Cheapest LLM APIs
178 models ranked by blended cost — (3×input + 1×output) ÷ 4 per million tokens (input-only models like embeddings rank by their input price). Lower is cheaper.
Lowest token prices right now
top 10 by blended cost · last scan 2026-08-09Top 10 by blended $/Mtokcheapest first
$0/M
2. Rerank 3.5
$0.02/M
$0.02/M
$0.02/M
$0.02/M
6. GLM-OCR
$0.03/M
$0.041/M
8. rerank-2.5
$0.05/M
$0.055/M
$0.058/M
MODELPRICEWATCH.COM · 2026-08-09
Every model by blended cost
178 models · sorted by blended cost (cheapest first)| Notes | |||||
|---|---|---|---|---|---|
| GLM-4.7-FlashZ.AI | $0 |
$0 | $0 | 128K | Open |
| Rerank 3.5Cohere | $0.020 |
$0.020 | $— | — | |
| text-embedding-3-smallOpenAI | $0.020 |
$0.020 | $— | 8K | |
| rerank-2.5-liteVoyage AI | $0.020 |
$0.020 | $— | — | |
| voyage-4-liteVoyage AI | $0.020 |
$0.020 | $— | — | |
| GLM-OCRZ.AI | $0.030 |
$0.030 | $0.030 | 128K | Open |
| Granite 4.0 MicroIBM | $0.041 |
$0.017 | $0.112 | 128K | Open |
| rerank-2.5Voyage AI | $0.050 |
$0.050 | $— | — | |
| Qwen3.7-FlashAlibaba | $0.055 |
$0.030 | $0.130 | 1M | |
| Llama 3.1 8B InstantGroq | $0.058 |
$0.050 | $0.080 | 128K | Open840 TPS |
| Llama 3.1 8BMeta | $0.058 |
$0.050 | $0.080 | 128K | Open |
| voyage-4Voyage AI | $0.060 |
$0.060 | $— | — | |
| Nova MicroAmazon | $0.061 |
$0.035 | $0.140 | 128K | |
| Baichuan M2-32BBaichuan | $0.070 |
$0.070 | $0.070 | 33K | Open |
| Qwen-TurboAlibaba | $0.088 |
$0.050 | $0.200 | 1M | |
| Ministral 3 3BMistral | $0.100 |
$0.100 | $0.100 | 128K | Open |
| Reka EdgeReka | $0.100 |
$0.100 | $0.100 | 66K | |
| GLM-4-32B-0414Z.AI | $0.100 |
$0.100 | $0.100 | 128K | Open |
| Nova LiteAmazon | $0.105 |
$0.060 | $0.240 | 300K | |
| Granite Embedding 278M MultilingualIBM | $0.106 |
$0.106 | $— | — | Open |
| Granite 4 H SmallIBM | $0.107 |
$0.060 | $0.250 | 128K | Open |
| DeepSeek V4 FlashDeepInfra | $0.113 |
$0.090 | $0.180 | 1M | |
| Embed 4Cohere | $0.120 |
$0.120 | $— | — | |
| voyage-4-largeVoyage AI | $0.120 |
$0.120 | $— | — | |
| voyage-multimodal-3.5Voyage AI | $0.120 |
$0.120 | $— | — | |
| GPT OSS 20BFireworks | $0.128 |
$0.070 | $0.300 | 128K | Open |
| text-embedding-3-largeOpenAI | $0.130 |
$0.130 | $— | 8K | |
| Qwen3 32BDeepInfra | $0.130 |
$0.080 | $0.280 | 128K | Open |
| GPT-OSS 20BGroq | $0.131 |
$0.075 | $0.300 | 128K | Open1000 TPS |
| Qwen-FlashAlibaba | $0.138 |
$0.050 | $0.400 | 1M | |
