Alternatives
Best cheaper alternatives to Codestral Embed
Looking for a cheaper or smarter replacement for Codestral Embed by Mistral AI? We compared every Embedding model with verifiable pricing on real input/output cost, context window, intelligence and modalities. 18 options are meaningfully cheaper.
Category: Embedding
pplx-embed-v1-0.6b98% CHEAPER
Perplexity
Same category
$0.004 in · $0 out / 1M Tokens 128K ctx 98%
pplx-embed-context-v1-0.6b96% CHEAPER
Perplexity
Same category
$0.008 in · $0 out / 1M Tokens 128K ctx 98%
Embedding up to 150M parameters96% CHEAPER
Fireworks AI
Same category
$0.008 in · $0 out / 1M Tokens 96%
Marengo Embed Audio94% CHEAPER
TwelveLabs
Same category
$0.0083 in · $0 out / 1 Minute Audio 96%
Voyage 3.5 Lite96% CHEAPER
Voyage AI
Same category
$0.00002 in · $0.02 out / 1M Tokens 80%
Voyage 4 Lite96% CHEAPER
Voyage AI
Same category
$0.00002 in · $0.02 out / 1M Tokens 32K ctx 80%
Pplx Embed94% CHEAPER
Perplexity
Same category
$0.008 in · $0.008 out / 1M Tokens 128K ctx 80%
Rerank 2.591% CHEAPER
Voyage AI
Same category
$0.00005 in · $0.05 out / 1M Tokens 32K ctx 80%
Rerank 291% CHEAPER
Voyage AI
Same category
$0.00005 in · $0.05 out / 1M Tokens 32K ctx 80%
rerank-2.5-lite89% CHEAPER
Voyage AI
Same category
$0.02 in · $0 out / 1M Tokens 32K ctx 98%
Voyage 3.589% CHEAPER
Voyage AI
Same category
$0.00006 in · $0.06 out / 1M Tokens 80%
Voyage 489% CHEAPER
Voyage AI
Same category
$0.00006 in · $0.06 out / 1M Tokens 32K ctx 80%
Voyage 389% CHEAPER
Voyage AI
Same category
$0.00006 in · $0.06 out / 1M Tokens 80%
pplx-embed-v1-4b84% CHEAPER
Perplexity
Same category
$0.03 in · $0 out / 1M Tokens 128K ctx 98%
Voyage Finance78% CHEAPER
Voyage AI
Same category
$0.00012 in · $0.12 out / 1M Tokens 80%
Voyage 4 Large78% CHEAPER
Voyage AI
Same category
$0.00012 in · $0.12 out / 1M Tokens 32K ctx 80%
Voyage Multilingual78% CHEAPER
Voyage AI
Same category
$0.00012 in · $0.12 out / 1M Tokens 80%
Voyage Finance 278% CHEAPER
Voyage AI
Same category
$0.00012 in · $0.122 out / 1M Tokens 32K ctx 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.