Cheapest PDF-Input Model APIs
As of Nov 22, 2026, the cheapest PDF-capable model API is GLM-5.3-Flash at $0.0062 per 1M input and $0.0185 per 1M output tokens on JoinGonka.
The table ranks the 20 cheapest of 197 qualifying models offered by at least 3 providers, by the cheapest offer's 3:1 input:output blended price. Models that accept PDF files.
| # | Model | |||||
|---|---|---|---|---|---|---|
| 1 | GLM-5.3-Flash | $0.0062JoinGonka | $0.0185JoinGonka | $0.0093 | 1.0M | 113 |
| 2 | DeepSeek V4.1 Flash 1017 | $0.01Refuseless | $0.08Refuseless | $0.0275 | 1.1M | 73 |
| 3 | GPT-5.6 Luna | $0.0123xxapi | $0.0738xxapi | $0.0277 | 1.1M | 54 |
| 4 | Ministral 3B | $0.04Azure | $0.04Azure | $0.04 | 131k | 7 |
| 5 | Gemma 3 4B IT | $0.04Kilo Gateway | $0.05Kilo Gateway | $0.0425 | 131k | 6 |
| 6 | DeepSeek V4.1 Flash | $0.03engy | $0.12engy | $0.0525 | 1.1M | 82 |
| 7 | Gemma 3 12B IT | $0.04Kilo Gateway | $0.1Novita AI | $0.06 | 131k | 8 |
| 8 | GPT-6 Luna | $0.04Kunavo | $0.2Kunavo | $0.08 | 1.1M | 48 |
| 9 | Gemma 3 27B IT | $0.064Kilo Gateway | $0.128Kilo Gateway | $0.08 | 131k | 11 |
| 10 | Gemma 4 26B A4B IT | $0.05Kilo Gateway | $0.19Kilo Gateway | $0.085 | 262k | 23 |
| 11 | Claude Haiku 5.5 | $0.05IteraCompute | $0.25IteraCompute | $0.1 | 1.0M | 47 |
| 12 | Ministral 3 3B | $0.1Amazon Bedrock | $0.1Amazon Bedrock | $0.1 | 262k | 3 |
| 13 | GPT-5 Mini | $0.04QiHang | $0.29QiHang | $0.1025 | 400k | 34 |
| 14 | Nova Lite 1.0 | $0.0595NanoGPT | $0.238NanoGPT | $0.1041 | 300k | 5 |
| 15 | Nova Lite | $0.06Amazon Bedrock | $0.24Amazon Bedrock | $0.105 | 1.0M | 5 |
| 16 | Qwen3.8 27B | $0.03CedarLLM | $0.32engy | $0.1138 | 1.1M | 65 |
| 17 | Muse Spark 1.3 Contributor | $0.1Bothub | $0.2Bothub | $0.125 | 1.0M | 10 |
| 18 | Muse Spark 1.2 Contributor | $0.1CommandCode | $0.2CommandCode | $0.125 | 1.0M | 9 |
| 19 | GPT-5 Nano | $0.0455Poe | $0.3636Poe | $0.125 | 400k | 32 |
| 20 | GPT-4o mini | $0.075Cloudflare AI Gateway | $0.3Cloudflare AI Gateway | $0.1312 | 128k | 25 |
FAQ
What is the cheapest PDF-capable model API?
As of Nov 22, 2026, the cheapest PDF-capable model API is GLM-5.3-Flash at $0.0062 per 1M input and $0.0185 per 1M output tokens on JoinGonka.
Which PDF-capable model APIs are cheapest after GLM-5.3-Flash?
DeepSeek V4.1 Flash 1017 ($0.0275 blended per 1M tokens on Refuseless), GPT-5.6 Luna ($0.0277 blended per 1M tokens on xxapi), Ministral 3B ($0.04 blended per 1M tokens on Azure), as of Nov 22, 2026.
How is this list ranked?
By each model's cheapest metered offer, blended 3:1: (3 × input + output) ÷ 4 per 1M tokens. Free tiers and subscription plans are excluded, and a model needs at least 3 paid providers to qualify.