| Voxtral Small 24BMistral | $0.150 |
$0.100 | $0.300 | 128K | Open |
| Llama 4 ScoutDeepInfra | $0.150 |
$0.100 | $0.300 | 10M | Open |
| GLM-4.7-FlashXZ.AI | $0.153 |
$0.070 | $0.400 | 128K | Open |
| Llama 4 ScoutMeta | $0.168 |
$0.110 | $0.340 | 10M | Open |
| DeepSeek V4 FlashDeepSeek | $0.175 |
$0.140 | $0.280 | 1M | |
| DeepSeek V4 FlashFireworks | $0.175 |
$0.140 | $0.280 | 1M | |
| Gemini 2.5 Flash-LiteGoogle | $0.175 |
$0.100 | $0.400 | 1M | |
| GPT-4.1 nanoOpenAI | $0.175 |
$0.100 | $0.400 | 1M | |
| voyage-code-3Voyage AI | $0.180 |
$0.180 | $— | 32K | |
| voyage-context-3Voyage AI | $0.180 |
$0.180 | $— | 32K | |
| Jamba MiniAI21 Labs | $0.250 |
$0.200 | $0.400 | 256K | Open |
| Hunyuan Hy3 PreviewTencent | $0.257 |
$0.147 | $0.588 | 262K | |
| Command R 08-2024Cohere | $0.262 |
$0.150 | $0.600 | 128K | |
| GPT OSS 120BFireworks | $0.262 |
$0.150 | $0.600 | 128K | Open |
| GPT-OSS 120BGroq | $0.262 |
$0.150 | $0.600 | 128K | Open500 TPS |
| Granite 4 H MediumIBM | $0.262 |
$0.150 | $0.600 | 128K | Open |
| Mistral Small 4Mistral | $0.262 |
$0.150 | $0.600 | 128K | |
| gpt-oss-120BTogether | $0.262 |
$0.150 | $0.600 | 128K | Open |
| Solar Pro 3Upstage | $0.262 |
$0.150 | $0.600 | 131K | |
| Qwen3-32BAlibaba | $0.280 |
$0.160 | $0.640 | 131K | Open |
| Llama 4 MaverickDeepInfra | $0.350 |
$0.200 | $0.800 | 1M | Open |
| Qwen3 32BGroq | $0.365 |
$0.290 | $0.590 | 128K | Open662 TPS |
| Gemma-4-31B-it-PearlTogether | $0.425 |
$0.280 | $0.860 | 128K | Open |
| GLM-4.5-AirZ.AI | $0.425 |
$0.200 | $1.10 | 128K | Open |
| CodestralMistral | $0.450 |
$0.300 | $0.900 | 256K | |
| Codestral 2508Mistral | $0.450 |
$0.300 | $0.900 | 256K | |
| GLM-4.6VZ.AI | $0.450 |
$0.300 | $0.900 | 128K | Open |
| GPT-5.6 LunaOpenAI | $0.450 |
$0.200 | $1.20 | 1M | |
| GPT-5.4 nanoOpenAI | $0.463 |
$0.200 | $1.25 | 400K | |
| MiniMax 2.5Fireworks | $0.525 |
$0.300 | $1.20 | 128K | Open |
| MiniMax 2.7Fireworks | $0.525 |
$0.300 | $1.20 | 128K | Open |
| MiniMax M3Fireworks | $0.525 |
$0.300 | $1.20 | 1M | Open |
| Granite 4 H LargeIBM | $0.525 |
$0.300 | $1.20 | 128K | Open |
| MiniMax-M2.7MiniMax | $0.525 |
$0.300 | $1.20 | 205K | Open |
| MiniMax-M3MiniMax | $0.525 |
$0.300 | $1.20 | 1M | Open |
| MiniMax M3Together | $0.525 |
$0.300 | $1.20 | 1M | Open |
| Inkling SmallThinking Machines | $0.525 |
$0.300 | $1.20 | 262K | Open |
| DeepSeek V4 ProDeepSeek | $0.544 |
$0.435 | $0.870 | 1M | |
