Skip to content

Cheapest LLM APIs by input price

1,966 models have a published input price above zero. The cheapest is Laya at $0.0000 per million input tokens. Prices are the lowest any tracked gateway publishes — the same model often costs more elsewhere.

Models by cheapest published input price
Free
209
Under $0.10
313
$0.10 – $1
945
$1 – $10
612
$10 and above
96
ModelVendorTypeAvailable onContextInput / MtokSpread
Laya convaiinnovations/laya Convaiinnovations Text Cheaper InferenceVercel 8.2K $0.0000–$0.011 1166.67x
Transcribe-1 fish-audio/transcribe-1 Fish Audio Audio Cheaper InferenceVercel — $0.0001–$85.00 850000x
Gemini 3.5 Transcribe Live google/gemini-3.5-transcribe-live Google Audio Vercel — $0.0001 —
Whisper openai/whisper-1 OpenAI Audio Cheaper InferenceVercel — $0.0001–$85.00 850000x
GPT Live Transcribe openai/gpt-live-transcribe OpenAI Audio Vercel — $0.0002 —
gpt-realtime-whisper openai/gpt-realtime-whisper OpenAI Audio Vercel — $0.0002 —
embeddinggemma-300m embeddinggemma-300m Google Embedding Cheaper Inference — $0.0023 —
Embed v1 0.6b perplexity/pplx-embed-v1-0.6b Perplexity Embedding Cheaper InferenceVercel 32K $0.0034–$0.0040 1.18x
all-minilm-l12-v2 all-minilm-l12-v2 Sentence Transformers Embedding Cheaper Inference — $0.0057 —
all-minilm-l6-v2 all-minilm-l6-v2 Sentence Transformers Embedding Cheaper Inference — $0.0057 —
all-mpnet-base-v2 all-mpnet-base-v2 Sentence Transformers Embedding Cheaper Inference — $0.0057 —
bge-base-en-v1.5 baai/bge-base-en-v1.5 BAAI Embedding Cheaper InferenceCloudflare — $0.0057 —
clip-vit-b-32 clip-vit-b-32 Sentence Transformers Embedding Cheaper Inference — $0.0057 —
clip-vit-b-32-multilingual-v1 clip-vit-b-32-multilingual-v1 Sentence Transformers Embedding Cheaper Inference — $0.0057 —
e5-base-v2 e5-base-v2 Microsoft Embedding Cheaper Inference — $0.0057 —
gte-base gte-base Alibaba Embedding Cheaper Inference — $0.0057 —
multi-qa-mpnet-base-dot-v1 multi-qa-mpnet-base-dot-v1 Sentence Transformers Embedding Cheaper Inference — $0.0057 —
paraphrase-minilm-l6-v2 paraphrase-minilm-l6-v2 Sentence Transformers Embedding Cheaper Inference — $0.0057 —
text2vec-base-chinese text2vec-base-chinese Shibing624 Embedding Cheaper Inference — $0.0057 —
GLM 5.2 z-ai/glm-5.2 Z.ai Multimodal BasetenCloudflareNanoGPTOpenRouterOrcaRouterRampRequestyTogetherVercel 1M $0.0060–$1.40 233.33x
Decider Flash V1.2 4B perplexity/pplx-decider-flash-v1.2 Perplexity Text Cheaper InferenceVercel 262.1K $0.0085–$0.010 1.18x
Qwen3 Embedding 0.6B alibaba/qwen3-embedding-0.6b Alibaba Embedding Vercel 32.8K $0.010 —
Qwen3 Embedding 8B alibaba/qwen3-embedding-8b Alibaba Embedding Vercel 32.8K $0.010 —
BGE-M3 baai/bge-m3 BAAI Embedding Cheaper InferenceCloudflareLLM Gateway 8.2K $0.010–$0.011 1.14x
Joey-1 baseten/joey-1 Baseten Text Cheaper InferenceVercel 16.4K $0.010–$0.011 1.14x
