Amazon Bedrock LLM API pricing
Every model Amazon Bedrock serves, with its pricing per 1M tokens and the exact model ID to copy. Sorted cheapest input first, with models Amazon Bedrock lists no paid price for at the end. Listed prices from LiteLLM, OpenRouter and Vercel.
Models served
136
on this provider
Cheapest input
$0.035
per 1M tokens
Cheapest output
$0.04
per 1M tokens
Max context
10M
tokens
On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
| Model ID | |||||
|---|---|---|---|---|---|
| Nova Micro 1.0 | Amazon | 128K | $0.035 | $0.14 | amazon.nova-micro-v1:0 |
| Gemma 3 4B | 131K | $0.04 | $0.08 | google.gemma-3-4b-it | |
| Gemma 4 E2b | 128K | $0.04 | $0.08 | bedrock_mantle/google.gemma-4-e2b | |
| Voxtral Mini 3B 2507 | Mistral | 33K | $0.04 | $0.04 | mistral.voxtral-mini-3b-2507 |
| Nova Lite 1.0 | Amazon | 300K | $0.06 | $0.24 | amazon.nova-lite-v1:0 |
| Nvidia Nemotron Nano 3 30B | NVIDIA | 262K | $0.06 | $0.24 | nvidia.nemotron-nano-3-30b |
| Nvidia Nemotron Nano 9B V2 | NVIDIA | 131K | $0.06 | $0.23 | nvidia.nemotron-nano-9b-v2 |
| GLM 4.7 Flash | Zhipu | 203K | $0.07 | $0.40 | zai.glm-4.7-flash |
| GPT OSS 20B 1 | OpenAI | 128K | $0.07 | $0.30 | openai.gpt-oss-20b-1:0 |
| gpt-oss-20b | OpenAI | 131K | $0.07 | $0.30 | bedrock_mantle/openai.gpt-oss-20b |
| gpt-oss-safeguard-20b | OpenAI | 131K | $0.07 | $0.20 | bedrock_mantle/openai.gpt-oss-safeguard-20b |
| Gemma 3 12B | 131K | $0.09 | $0.29 | google.gemma-3-12b-it | |
| Claude Haiku 5.5 | Anthropic | 1M | $0.10 | $0.50 | anthropic.claude-haiku-5-5 |
| GPT-6 Luna | OpenAI | 1.1M | $0.10 | $0.50 | global.openai.gpt-6-luna |
| Llama 3.2 1B Instruct | Meta | 131K | $0.10 | $0.10 | meta.llama3-2-1b-instruct-v1:0 |
| Ministral 3 3B Instruct | Mistral | 128K | $0.10 | $0.10 | mistral.ministral-3-3b-instruct |
| Voxtral Small 24B 2507 | Mistral | 33K | $0.10 | $0.30 | mistral.voxtral-small-24b-2507 |
| Gemma 4 26B A4b | 256K | $0.13 | $0.40 | bedrock_mantle/google.gemma-4-26b-a4b | |
| Gemma 4 31B | 256K | $0.14 | $0.40 | bedrock_mantle/google.gemma-4-31b | |
| Qwen3 Next 80B A3B Instruct | Alibaba | 262K | $0.14 | $1.20 | bedrock_mantle/qwen.qwen3-next-80b-a3b-instruct |
| GPT OSS 120B 1 | OpenAI | 128K | $0.15 | $0.60 | openai.gpt-oss-120b-1:0 |
| GPT OSS Safeguard 120B | OpenAI | 131K | $0.15 | $0.60 | bedrock_mantle/openai.gpt-oss-safeguard-120b |
| gpt-oss-120b | OpenAI | 131K | $0.15 | $0.60 | bedrock_mantle/openai.gpt-oss-120b |
| Llama 3.2 3B Instruct | Meta | 131K | $0.15 | $0.15 | meta.llama3-2-3b-instruct-v1:0 |
