Anbieter · 2026-05-12
amazon-bedrock
| Modell | Eingabe / 1M | Ausgabe / 1M | Kontext | Hoster | Tags |
|---|---|---|---|---|---|
| Nova Micro | $0.035 | $0.140 | 128K | 1 | tools |
| Nova Lite | $0.060 | $0.240 | 300K | 1 | tools · vision |
| Nova 2 Lite | $0.330 | $2.75 | 128K | 1 | tools · vision |
| Nova Pro | $0.800 | $3.20 | 300K | 1 | tools · vision |
| Palmyra X5 | $0.600 | $6.00 | 1.04M | 1 | tools · reasoning |
| Palmyra X4 | $2.50 | $10.00 | 123K | 1 | tools · reasoning |
| Voxtral Mini 3B 2507Derivat | $0.040 | $0.040 | 128K | 1 | tools · json |
| Ministral 3 3BDerivat | $0.100 | $0.100 | 256K | 1 | tools · json · vision · open-weights |
| NVIDIA Nemotron Nano 3 30BDerivat | $0.060 | $0.240 | 128K | 1 | tools · reasoning · open-weights |
| Ministral 3 8BDerivat | $0.150 | $0.150 | 128K | 1 | tools · json |
| gpt-oss-20bDerivat | $0.070 | $0.300 | 128K | 1 | tools · json |
| Ministral 14B 3.0Derivat | $0.200 | $0.200 | 128K | 1 | tools · json |
| GPT OSS Safeguard 120BDerivat | $0.150 | $0.600 | 128K | 1 | tools · json |
| gpt-oss-120bDerivat | $0.150 | $0.600 | 128K | 1 | tools · json |
| NVIDIA Nemotron 3 Super 120B A12BDerivat | $0.150 | $0.650 | 262K | 1 | tools · reasoning · open-weights |
| NVIDIA Nemotron Nano 12B v2 VL BF16Derivat | $0.200 | $0.600 | 128K | 1 | tools · json · vision |
| Qwen3 235B A22B 2507Derivat | $0.220 | $0.880 | 262K | 1 | tools · json · open-weights |
| MiniMax M2Derivat | $0.300 | $1.20 | 205K | 1 | tools · reasoning · open-weights |
| MiniMax M2.5Derivat | $0.300 | $1.20 | 197K | 1 | tools · reasoning · open-weights |
| MiniMax M2.1Derivat | $0.300 | $1.20 | 205K | 1 | tools · reasoning · open-weights |
| Qwen/Qwen3-Next-80B-A3B-InstructDerivat | $0.140 | $1.40 | 262K | 1 | tools · json |
| Magistral Small 1.2Derivat | $0.500 | $1.50 | 128K | 1 | tools · json · reasoning · vision · open-weights |
| Mistral Large 3Derivat | $0.500 | $1.50 | 256K | 1 | tools · json · vision · open-weights |
| Qwen3 Coder 480B A35B InstructDerivat | $0.220 | $1.80 | 131K | 1 | tools · json · open-weights |
| Devstral 2 123BDerivat | $0.400 | $2.00 | 256K | 1 | tools · open-weights |
| DeepSeek-R1 (US)Derivat | $1.35 | $5.40 | 128K | 1 | tools · reasoning |
| Pixtral Large (25.02)Derivat | $2.00 | $6.00 | 128K | 1 | tools · vision |
Frequently asked questions
How many AI models does amazon-bedrock offer?
We track 6 canonical amazon-bedrock models plus 21 community fine-tunes / derivatives (excluded from the main table). The list is recomputed daily from models.dev.
Which amazon-bedrock model is the cheapest?
Nova Micro is currently the lowest-priced amazon-bedrock model, at $0.035 per 1M input tokens and $0.140 per 1M output tokens. For the full apples-to-apples list, see /pricing/cheapest-llm-api.
Which amazon-bedrock model has the largest context window?
Palmyra X5 leads at 1.04M tokens. This is the total of prompt + completion.
Which amazon-bedrock models support tool calling?
Multiple amazon-bedrock models support tool calling, with Nova Micro being a popular pick. The capability column in the table above marks every model with amazon-bedrock tool-calling support.
Which amazon-bedrock models accept image input?
Nova Lite accepts image input. Other vision-capable amazon-bedrock models are tagged 'vision' in the table above. See /capabilities/vision for a cross-vendor comparison.
What are the best alternatives to amazon-bedrock?
Depends on the use case. For raw cost savings, look at /pricing/cheapest-llm-api. For agent-oriented workloads, /best/best-ai-model-for-agents. For long-document workflows, /best/best-long-context-llm.
How fresh is this amazon-bedrock pricing data?
Daily. Our pipeline pulls models.dev each morning and rebuilds these pages on data change, so list-price moves and new model releases land within roughly 24 hours.
Explore more
Top amazon-bedrock models
- Nova Micro$0.04 in / $0.14 out
- Nova Lite$0.06 in / $0.24 out
- Nova 2 Lite$0.33 in / $2.75 out
- Nova Pro$0.80 in / $3.20 out
- Palmyra X5$0.60 in / $6.00 out
Browse by use case
Browse by capability
Zuletzt aktualisiert:
Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.
Data is sourced from models.dev and normalized for comparison. Prices and capabilities may change. Always verify critical production decisions with the provider's official documentation.