| Qwen3.7-PlusTogether | $0.560 |
$0.320 | $1.28 | 128K | Open |
| Qwen3.6-FlashAlibaba | $0.563 |
$0.250 | $1.50 | 1M | |
| Gemini 3.1 Flash-LiteGoogle | $0.563 |
$0.250 | $1.50 | 1M | |
| Qwen-PlusAlibaba | $0.600 |
$0.400 | $1.20 | 131K | |
| Llama 3.3 70B VersatileGroq | $0.640 |
$0.590 | $0.790 | 128K | Open394 TPS |
| Llama 3.3 70BMeta | $0.640 |
$0.590 | $0.790 | 128K | Open |
| Qwen3.7-PlusAlibaba | $0.700 |
$0.400 | $1.60 | 1M | |
| Qwen 3.7 PlusFireworks | $0.700 |
$0.400 | $1.60 | 128K | Open |
| GPT-4.1 miniOpenAI | $0.700 |
$0.400 | $1.60 | 1M | |
| Command R 03-2024Cohere | $0.750 |
$0.500 | $1.50 | 128K | |
| Mistral Large 3Mistral | $0.750 |
$0.500 | $1.50 | 128K | |
| Mistral Medium 3Mistral | $0.800 |
$0.400 | $2.00 | 128K | |
| Gemini 2.5 FlashGoogle | $0.850 |
$0.300 | $2.50 | 1M | |
| Gemini 3.5 Flash-LiteGoogle | $0.850 |
$0.300 | $2.50 | 1M | |
| Relace Apply 3Relace | $0.900 |
$0.800 | $1.20 | 256K | |
| SonarPerplexity | $1.00 |
$1.00 | $1.00 | 200K | |
| GLM-4.5Z.AI | $1.00 |
$0.600 | $2.20 | 128K | Open |
| GLM-4.6Z.AI | $1.00 |
$0.600 | $2.20 | 200K | Open |
| GLM-4.7Z.AI | $1.00 |
$0.600 | $2.20 | 128K | Open |
| Llama 3.3 70BTogether | $1.04 |
$1.04 | $1.04 | 128K | Open |
| NVIDIA Nemotron 3 UltraFireworks | $1.05 |
$0.600 | $2.40 | 128K | Open |
| Reka FlashReka | $1.10 |
$0.800 | $2.00 | 128K | |
| Qwen3.6-PlusAlibaba | $1.13 |
$0.500 | $3.00 | 1M | |
| Qwen 3.6 PlusFireworks | $1.13 |
$0.500 | $3.00 | 128K | Open |
| Gemini 3 Flash PreviewGoogle | $1.13 |
$0.500 | $3.00 | 1M | |
| Kimi K2.5Fireworks | $1.20 |
$0.600 | $3.00 | 256K | Open |
| Qwen 3.6 27BGroq | $1.20 |
$0.600 | $3.00 | 128K | Open500 TPS |
| Kimi K2.5Moonshot | $1.20 |
$0.600 | $3.00 | 262K | Open |
| QwQ-PlusAlibaba | $1.20 |
$0.800 | $2.40 | 131K | |
| Grok Build 0.1xAI | $1.25 |
$1.00 | $2.00 | 256K | |
| LongCat-2.0Meituan | $1.30 |
$0.750 | $2.95 | 262K | Open |
| Qwen3.6-27BAlibaba | $1.35 |
$0.600 | $3.60 | 262K | Open |
| Qwen3.5-397B-A17BAlibaba | $1.35 |
$0.600 | $3.60 | 262K | Open |
| NVIDIA Nemotron 3 UltraTogether | $1.35 |
$0.600 | $3.60 | 128K | Open |
| Nova ProAmazon | $1.40 |
$0.800 | $3.20 | 300K | |
| Relace SearchRelace | $1.50 |
$1.00 | $3.00 | 256K | |
| GLM-5Z.AI | $1.55 |
$1.00 | $3.20 | 128K | Open |
| Grok 4.20xAI | $1.56 |
$1.25 | $2.50 | 256K | |
| Grok 4.3xAI | $1.56 |
$1.25 | $2.50 | 1M | |
| GPT-5.4 miniOpenAI | $1.69 |
