theserverless.dev InferenceList

Models

Showing 1–17 of 17 · Sorted by input price, low to high.

Cheaper elsewhere
More filters
Meta × Clear
Model Provider Modality Input ↑ Output Context
Meta: Llama 3.2 1B Instruct
Cheaper on Novita (−71.6%)
 Meta text $0.027/1M $0.201/1M 60K
Meta: Llama 3.1 8B Instruct
Cheaper on DeepInfra (−56.5%)
 Meta text $0.05/1M $0.08/1M 131K
Meta: Llama 3.2 3B Instruct
Cheaper on Together (−50%)
 Meta text $0.05/1M $0.33/1M 131K
Meta: Llama 3.3 70B Instruct Meta text $0.1/1M $0.32/1M 131K
Meta: Llama 4 Scout
Cheaper on DeepInfra (−20%)
 Meta text image $0.1/1M $0.3/1M 1.3M
Meta: Muse Spark 1.2 Contributor Meta text image video $0.1/1M $0.2/1M 1.0M
Meta: Muse Spark 1.3 Contributor Meta text image video $0.1/1M $0.2/1M 1.0M
Meta: Llama Guard 4 12B
Cheaper on DeepInfra (−20%)
 Meta image text $0.18/1M $0.18/1M 164K
Meta: Llama 4 Maverick Meta text image $0.1875/1M $0.6525/1M 524K
Meta: Muse Glimmer 30B Meta text image $0.3/1M $1.2/1M 131K
Meta: Llama 3.1 70B Instruct Meta text $0.4/1M $0.4/1M 131K
Meta: Muse Spark 1.1 Meta text image video $1.25/1M $4.25/1M 1.0M
Meta: Muse Spark 1.2 Meta text image video $1.25/1M $4.25/1M 1.0M
Meta: Muse Spark 1.3 Meta text image video $1.25/1M $4.25/1M 1.0M
Meta: Muse Spark Open Meta text image video audio $1.25/1M $4.25/1M 1.0M
Meta: Muse Image Meta text image $2.395/1M Not published— 66K
Meta: Muse Wonder Meta text image video audio $4/1M $20/1M 1.0M

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