| Ministral 3 8B Instruct | Mistral | 128K | $0.15 | $0.15 | mistral.ministral-3-8b-instruct |
| Mistral 7B Instruct V0.2 | Mistral | 33K | $0.15 | $0.20 | bedrock/us-east-1/mistral.mistral-7b-instruct-v0:2 |
| Nvidia Nemotron Super 3 120B | NVIDIA | 256K | $0.15 | $0.65 | nvidia.nemotron-super-3-120b |
| Palmyra Vision 7B | 4K | $0.15 | $0.60 | writer.palmyra-vision-7b | |
| Qwen3 32B | Alibaba | 131K | $0.15 | $0.60 | bedrock_mantle/qwen.qwen3-32b |
| Qwen3 Coder 30B A3b | Alibaba | 262K | $0.15 | $0.60 | qwen.qwen3-coder-30b-a3b-v1:0 |
| Qwen3 Coder 30B A3B Instruct | Alibaba | 262K | $0.15 | $0.60 | bedrock_mantle/qwen.qwen3-coder-30b-a3b-instruct |
| Qwen3 Next 80B A3b | Alibaba | 262K | $0.15 | $1.20 | qwen.qwen3-next-80b-a3b |
| Titan Text Lite | Amazon | 42K | $0.15 | $0.20 | amazon.titan-text-lite-v1 |
| Llama 3.2 11B Instruct | Meta | 128K | $0.16 | $0.16 | meta.llama3-2-11b-instruct-v1:0 |
| Llama 4 Scout 17B Instruct | Meta | 10M | $0.17 | $0.66 | meta.llama4-scout-17b-instruct-v1:0 |
| GPT-5.6 Luna | OpenAI | 1.1M | $0.20 | $1.20 | global.openai.gpt-5.6-luna |
| Jamba 1.5 Mini | AI21 | 256K | $0.20 | $0.40 | ai21.jamba-1-5-mini-v1:0 |
| Ministral 3 14B Instruct | Mistral | 128K | $0.20 | $0.20 | mistral.ministral-3-14b-instruct |
| Nvidia Nemotron Nano 12B V2 | NVIDIA | 128K | $0.20 | $0.60 | nvidia.nemotron-nano-12b-v2 |
| Titan Text Express | Amazon | 42K | $0.20 | $0.60 | amazon.titan-text-express-v1 |
| Llama 3.1 8B Instruct | Meta | 200K | $0.22 | $0.22 | meta.llama3-1-8b-instruct-v1:0 |
| Qwen3 235B A22B Instruct 2507 | Alibaba | 262K | $0.22 | $0.88 | bedrock_mantle/qwen.qwen3-235b-a22b-2507 |
| Gemma 3 27B | 131K | $0.23 | $0.38 | google.gemma-3-27b-it | |
| Llama 4 Maverick 17B Instruct | Meta | 1M | $0.24 | $0.97 | meta.llama4-maverick-17b-instruct-v1:0 |
| Claude 3 Haiku (2024-03-07) | Anthropic | 200K | $0.25 | $1.25 | anthropic.claude-3-haiku-20240307-v1:0 |
| Command Light Text | Cohere | 4K | $0.30 | $0.60 | cohere.command-light-text-v14 |
| Llama 3 8B Instruct | Meta | 8K | $0.30 | $0.60 | bedrock/us-east-1/meta.llama3-8b-instruct-v1:0 |
| MiniMax M2 | MiniMax | 1M | $0.30 | $1.20 | minimax.minimax-m2 |
| MiniMax M2.1 | MiniMax | 1M | $0.30 | $1.20 | bedrock/us-east-1/minimax.minimax-m2.1 |
| MiniMax M2.5 | MiniMax | 1M | $0.30 | $1.20 | bedrock/us-east-1/minimax.minimax-m2.5 |
1–50 of 136
Page 1 of 3
Listed prices from LiteLLM, OpenRouter and Vercel · catalogue refreshed Oct 14, 2026 · 4 prices older, back to Sep 22, 2026
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI