theserverless.dev InferenceList

Models

Showing 1–50 of 130 · Sorted by input price, low to high.

Cheaper elsewhere
More filters
Amazon Bedrock × Clear
Model Provider Modality Input ↑ Output Context
Nova 2.0 Lite Amazon Bedrock text $0/tokens cache write Not published— —
Nova 2.0 Lite Amazon Bedrock text $0/tokens cache write Not published— —
Nova Lite Amazon Bedrock text $0/tokens cache write Not published— —
Nova Lite Amazon Bedrock text $0/tokens cache write Not published— —
Nova Micro Amazon Bedrock text $0/tokens cache write Not published— —
Nova Micro Amazon Bedrock text $0/tokens cache write Not published— —
Nova Premier Amazon Bedrock text $0/tokens cache write Not published— —
Nova Pro Amazon Bedrock text $0/tokens cache write Not published— —
Nova Pro Amazon Bedrock text $0/tokens cache write Not published— —
Nova Micro Amazon Bedrock text $0.0088/tokens cache read Not published— —
Nova Micro Amazon Bedrock text $0.0088/tokens cache read Not published— —
Nova Lite Amazon Bedrock text $0.015/tokens cache read Not published— —
Nova Lite Amazon Bedrock text $0.015/tokens cache read Not published— —
TitanEmbeddingV2-Text Amazon Bedrock text $0.02/1M Not published— —
Nova Micro Amazon Bedrock text $0.035/1M $0.14/1M —
Nova Micro Amazon Bedrock text $0.035/1M Not published— —
Gemma 3 4B Amazon Bedrock text $0.04/1M $0.08/1M —
Gemma 3 4B Amazon Bedrock text $0.04/1M $0.08/1M —
google.gemma-4-e2b Amazon Bedrock text $0.04/1M $0.08/1M —
Voxtral Mini 1.0 Amazon Bedrock text $0.04/1M $0.04/1M —
Voxtral Mini 1.0 Amazon Bedrock text $0.04/1M $0.04/1M —
Nemotron Nano 3 30B Amazon Bedrock text $0.06/1M $0.24/1M —
Nemotron Nano 3 30B Amazon Bedrock text $0.06/1M $0.24/1M —
Nova Lite Amazon Bedrock text $0.06/1M $0.24/1M —
Nova Lite Amazon Bedrock text $0.06/1M Not published— —
Nova Sonic Amazon Bedrock text $0.06/1M $0.24/1M —
NVIDIA Nemotron Nano 2 Amazon Bedrock text $0.06/1M $0.23/1M —
NVIDIA Nemotron Nano 2 Amazon Bedrock text $0.06/1M $0.23/1M —
GLM 4.7 Flash Amazon Bedrock text $0.07/1M $0.4/1M —
GPT OSS Safeguard 20B Amazon Bedrock text $0.07/1M $0.2/1M —
GPT OSS Safeguard 20B Amazon Bedrock text $0.07/1M $0.2/1M —
gpt-oss-20b Amazon Bedrock text $0.07/1M $0.3/1M —
gpt-oss-20b Amazon Bedrock text $0.07/1M $0.3/1M —
Qwen3 Next 80B A3B Amazon Bedrock text $0.07/1M $0.6/1M —
Nova 2.0 Lite Amazon Bedrock text $0.075/tokens cache read Not published— —
Nova 2.0 Lite Amazon Bedrock text $0.0825/tokens cache read Not published— —
Gemma 3 12B Amazon Bedrock text $0.09/1M $0.29/1M —
Gemma 3 12B Amazon Bedrock text $0.09/1M $0.29/1M —
Llama 3.2 1B Amazon Bedrock text $0.1/1M $0.1/1M —
Ministral 3B 3.0 Amazon Bedrock text $0.1/1M $0.1/1M —
Ministral 3B 3.0 Amazon Bedrock text $0.1/1M $0.1/1M —
TitanEmbeddingsG1-Text Amazon Bedrock text $0.1/1M Not published— —
Voxtral Small 1.0 Amazon Bedrock text $0.1/1M $0.3/1M —
Voxtral Small 1.0 Amazon Bedrock text $0.1/1M $0.3/1M —
google.gemma-4-26b-a4b Amazon Bedrock text $0.13/1M $0.4/1M —
google.gemma-4-31b Amazon Bedrock text $0.14/1M $0.4/1M —
Qwen3 Next 80B A3B Amazon Bedrock text $0.14/1M $1.2/1M —
GPT OSS Safeguard 120B Amazon Bedrock text $0.15/1M $0.6/1M —
GPT OSS Safeguard 120B Amazon Bedrock text $0.15/1M $0.6/1M —
gpt-oss-120b Amazon Bedrock text $0.15/1M $0.6/1M —

Token rates are USD per 1M tokens. A dash means the source did not publish that amount. A zero is a real zero.