$0.750 | $4.50 | 1M | |
| Kimi K2.6Fireworks | $1.71 |
$0.950 | $4.00 | 256K | Open |
| Kimi K2.7 CodeFireworks | $1.71 |
$0.950 | $4.00 | 256K | Open |
| Kimi K2.6Moonshot | $1.71 |
$0.950 | $4.00 | 262K | Open |
| Kimi K2.7 CodeMoonshot | $1.71 |
$0.950 | $4.00 | 262K | Open |
| Kimi K2.7 CodeTogether | $1.71 |
$0.950 | $4.00 | 256K | Open |
| InklingThinking Machines | $1.76 |
$1.00 | $4.05 | 262K | Open |
| Qwen3.7-MaxTogether | $1.88 |
$1.25 | $3.75 | 1M | |
| GLM-5-TurboZ.AI | $1.90 |
$1.20 | $4.00 | 128K | Open |
| GLM-5V-TurboZ.AI | $1.90 |
$1.20 | $4.00 | 128K | Open |
| o3-miniOpenAI | $1.93 |
$1.10 | $4.40 | 200K | |
| o4-miniOpenAI | $1.93 |
$1.10 | $4.40 | 200K | |
| Claude Haiku 4.5Anthropic | $2.00 |
$1.00 | $5.00 | 200K | |
| Muse Spark 1.1Meta | $2.00 |
$1.25 | $4.25 | 1M | |
| Muse Spark 1.2Meta | $2.00 |
$1.25 | $4.25 | 1M | |
| GLM 5.1Fireworks | $2.15 |
$1.40 | $4.40 | 128K | Open |
| GLM 5.2Fireworks | $2.15 |
$1.40 | $4.40 | 1M | Open |
| GLM-5.2Together | $2.15 |
$1.40 | $4.40 | 1M | Open |
| GLM-5.1Z.AI | $2.15 |
$1.40 | $4.40 | 128K | Open |
| GLM-5.2Z.AI | $2.15 |
$1.40 | $4.40 | 1M | Open |
| DeepSeek V4 ProFireworks | $2.17 |
$1.74 | $3.48 | 1M | |
| DeepSeek V4 ProTogether | $2.17 |
$1.74 | $3.48 | 1M | |
| Qwen3-MaxAlibaba | $2.40 |
$1.20 | $6.00 | 262K | |
| Qwen3.8-MaxAlibaba | $3.00 |
$2.00 | $6.00 | 1M | |
| Gemini 3.6 FlashGoogle | $3.00 |
$1.50 | $7.50 | 1M | |
| Mistral Medium 3.5Mistral | $3.00 |
$1.50 | $7.50 | 128K | |
| Reka CoreReka | $3.00 |
$2.00 | $6.00 | 128K | |
| Grok 4.5xAI | $3.00 |
$2.00 | $6.00 | 500K | |
| Gemini 3.5 FlashGoogle | $3.38 |
$1.50 | $9.00 | 1M | |
| Kimi K2.7 Code HighSpeedMoonshot | $3.42 |
$1.90 | $8.00 | 262K | Open |
| Gemini 2.5 ProGoogle | $3.44 |
$1.25 | $10.00 | 2M | |
| Jamba LargeAI21 Labs | $3.50 |
$2.00 | $8.00 | 256K | Open |
| GPT-4.1OpenAI | $3.50 |
$2.00 | $8.00 | 1M | |
| Sonar Deep ResearchPerplexity | $3.50 |
$2.00 | $8.00 | 200K | |
| Sonar Reasoning ProPerplexity | $3.50 |
$2.00 | $8.00 | 200K | |
| Qwen3.7-MaxAlibaba | $3.75 |
$2.50 | $7.50 | 1M | |
| Claude Sonnet 5Anthropic | $4.00 |
$2.00 | $10.00 | 1M | |
| Command ACohere | $4.38 |
$2.50 | $10.00 | 256K | |
| Command R+ 08-2024Cohere | $4.38 |
$2.50 | $10.00 | 128K | |
| Yi Large01.AI | $4.50 |
$3.00 | $9.00 | 32K | |
| Gemini 3.1 ProGoogle | $4.50 |
$2.00 | $12.00 | 2M | |
| GPT-5.6 TerraOpenAI | $4.50 |
$2.00 | $12.00 | 1M | |
