against a catalog average of 5 per provider.
- Integration. Identical to every other provider here — same endpoint, same SDK, same keys, so a switch costs one string change.
Median blended price per 1M tokens
lower is better| Amazon Bedrock | $3.87 | |
| DeepInfra | $3.88 | |
| Scaleway | $3.95 | |
| Modular | $3.96 | |
| Databricks | $4.19 | |
| Xiaomi | $3.24 |
Median output speed
higher is better| Amazon Bedrock | 360 tok/s | |
| DeepInfra | 363 tok/s | |
| Scaleway | 281 tok/s | |
| Modular | 900 tok/s | |
| Databricks | 214 tok/s | |
| Xiaomi | 416 tok/s |
Figures are medians across the models listed on each provider page and are refreshed with the catalog.
Models & pricing
Every Amazon Bedrock model reachable with your LLMAPI key. Click a column heading to sort.
| Model | API model name | Uptime 24h | Price / 1M | Context |
|---|---|---|---|---|
| Claude Fable 5.1 | claude-fable-5-1 | 99.94% | $ 20 | 1000 k |
| Claude Opus 5 | claude-opus-5 | 100.00% | $ 10 | 1000 k |
| Claude Opus 5.5 | claude-opus-5-5 | 99.90% | $ 8 | 1000 k |
| GPT-5.6 Luna | gpt-5.6-luna | 100.00% | $ 0.49 | 1050 k |
| Claude Fable 5 | claude-fable-5 | 100.00% | $ 20 | 1000 k |
| Claude Opus 4.8 | claude-opus-4-8 | 99.74% | $ 10 | 1000 k |
| Claude Opus 4.7 | claude-opus-4-7 | 99.87% | $ 10 | 1000 k |
| Claude Sonnet 4.6 | claude-sonnet-4-6 | 99.67% | $ 6 | 1000 k |
| Claude Opus 4.6 | claude-opus-4-6 | 99.65% | $ 10 | 1000 k |
| Amazon Nova 2 Lite | nova-2-lite | — | $ 0.07 | 1000 k |
| Claude Opus 4.5 | claude-opus-4-5-20251101 | 100.00% | $ 10 | 200 k |
| Claude Haiku 4.5 | claude-haiku-4-5 | 99.96% | $ 2 | 200 k |
| Claude Sonnet 4.5 | claude-sonnet-4-5 | 100.00% | $ 6 | 200 k |
| GPT OSS 120B | gpt-oss-120b | 99.98% | $ 0.26 | 131 k |
| GPT OSS 20B | gpt-oss-20b | 99.99% | $ 0.13 | 131 k |
| Claude Opus 4.1 | claude-opus-4-1-20250805 | 99.99% | $ 30 | 200 k |
| Qwen3 Coder Next | qwen3-coder-next | 99.98% | $ 0.25 | 262 k |
| MiniMax M2.5 | minimax-m2.5 | 99.99% | $ 0.52 | 205 k |
| Llama 4 Scout 17B Instruct | llama-4-scout-17b-instruct | — | $ 0.29 | 131 k |
| Llama 4 Maverick 17B Instruct | llama-4-maverick-17b-instruct | — | $ 0.42 | 1049 k |
| Amazon Nova Lite | nova-lite | — | $ 0.11 | 300 k |
| Amazon Nova Micro | nova-micro | — | $ 0.06 | 128 k |
| Amazon Nova Pro | nova-pro | — | $ 1.4 | 300 k |
| Llama 3.1 8B Instruct | llama-3.1-8b-instruct | 100.00% | $ 0.22 | 128 k |
| Llama 3.1 70B Instruct | llama-3.1-70b-instruct | 99.99% | $ 0.72 | 128 k |
Price is a blended per-1M-token figure; latency is time to first token and throughput is output tokens per second, measured on the LLMAPI edge.
Cost calculator
Pick a model, enter your traffic, and see the monthly bill at LLMAPI rates.
Estimates use the blended per-1M-token price shown in the table above. Word counts differ by language — Cyrillic and CJK text uses 2–3× more tokens per word.
Amazon Bedrock via LLMAPI
Same models, same features, one key. Prefix the model ID with amazon-bedrock/ and point your OpenAI client at our base URL.
# Python · OpenAI SDK from openai import OpenAI client = OpenAI( base_url="https://api.llmapi.ai/v1", api_key="LLMAPI_KEY", ) r = client.chat.completions.create( model="amazon-bedrock/claude-opus-4-1", messages=[{"role": "user", "content": "Hello"}], )
| Pricing | Eligible for LLMAPI volume discounts; billed on one invoice with every other provider. |
| Features | Full pass-through — tool calling, JSON schema, streaming, vision and reasoning behave exactly as on Amazon Bedrock’s own API. |
| Fallback | Configurable. On 429 or 5xx the router switches to any model or provider on your fallback list. |
| Regions | Global (AWS) |
| Your data | LLMAPI stores request metadata only — model, token counts, latency and status. No prompt or completion content. |
Capabilities & use cases
Each tag below is its own catalog page listing every provider that shares it.
Developer resources
Where to go next.
Join thousands of developers building on one API key
Every provider in the catalog, one key, one invoice.
Questions
How do I call Amazon Bedrock models through LLMAPI?
Point any OpenAI-compatible client at https://api.llmapi.ai/v1 and use the model ID amazon-bedrock/claude-opus-4-1. No other change is needed.
Does Amazon Bedrock cost more through LLMAPI?
No. This provider is eligible for LLMAPI volume discounts, so heavy usage lands below list price.
Which regions are used?
Global (AWS)
What happens if the provider returns an error?
On 429 or 5xx responses the router falls back to any other model or provider on your configured list, so requests keep succeeding.
How many Amazon Bedrock models are available?
12 at the moment, all listed in the models table above and updated as the provider ships new ones.
Related providers
Providers covering similar use cases.