Cheapest LLM APIs by input price
1,043 models have a published input price above zero. The cheapest is Gemini 3.5 Transcribe Live at $0.0001 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
43
Under $0.10
114
$0.10 – $1
488
$1 – $10
390
$10 and above
51
| Model | Vendor | Type | Available on | Context | Input / Mtok | Spread |
|---|---|---|---|---|---|---|
Gemini 3.5 Transcribe Live
google/gemini-3.5-transcribe-live
|
Audio | Vercel | — | $0.0001 | — | |
Whisper
openai/whisper-1
|
OpenAI | Audio | Vercel | — | $0.0001 | — |
gpt-realtime-whisper
openai/gpt-realtime-whisper
|
OpenAI | Audio | Vercel | — | $0.0002 | — |
Seedream 5.0 Pro
bytedance/seedream-5.0-pro
|
ByteDance | Image | Vercel | — | $0.0030 | — |
Embed v1 0.6b
perplexity/pplx-embed-v1-0.6b
|
Perplexity | Embedding | Vercel | 32K | $0.0040 | — |
Qwen3 Embedding 0.6B
alibaba/qwen3-embedding-0.6b
|
Alibaba | Embedding | Vercel | 32.8K | $0.010 | — |
BGE-M3
bge-m3
|
BAAI | Embedding | LLM Gateway | 8.2K | $0.010 | — |
Granite 4.0 Micro
ibm-granite/granite-4.0-h-micro
|
Ibm Granite | Text | CloudflareOpenRouter | 131K | $0.017 | — |
Mistral Nemo
mistralai/mistral-nemo
|
Mistral AI | Text | CloudflareOpenRouterRequestyVercel | 131.1K | $0.019–$0.170 | 8.95x |
Qwen3 Embedding 4B
alibaba/qwen3-embedding-4b
|
Alibaba | Embedding | Vercel | 32.8K | $0.020 | — |
Titan Text Embeddings V2
amazon/titan-embed-text-v2
|
Amazon | Embedding | Vercel | — | $0.020 | — |
meta-llama-3.1-8b-instruct-turbo
meta-llama/meta-llama-3.1-8b-instruct-turbo
|
Meta | Text | Requesty | 131.1K | $0.020 | — |
text-embedding-3-small
openai/text-embedding-3-small
|
OpenAI | Embedding | CloudflareOrcaRouterVercel | — | $0.020 | — |
qwen3.5-2b
qwen/qwen3.5-2b
|
Qwen | Multimodal | Requesty | 262.1K | $0.020 | — |
Voyage Rerank 2.5 Lite
voyage/rerank-2.5-lite
|
Voyage | Rerank | Vercel | 32K | $0.020 | — |
Voyage 3.5 Lite
voyage/voyage-3.5-lite
|
Voyage | Embedding | Vercel | — | $0.020 | — |
Voyage 4 Lite
voyage/voyage-4-lite
|
Voyage | Embedding | Vercel | 32K | $0.020 | — |
Ling 3.0 Flash
inclusionai/ling-3.0-flash
|
inclusionAI | Text | CloudflareOpenRouterVercel | 262.1K | $0.021–$0.060 | 2.86x |
Text Embedding 005
google/text-embedding-005
|
Embedding | Vercel | — | $0.025 | — | |
Text Multilingual Embedding 002
google/text-multilingual-embedding-002
|
Embedding | Vercel | — | $0.025 | — | |
GPT-5 Nano (batch)
openai/gpt-5-nano:batch
|
OpenAI | Multimodal | CloudflareOpenRouter | 400K | $0.025 | — |
gpt-5-nano:flex
openai/gpt-5-nano:flex
|
OpenAI | Multimodal | Requesty | 400K | $0.025 | — |
Llama 3.2 1B Instruct
meta-llama/llama-3.2-1b-instruct
|
Meta | Text | CloudflareOpenRouter | 60K | $0.027 | — |
Qwen 3.7 Flash
alibaba/qwen3.7-flash
|
Alibaba | Text | Vercel | 991K | $0.030 | — |
gpt-oss-120b
openai/gpt-oss-120b
|
