API pricing

AWS Bedrock Pricing

AWS Bedrock charges between $0.040 and $75.00 per 1 million output tokens, depending on the model. Voxtral Mini 3B 2507 is the cheapest at $0.040/1M output and $0.040/1M input; Claude Opus 4.1 (2025-08-05) is the most expensive at $75.00/1M output. The largest context window is 1.0M tokens (Claude 3.5 Sonnet (2024-06-20)). Prices are USD, current as of July 20, 2026.

Bedrock is a multi-vendor surface — Anthropic, Meta, Mistral, Cohere and Amazon Nova models all billed through AWS on-demand token pricing. Provisioned throughput is priced per model-unit-hour instead and is excluded from the on-demand rates below.

Last updated · synced weekly from the upstream model catalog

Cheapest input

$0.035/1M

Nova Micro

Cheapest output

$0.040/1M

Voxtral Mini 3B 2507

Longest context

1.0M

Claude 3.5 Sonnet (2024-06-20)

Models priced

99

Avg $7.93/1M output

Pricing by model

All prices in USD per 1 million tokens. Showing 80 of 99 priced models, cheapest first.

ModelInput / 1MOutput / 1MContext
Voxtral Mini 3B 2507$0.040$0.040128K
Gemma 3 4B It$0.040$0.080128K
Ministral 3 3B Instruct$0.100$0.100128K
Llama3 2 1B Instruct$0.130$0.130128K
Nova Micro$0.035$0.140128K
Ministral 3 8B Instruct$0.150$0.150128K
Llama3 2 3B Instruct$0.190$0.190128K
GPT Oss Safeguard 20B$0.070$0.200128K
Ministral 3 14B Instruct$0.200$0.200128K
Mistral 7B Instruct$0.150$0.20032K
Llama3 1 8B Instruct$0.220$0.220128K
Nemotron Nano 9B$0.060$0.230128K
Nemotron Nano 3 30B$0.060$0.240262K
Nova Lite$0.060$0.240300K
Gemma 3 12B It$0.090$0.290128K
GPT Oss 20B 1$0.070$0.300128K
Voxtral Small 24B 2507$0.100$0.300128K
Llama3 2 11B Instruct$0.350$0.350128K
Gemma 3 27B It$0.230$0.380128K
Glm 4.7 Flash$0.070$0.400200K
Jamba 1.5 Mini$0.200$0.400256K
Titan Text Lite$0.300$0.40042K
Command Light Text$0.300$0.6004K
GPT Oss 120B 1$0.150$0.600128K
GPT Oss Safeguard 120B$0.150$0.600128K
Llama3 8B Instruct$0.300$0.6008K
Nemotron Nano 12B$0.200$0.600128K
Qwen3 32B$0.150$0.600131K
Qwen3 Coder 30B A3b$0.150$0.600262K
Nemotron Super 3 120B$0.150$0.650256K
Llama4 Scout 17B Instruct$0.170$0.660128K
Jamba Instruct$0.500$0.70070K
Mixtral 8X7B Instruct$0.450$0.70032K
Llama3 3 70B Instruct$0.720$0.720128K
Qwen3 235B A22b 2507$0.220$0.880262K
Llama4 Maverick 17B Instruct$0.240$0.970128K
Llama3 1 70B Instruct$0.990$0.990128K
Llama2 13B Chat$0.750$1.004K
Minimax M2$0.300$1.20128K
Minimax M2.1$0.300$1.20196K
Minimax M2.5$0.300$1.201.0M
Qwen3 Coder Next$0.500$1.20262K
Qwen3 Next 80B A3b$0.150$1.20128K
Claude 3 Haiku (2024-03-07)$0.250$1.25200K
Command R$0.500$1.50128K
Magistral Small 2509$0.500$1.50128K
Mistral Large 3 675B Instruct$0.500$1.50128K
Titan Text Premier$0.500$1.5042K
V3$0.580$1.68164K
Titan Text Express$1.30$1.7042K
Qwen3 Coder 480B A35b$0.220$1.80262K
V3.2$0.620$1.85164K
Command Text$1.50$2.004K
Devstral 2 123B$0.400$2.00256K
Llama3 2 90B Instruct$2.00$2.00128K
Glm 4.7$0.600$2.20200K
Claude Instant$0.800$2.40100K
Kimi K2 Thinking$0.600$2.50128K
Nova 2 Lite$0.300$2.501.0M
Llama2 70B Chat$1.95$2.564K
Qwen3 VL 235B A22b$0.530$2.66128K
Kimi K2.5$0.600$3.00262K
Mistral Small 2402$1.00$3.0032K
Glm 5$1.00$3.20200K
Nova Pro$0.800$3.20300K
Llama3 70B Instruct$2.65$3.508K
Claude 3.5 Haiku (2024-10-22)$0.800$4.00200K
Claude Haiku 4.5 (2025-10-01)$1.00$5.00200K
R1$1.35$5.40128K
Palmyra X5$0.600$6.001.0M
Pixtral Large 2502$2.00$6.00128K
Jamba 1.5 Large$2.00$8.00256K
Mistral Large 2407$3.00$9.00128K
Claude Sonnet 5$2.00$10.001.0M
Palmyra X4$2.50$10.00128K
J2 Mid$12.50$12.508K
Nova Premier$2.50$12.501.0M
Claude 3 Sonnet (2024-02-29)$3.00$15.00200K
Claude 3.5 Sonnet (2024-06-20)$3.00$15.001.0M
Claude Opus 4.1 (2025-08-05)$15.00$75.00200K

Frequently asked questions

How much does AWS Bedrock cost per 1M tokens?

AWS Bedrock pricing ranges from $0.040 to $75.00 per 1 million output tokens across 99 models. Input tokens are cheaper than output on every model. Rates current as of July 20, 2026.

What is the cheapest AWS Bedrock model?

Voxtral Mini 3B 2507 is the cheapest AWS Bedrock model on output tokens at $0.040 per 1M, while Nova Micro is cheapest on input at $0.035 per 1M. Which wins for you depends on your input-to-output ratio.

What is the largest AWS Bedrock context window?

Claude 3.5 Sonnet (2024-06-20) has the largest context window in the AWS Bedrock catalog at 1.0M input tokens, with up to 4K output tokens per response.

How do I calculate my actual AWS Bedrock bill?

Multiply your input tokens by the input rate and your output tokens by the output rate, both per million, then add retries and any conversation history resent on each turn. Calcaas does this against your real usage pattern and shows the margin left at your price point.

Other providers

What will this actually cost you?

Per-token rates only tell you half the story. Calcaas multiplies them by your real usage — prompt size, response length, retries and conversation history — then shows the margin left at your price point.

Open the free cost calculator