Amazon Bedrock
- Categories
- Hyperscaler AI platforms
- Owned by
- Amazon.com Inc. (NASDAQ: AMZN)
- HQ
- US
- Website
- https://aws.amazon.com/bedrock/
- Pricing page
- https://aws.amazon.com/bedrock/pricing/
- Fee model
- per_token+per_second_gpu
- Fees
- On-demand per-token (Standard tier). Priority tier = 75% premium, Flex tier = 50% discount to Standard (per pricing page; varies by model). Batch inference 50% lower than on-demand for select models. Reserved/Provisioned Throughput billed per model-unit-hour/TPM with term commitment. Custom Model Import billed per Custom Model Unit-minute ($0.05718/CMU-min us-east-1).
- Free tier
- no
- OpenAI-compatible API
- partial
- Notes
- Prices here = us-east-1 in-region Standard tier. For Claude 4.5+ / Nova 2 / Kimi K3 / Grok 4.6 the global cross-region inference profile is ~10% cheaper than in-region (noted per offer). OpenAI-compatible Chat Completions via bedrock-mantle endpoint for many open models; native Converse/InvokeModel otherwise. Third-party models (Claude, Cohere, AI21, Writer) billed via AWS Marketplace offer files.
- Sources
- https://aws.amazon.com/bedrock/pricing/ https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockService/current/us-east-1/index.json https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/us-east-1/index.json https://docs.aws.amazon.com/bedrock/latest/userguide/model-cards.md collected 2026-09-18
LLM prices (68 models, USD per 1M tokens)
| Model | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| Amazon Nova 2 Lite amazon.nova-2-lite-v1:0 |
$0.33 | $2.75 | $0.083 | 1M | ✓ src src2 |
| Amazon Nova 2 Pro | $1.38 | $11 | — | — | ✓ src |
| Amazon Nova Lite amazon.nova-lite-v1:0 |
$0.06 | $0.24 | $0.015 | 300k | ✓ src src2 |
| Amazon Nova Micro amazon.nova-micro-v1:0 |
$0.035 | $0.14 | $0.00875 | 128k | ✓ src src2 |
| Amazon Nova Premier amazon.nova-premier-v1:0 |
$2.50 | $12.50 | $0.625 | 1M | ✓ src src2 |
| Amazon Nova Pro amazon.nova-pro-v1:0 |
$0.80 | $3.20 | $0.20 | 300k | ✓ src src2 |
| Claude 3 Haiku anthropic.claude-3-haiku-20240307-v1:0 |
$0.25 | $1.25 | — | 200k | ✓ src src2 |
| Claude Fable 5 anthropic.claude-fable-5 |
$11 | $55 | $1.10 | 1M | ✓ src src2 |
| Claude Fable 5.1 anthropic.claude-fable-5-1 |
$11 | $55 | $0.275 | 1M | ✓ src src2 |
| Claude Haiku 4.5 us.anthropic.claude-haiku-4-5-20251001-v1:0 |
$1.10 | $5.50 | $0.11 | 200k | ✓ src src2 |
| Claude Mythos 5.1 anthropic.claude-mythos-5-1 |
$11 | $55 | $0.275 | 1M | ✓ src src2 |
| Claude Opus 4.1 anthropic.claude-opus-4-1-20250805-v1:0 |
$15 | $75 | $1.50 | 200k | ✓ src src2 |
| Claude Opus 4.5 anthropic.claude-opus-4-5-20251101-v1:0 |
$5.50 | $27.50 | $0.55 | 200k | ✓ src src2 |
| Claude Opus 4.6 anthropic.claude-opus-4-6-v1 |
$5.50 | $27.50 | $0.55 | 1M | ✓ src src2 |
| Claude Opus 4.7 anthropic.claude-opus-4-7 |
$5.50 | $27.50 | $0.55 | 1M | ✓ src src2 |
| Claude Opus 4.8 anthropic.claude-opus-4-8 |
$5.50 | $27.50 | $0.55 | 1M | ✓ src src2 |
| Claude Opus 5 anthropic.claude-opus-5 |
$5.50 | $27.50 | $0.55 | 1M | ✓ src src2 |
| Claude Sonnet 4 anthropic.claude-sonnet-4-20250514-v1:0 |
$3 | $15 | $0.30 | 200k | ✓ src src2 |
| Claude Sonnet 4.5 anthropic.claude-sonnet-4-5-20250929-v1:0 |
$3.30 | $16.50 | $0.33 | 200k | ✓ src src2 |
| Claude Sonnet 4.6 anthropic.claude-sonnet-4-6 |
$3.30 | $16.50 | $0.33 | 1M | ✓ src src2 |
| Claude Sonnet 5 us.anthropic.claude-sonnet-5 |
$2.20 | $11 | $0.22 | 1M | ✓ src src2 |
| Command R+ cohere.command-r-plus-v1:0 |
$3 | $15 | — | 128k | ✓ src src2 |
| DeepSeek R1 deepseek.r1-v1:0 |
$1.35 | $5.40 | — | 128k | ✓ src src2 |
| DeepSeek V3.1 deepseek.v3-v1:0 |
$0.58 | $1.68 | — | 128k | ✓ src src2 |
| DeepSeek V3.2 deepseek.v3.2 |
$0.62 | $1.85 | — | 164k | ✓ src src2 |
| Devstral 2 123B mistral.devstral-2-123b |
$0.40 | $2 | — | 256k | ✓ src src2 |
| Gemma 3 12B IT google.gemma-3-12b-it |
$0.09 | $0.29 | — | 128k | ✓ src src2 |
| Gemma 3 27B IT google.gemma-3-27b-it |
$0.23 | $0.38 | — | 128k | ✓ src src2 |
| Gemma 4 26B A4B google.gemma-4-26b-a4b |
$0.13 | $0.40 | — | 256k | ✓ src src2 |
| Gemma 4 31B google.gemma-4-31b |
$0.14 | $0.40 | — | 256k | ✓ src src2 |
| GLM 4.7 zai.glm-4.7 |
$0.60 | $2.20 | — | 203k | ✓ src src2 |
| GLM 4.7 Flash zai.glm-4.7-flash |
$0.07 | $0.40 | — | 203k | ✓ src src2 |
| GLM 5 zai.glm-5 |
$1 | $3.20 | — | 200k | ✓ src src2 |
| gpt-oss-120b openai.gpt-oss-120b-1:0 |
$0.15 | $0.60 | — | 128k | ✓ src src2 |
| gpt-oss-20b openai.gpt-oss-20b-1:0 |
$0.07 | $0.30 | — | 128k | ✓ src src2 |
| gpt-oss-safeguard-20b openai.gpt-oss-safeguard-20b |
$0.07 | $0.20 | — | 128k | ✓ src src2 |
| Grok 4.3 xai.grok-4.3 |
$1.25 | $2.50 | $0.20 | 1M | ✓ src src2 |
| Grok 4.6 xai.grok-4.6 |
$2.20 | $6.60 | $0.55 | 500k | ✓ src src2 |
| Jamba 1.5 Large ai21.jamba-1-5-large-v1:0 |
$2 | $8 | — | 256k | ✓ src src2 |
| Kimi K2 Thinking moonshot.kimi-k2-thinking |
$0.60 | $2.50 | — | 256k | ✓ src src2 |
| Kimi K2.5 moonshotai.kimi-k2.5 |
$0.60 | $3 | — | 256k | ✓ src src2 |
