Cheapest LLM APIs by Token Cost
The cheapest LLM APIs ranked by token cost. Find budget-friendly models under $1/Mtok for high-volume production workloads.
76 models qualify
top 20 shown
sorted by input price, cheapest first
MODELPRICEWATCH.COM · 2026-11-07
Cost calculator for this use casemonthly cost, top 3 models
- 1 pplx-decider-flash-v1.2
- $—
- 2 Granite 4.0 H Micro
- $—
- 3 pplx-decider-v1.2
- $—
Full ranking — top 20 models
list prices, USD per 1M tokens| Model | Blended* | Input | Output | Context | Provider |
|---|---|---|---|---|---|
| 1pplx-decider-flash-v1.2 | $0.007 | $0.010 | $0 | 262K | Perplexity |
| 2Granite 4.0 H Micro | $0.041 | $0.017 | $0.112 | 128K | Cloudflare |
| 3pplx-decider-v1.2 | $0.015 | $0.020 | $0 | 262K | Perplexity |
| 4Qwen3.7-Flash | $0.055 | $0.030 | $0.130 | 1M | Alibaba |
| 5Schematron V2 Turbo | $0.060 | $0.030 | $0.150 | 128K | Inference.net |
| 6GLM-OCR | $0.030 | $0.030 | $0.030 | 128K | Z.AI |
| 7Nova Micro | $0.061 | $0.035 | $0.140 | 128K | Amazon |
| 8Clef-flash | $0.028 | $0.038 | $0 | 25K | Cloudflare |
| 9GLM-4.6V-FlashX | $0.130 | $0.040 | $0.400 | 128K | Z.AI |
| 10Tev1 4B Experimental | $0.032 | $0.042 | $0 | 33K | Together |
| 11Jev 1.13 | $0.032 | $0.042 | $0 | 64K | TypeSafe AI |
| 12Jev 1.14 | $0.032 | $0.042 | $0 | 64K | TypeSafe AI |
| 13Hy-MT2 1.8B | $0.077 | $0.044 | $0.177 | 8K | Tencent |
| 14Qwen-Flash | $0.138 | $0.050 | $0.400 | 1M | Alibaba |
| 15Schematron V2 Small | $0.095 | $0.050 | $0.230 | 128K | Inference.net |
| 16Summarize | $0.038 | $0.050 | $0 | 1M | ScaleDown |
| 17Classify | $0.038 | $0.050 | $0 | 1M | ScaleDown |
| 18Compress | $0.038 | $0.050 | $0 | 1M | ScaleDown |
| 19Extract | $0.038 | $0.050 | $0 | 1M | ScaleDown |
| 20LFM2.5-24B-A2B | $0.212 | $0.050 | $0.700 | 131K | Liquid AI |
Ranking basis: input price, cheapest first. * Blended = (3×input + 1×output) ÷ 4. Every price links to its source on the model page.
How models are selected
Budget-category models, sorted by input price per million tokens.
Prices are per million tokens (Mtok), sourced directly from — and linked to — official provider pricing pages. "Blended cost" is (3×input + 1×output) ÷ 4 — weighted toward input because real workloads read far more tokens than they generate.