joey-1 decision-models/baseten-joey-2b-latest Decision Models Multimodal Baseten 16.4K $0.010 —
Qwen3 Embedding 0.6B qwen/qwen3-embedding-0.6b Qwen Embedding Cheaper InferenceCloudflareLLM Gateway 32.8K $0.010–$0.011 1.14x
Qwen3 Embedding 8B qwen/qwen3-embedding-8b Qwen Embedding Cheaper InferenceCloudflareFireworksLLM Gateway 41K $0.010–$0.012 1.18x
Qwen3 Reranker 0.6B qwen3-reranker-0.6b Qwen Rerank LLM Gateway 32.8K $0.010 —
bge-large-en-v1.5 baai/bge-large-en-v1.5 BAAI Embedding Cheaper InferenceCloudflare — $0.011 —
bge-en-icl bge-en-icl BAAI Embedding Cheaper Inference — $0.011 —
bge-m3-multi bge-m3-multi BAAI Embedding Cheaper Inference — $0.011 —
bge-m3-multi-8k bge-m3-multi-8k BAAI Embedding Cheaper Inference — $0.011 —
e5-large-v2 e5-large-v2 Microsoft Embedding Cheaper Inference — $0.011 —
gte-large gte-large Alibaba Embedding Cheaper Inference — $0.011 —
llama-nemotron-embed-vl-1b-v2 llama-nemotron-embed-vl-1b-v2 Meta Embedding Cheaper Inference — $0.011 —
multilingual-e5-large multilingual-e5-large Microsoft Embedding Cheaper Inference — $0.011 —
multilingual-e5-large-instruct multilingual-e5-large-instruct Microsoft Embedding Cheaper Inference — $0.011 —
Text Embedding 005 google/text-embedding-005 Google Embedding Cheaper InferenceLLM GatewayVercel 2K $0.016–$0.025 1.54x
Text Multilingual Embedding 002 google/text-multilingual-embedding-002 Google Embedding Cheaper InferenceLLM GatewayVercel 2K $0.016–$0.025 1.54x
Titan Text Embeddings V2 amazon/titan-embed-text-v2 Amazon Embedding Cheaper InferenceVercel — $0.017–$0.020 1.18x
Cohere Rerank 5 Fast cohere/rerank-v5-fast Cohere Rerank Cheaper InferenceVercel 32.8K $0.017–$0.020 1.18x
d1 d1 Liquid Ai Multimodal Cheaper Inference 65.5K $0.017 —
llama-3.1-8b llama-3.1-8b Meta Text Cheaper Inference 16.4K $0.017 —
Text Embedding 3 Small openai/text-embedding-3-small OpenAI Embedding Cheaper InferenceCloudflareLLM GatewayOrcaRouterVercel 8.2K $0.017–$0.020 1.18x
Decider V1.2 27B perplexity/pplx-decider-v1.2 Perplexity Text Cheaper InferenceVercel 262.1K $0.017–$0.020 1.18x
rerank-2.5-lite rerank-2.5-lite Cohere Rerank Cheaper Inference 32K $0.017 —
rerank-3-lite rerank-3-lite Cohere Rerank Cheaper Inference 32K $0.017 —
voyage-3.5-lite voyage-3.5-lite Voyage Ai Embedding Cheaper Inference — $0.017 —
voyage-4-lite voyage-4-lite Voyage Ai Embedding Cheaper Inference 32K $0.017 —

Showing the top 50 of 1,966. Search the full catalog to go further.

How this is measured. Ranked on the lowest input (prompt) price published by any tracked gateway, normalized to US dollars per million tokens. Output prices are shown on each model page and are not what this ranking sorts on. Genuinely free models are excluded here and listed separately. A model no gateway prices is excluded rather than treated as free.
Other rankings

Sorted a different way

Largest context 1,932 Free 378 Tool calling 804 Price spreads 571