| Kimi K3 moonshotai.kimi-k3 |
$3.30 | $16.50 | $0.33 | 1M | ✓ src src2 |
| Llama 3.1 405B Instruct meta.llama3-1-405b-instruct-v1:0 |
— | — | — | 128k | ◐ src src2 |
| Llama 3.1 70B Instruct meta.llama3-1-70b-instruct-v1:0 |
$0.72 | $0.72 | — | 128k | ✓ src src2 |
| Llama 3.1 8B Instruct meta.llama3-1-8b-instruct-v1:0 |
$0.22 | $0.22 | — | 128k | ✓ src src2 |
| Llama 3.2 1B Instruct meta.llama3-2-1b-instruct-v1:0 |
$0.10 | $0.10 | — | 128k | ✓ src src2 |
| Llama 3.2 3B Instruct meta.llama3-2-3b-instruct-v1:0 |
$0.15 | $0.15 | — | 128k | ✓ src src2 |
| Llama 3.2 90B Vision Instruct meta.llama3-2-90b-instruct-v1:0 |
$0.72 | $0.72 | — | 128k | ✓ src src2 |
| Llama 3.3 70B Instruct meta.llama3-3-70b-instruct-v1:0 |
$0.72 | $0.72 | — | 128k | ✓ src src2 |
| Llama 4 Maverick 17B Instruct meta.llama4-maverick-17b-instruct-v1:0 |
$0.24 | $0.97 | — | 1M | ✓ src src2 |
| Llama 4 Scout 17B Instruct meta.llama4-scout-17b-instruct-v1:0 |
$0.17 | $0.66 | — | 10M | ✓ src src2 |
| MiniMax M2 minimax.minimax-m2 |
$0.30 | $1.20 | — | 1M | ✓ src src2 |
| MiniMax M2.1 minimax.minimax-m2.1 |
$0.30 | $1.20 | — | 196k | ✓ src src2 |
| MiniMax M2.5 minimax.minimax-m2.5 |
$0.30 | $1.20 | — | 196k | ✓ src src2 |
| Ministral 3 14B mistral.ministral-3-14b-instruct |
$0.20 | $0.20 | — | 128k | ✓ src src2 |
| Ministral 3 8B mistral.ministral-3-8b-instruct |
$0.15 | $0.15 | — | 128k | ✓ src src2 |
| Mistral Large 3 (675B) mistral.mistral-large-3-675b-instruct |
$0.50 | $1.50 | — | 256k | ✓ src src2 |
| Mixtral 8x7B Instruct mistral.mixtral-8x7b-instruct-v0:1 |
$0.45 | $0.70 | — | 32k | ✓ src src2 |
| Nemotron 3 Nano 30B nvidia.nemotron-nano-3-30b |
$0.06 | $0.24 | — | 256k | ✓ src src2 |
| Nemotron 3 Super 120B A12B nvidia.nemotron-super-3-120b |
$0.15 | $0.65 | — | 256k | ✓ src src2 |
| Palmyra X5 writer.palmyra-x5-v1:0 |
$0.60 | $6 | — | 128k | ✓ src src2 |
| Qwen3 235B A22B 2507 qwen.qwen3-235b-a22b-2507-v1:0 |
$0.22 | $0.88 | — | 256k | ✓ src src2 |
| Qwen3 32B qwen.qwen3-32b-v1:0 |
$0.15 | $0.60 | — | 32k | ✓ src src2 |
| Qwen3 Coder 30B A3B qwen.qwen3-coder-30b-a3b-v1:0 |
$0.15 | $0.60 | — | 256k | ✓ src src2 |
| Qwen3 Coder 480B A35B qwen.qwen3-coder-480b-a35b-v1:0 |
$0.45 | $1.80 | — | 128k | ✓ src src2 |
| Qwen3 Coder Next qwen.qwen3-coder-next |
$0.50 | $1.20 | — | 256k | ✓ src src2 |
| Qwen3 Next 80B A3B qwen.qwen3-next-80b-a3b |
$0.14 | $1.20 | — | 256k | ✓ src src2 |
| Qwen3 VL 235B A22B qwen.qwen3-vl-235b-a22b |
$0.53 | $2.66 | — | 256k | ✓ src src2 |