Alternatives
Best cheaper alternatives to Embedding up to 150M parameters
Looking for a cheaper or smarter replacement for Embedding up to 150M parameters by Fireworks AI? We compared every Embedding model with verifiable pricing on real input/output cost, context window, intelligence and modalities. 3 options are meaningfully cheaper.
Category: Embedding
pplx-embed-v1-0.6b50% CHEAPER
Perplexity
Same category
$0.004 in · $0 out / 1M Tokens 128K ctx 98%
Voyage 3.5 Lite16% CHEAPER
Voyage AI
Same category
$0.00002 in · $0.02 out / 1M Tokens 80%
Voyage 4 Lite16% CHEAPER
Voyage AI
Same category
$0.00002 in · $0.02 out / 1M Tokens 32K ctx 80%
Gemini Embedding 2
Google
More modalitiesSame category
$0.2 in · $0 out / 1M Tokens 98%
voyage-multimodal-3.5
Voyage AI
More modalitiesSame category
$0.12 in · $0.6 out / 1M Tokens + 1B Pixels 32K ctx 96%
Embed 4 Small Model Vault
Cohere
More modalitiesSame category
$4 in · $0 out / 1 Instance Hour 512K ctx 86%
pplx-embed-context-v1-0.6b
Perplexity
Same category
$0.008 in · $0 out / 1M Tokens 128K ctx 98%
rerank-2.5-lite
Voyage AI
Same category
$0.02 in · $0 out / 1M Tokens 32K ctx 98%
pplx-embed-v1-4b
Perplexity
Same category
$0.03 in · $0 out / 1M Tokens 128K ctx 98%
pplx-embed-context-v1-4b
Perplexity
Same category
$0.05 in · $0 out / 1M Tokens 128K ctx 98%
Marengo Embed Audio
TwelveLabs
Same category
$0.0083 in · $0 out / 1 Minute Audio 96%
Marengo Embed Video
TwelveLabs
Same category
$0.042 in · $0 out / 1 Minute Video 96%
Marengo Embed Text
TwelveLabs
Same category
$0.07 in · $0 out / 1000 Requests 96%
Marengo Embed Image
TwelveLabs
Same category
$0.1 in · $0 out / 1000 Requests 96%
Pplx Embed
Perplexity
Same category
$0.008 in · $0.008 out / 1M Tokens 128K ctx 80%
Rerank 2.5
Voyage AI
Same category
$0.00005 in · $0.05 out / 1M Tokens 32K ctx 80%
Rerank 2
Voyage AI
Same category
$0.00005 in · $0.05 out / 1M Tokens 32K ctx 80%
Voyage 3.5
Voyage AI
Same category
$0.00006 in · $0.06 out / 1M Tokens 80%
Costs are normalised to a blended 1M-token workload (or per-unit price for non-token models) using each model's latest verified pricing. Models with pricing under review are excluded from recommendations.