| GPT-5.3 ChatOpenAI | $4.81 |
$1.75 | $14.00 | 128K | |
| GPT-5.3 CodexOpenAI | $4.81 |
$1.75 | $14.00 | 400K | |
| GPT-5.2OpenAI | $4.81 |
$1.75 | $14.00 | 400K | |
| GPT-5.2 CodexOpenAI | $4.81 |
$1.75 | $14.00 | 400K | |
| GPT-5.2 ChatOpenAI | $4.81 |
$1.75 | $14.00 | 128K | |
| Nova PremierAmazon | $5.00 |
$2.50 | $12.50 | 1M | |
| GPT-5.4OpenAI | $5.63 |
$2.50 | $15.00 | 1M | |
| Claude Sonnet 4.5Anthropic | $6.00 |
$3.00 | $15.00 | 200K | |
| Claude Sonnet 4.6Anthropic | $6.00 |
$3.00 | $15.00 | 1M | |
| Kimi K3Moonshot | $6.00 |
$3.00 | $15.00 | 1M | Open |
| Sonar ProPerplexity | $6.00 |
$3.00 | $15.00 | 200K | |
| Gemini 3.1 Flash Lite ImageGoogle | $7.69 |
$0.250 | $30.00 | — | |
| GPT-Realtime-2OpenAI | $9.00 |
$4.00 | $24.00 | 128K | |
| Claude Opus 4.5Anthropic | $10.00 |
$5.00 | $25.00 | 200K | |
| Claude Opus 4.6Anthropic | $10.00 |
$5.00 | $25.00 | 1M | |
| Claude Opus 4.7Anthropic | $10.00 |
$5.00 | $25.00 | 1M | |
| Claude Opus 4.8Anthropic | $10.00 |
$5.00 | $25.00 | 1M | |
| Claude Opus 5Anthropic | $10.00 |
$5.00 | $25.00 | 1M | |
| GPT-5.5OpenAI | $11.25 |
$5.00 | $30.00 | 1M | |
| GPT-5.6 SolOpenAI | $11.25 |
$5.00 | $30.00 | 1M | |
| Fugu UltraSakana AI | $11.25 |
$5.00 | $30.00 | 1M | |
| GPT-Image-2OpenAI | $13.50 |
$8.00 | $30.00 | 128K | |
| Gemini 3.1 Flash ImageGoogle | $15.38 |
$0.500 | $60.00 | — | |
| Claude Fable 5Anthropic | $20.00 |
$10.00 | $50.00 | 1M | |
| Claude Mythos 5Anthropic | $20.00 |
$10.00 | $50.00 | 1M | |
| Gemini 3 Pro ImageGoogle | $31.50 |
$2.00 | $120.00 | — | |
| GPT-5.2 ProOpenAI | $57.75 |
$21.00 | $168.00 | 400K | |
| GPT-5.5 ProOpenAI | $67.50 |
$30.00 | $180.00 | 1M | |
| GPT-5.4 ProOpenAI | $67.50 |
$30.00 | $180.00 | 1M |
* Blended = (3×input + 1×output) ÷ 4 $/Mtok (input price alone for embeddings/rerankers) · cheap · mid · expensive
How blended cost works
Blended cost = (3×input + 1×output) ÷ 4 per 1M tokens, weighted toward input to reflect typical read-heavy workloads. It's the simplest way to compare models when your usage mixes both. Input-only models — embeddings and rerankers — have no output side, so their blended cost is simply their input price. The cheapest models are often small open-weight models hosted on Groq or Together, but they may lack the reasoning power of frontier models. Use the Cost Calculator to estimate real monthly spending based on your actual input/output ratio.