OpenAI | Text | CloudflareOpenRouterOrcaRouterRequestyVercel | 131.1K | $0.030–$0.150 | 5x |
gpt-oss-20b
openai/gpt-oss-20b
|
OpenAI | Text | CloudflareOpenRouterRequestyVercel | 131.1K | $0.030–$0.070 | 2.33x |
Embed v1 4b
perplexity/pplx-embed-v1-4b
|
Perplexity | Embedding | Vercel | 32K | $0.030 | — |
Qwen3.7 Flash
qwen/qwen3.7-flash
|
Qwen | Multimodal | CloudflareOpenRouterOrcaRouter | 1M | $0.030 | — |
Solar Pro 4
upstage/solar-pro4
|
Upstage | Text | CloudflareOpenRouter | 524.3K | $0.030 | — |
gpt-oss-120b
runware/gpt-oss-120b
|
Runware | Text | Requesty | 131.1K | $0.032 | — |
Nova Micro
amazon/nova-micro
|
Amazon | Text | ConcentrateVercel | 128K | $0.035 | — |
Nova Micro 1.0
amazon/nova-micro-v1
|
Amazon | Text | CloudflareOpenRouter | 128K | $0.035 | — |
Command R7B (12-2024)
cohere/command-r7b-12-2024
|
Cohere | Text | CloudflareOpenRouter | 128K | $0.037 | — |
Mercury 2.5
inception/mercury-2.5
|
Inception | Text | OpenRouterVercel | 260K | $0.040 | — |
nemotron-3-nano-30b-a3b:flex
nvidia/nemotron-3-nano-30b-a3b:flex
|
NVIDIA | Text | Requesty | 262.1K | $0.040 | — |
Llama 3 8B Lunaris
sao10k/l3-lunaris-8b
|
Sao10k | Text | CloudflareOpenRouter | 8.2K | $0.040 | — |
Hy-MT2-1.8B
tencent/hy-mt2-1.8b
|
Tencent | Text | CloudflareOpenRouter | 8.2K | $0.044 | — |
Tencent Hy-MT2-Lite
tencent/hy-mt2-lite
|
Tencent | Text | Vercel | 8K | $0.044 | — |
Qwen3 30B A3B Instruct 2507
qwen/qwen3-30b-a3b-instruct-2507
|
Qwen | Text | CloudflareOpenRouterRequesty | 262.1K | $0.048–$0.100 | 2.08x |
qwen-turbo
alibaba/qwen-turbo
|
Alibaba | Text | Requesty | 1M | $0.050 | — |
Qwen3 Embedding 8B
alibaba/qwen3-embedding-8b
|
Alibaba | Embedding | Vercel | 32.8K | $0.050 | — |
DeepSeek V4 Flash Latest
deepseek/deepseek-v4-flash-latest
|
DeepSeek | Text | CloudflareOpenRouter | 1.3M | $0.050 | — |
Gemini 2.5 Flash Lite (batch)
google/gemini-2.5-flash-lite:batch
|
Multimodal | CloudflareOpenRouter | 1M | $0.050 | — | |
gemini-2.5-flash-lite:flex
google/gemini-2.5-flash-lite:flex
|
Multimodal | Requesty | 1M | $0.050 | — | |
Gemma 3 12B
google/gemma-3-12b-it
|
Multimodal | CloudflareOpenRouter | 131.1K | $0.050 | — | |
Gemma 3 4B
google/gemma-3-4b-it
|
Multimodal | CloudflareOpenRouter | 131.1K | $0.050 | — | |
Llama 3.1 8B Instruct
meta-llama/llama-3.1-8b-instruct
|
Meta | Text | CloudflareOpenRouterRequesty | 131.1K | $0.050 | — |
Llama 3.2 3B Instruct
meta-llama/llama-3.2-3b-instruct
|
Meta | Text | CloudflareOpenRouter | 131.1K | $0.050 | — |
Mistral Small 3
mistralai/mistral-small-24b-instruct-2501
|
Mistral AI | Text | CloudflareOpenRouter | 32.8K | $0.050 | — |
Nemotron 3.5 Lightning
nvidia/nemotron-3.5-lightning
|
NVIDIA | Text | CloudflareOpenRouterVercel | 262.1K | $0.050–$0.080 | 1.60x |
Showing the top 50 of 1,043. 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