Cheapest LLM APIs
The lowest-cost large language model APIs we track, ranked by combined input and output price per million tokens. Most of the cheapest options are open-weight models (DeepSeek, Qwen, GLM, MiniMax) served by competing providers — which is exactly why prices keep falling.
Ranking 50 options · updated June 30, 2026
| # | Model | Provider | Input /1M | Output /1M |
|---|---|---|---|---|
| 1 | Gemma 3 4B open | Together AI | $0.020 | $0.040 |
| 2 | Gemma 3 4B open | OpenRouter | $0.050 | $0.100 |
| 3 | Gemma 3 12B open | OpenRouter | $0.050 | $0.150 |
| 4 | Ministral 3 8B open | Mistral AI | $0.100 | $0.100 |
| 5 | Gemma 3 4B open | Fireworks AI | $0.100 | $0.100 |
| 6 | Gemma 3 27B open | OpenRouter | $0.080 | $0.160 |
| 7 | Qwen 3.5 9B open | DeepInfra | $0.040 | $0.200 |
| 8 | Qwen 3 8B open | Together AI | $0.100 | $0.150 |
| 9 | Qwen 3.5 9B open | OpenRouter | $0.100 | $0.150 |
| 10 | DeepSeek V4 Flash open | OpenRouter | $0.090 | $0.180 |
| 11 | Mistral Small 3.2 24B open | OpenRouter | $0.075 | $0.200 |
| 12 | Ministral 3 8B open | OpenRouter | $0.150 | $0.150 |
| 13 | Nova Lite | OpenRouter | $0.060 | $0.240 |
| 14 | Gemma 3 27B open | Novita AI | $0.119 | $0.200 |
| 15 | Gemma 3 27B open | Venice AI | $0.120 | $0.200 |
| 16 | Mistral Small 4 open | Venice AI | $0.090 | $0.250 |
| 17 | Qwen3 14B open | OpenRouter | $0.100 | $0.240 |
| 18 | Qwen3 Coder 30B A3B Instruct open | OpenRouter | $0.070 | $0.270 |
| 19 | Qwen 3 32B open | OpenRouter | $0.080 | $0.280 |
| 20 | GPT OSS 120B open | Venice AI | $0.070 | $0.300 |
| 21 | Qwen 3 8B open | Cloudflare Workers AI | $0.051 | $0.335 |
| 22 | Gemma 4 26B A4B open | OpenRouter | $0.060 | $0.330 |
| 23 | Llama 4 Scout open | OpenRouter | $0.100 | $0.300 |
| 24 | Gemma 3 12B open | Fireworks AI | $0.200 | $0.200 |
| 25 | Qwen 3 8B open | Fireworks AI | $0.200 | $0.200 |
| 26 | Ministral 3 8B open | Fireworks AI | $0.200 | $0.200 |
| 27 | Qwen 3 32B open | Nebius | $0.100 | $0.300 |
| 28 | Llama 3.3 70B open | OpenRouter | $0.100 | $0.320 |
| 29 | GPT-5 Nano | Replicate | $0.050 | $0.400 |
| 30 | GPT-5 Nano | OpenRouter | $0.050 | $0.400 |
| 31 | Qwen 3 8B open | OpenRouter | $0.050 | $0.400 |
| 32 | GPT-5 Nano | OpenAI | $0.050 | $0.400 |
| 33 | Llama 4 Scout open | Groq | $0.110 | $0.340 |
| 34 | Qwen 3 8B open | Alibaba Cloud | $0.050 | $0.400 |
| 35 | Qwen 3.5 9B open | Alibaba Cloud | $0.050 | $0.400 |
| 36 | GLM 4.7 | DeepInfra | $0.060 | $0.400 |
| 37 | GLM 4.7 | Cloudflare Workers AI | $0.060 | $0.400 |
| 38 | GLM 4.7 Flash open | OpenRouter | $0.060 | $0.400 |
| 39 | Gemma 4 27B open | OpenRouter | $0.120 | $0.350 |
| 40 | Gemini 2.0 Flash | OpenRouter | $0.100 | $0.400 |
| 41 | Gemini 2.0 Flash | $0.100 | $0.400 | |
| 42 | Qwen 3.5 35B open | Alibaba Cloud | $0.100 | $0.400 |
| 43 | DeepSeek V3 open | Hyperbolic | $0.250 | $0.250 |
| 44 | Seed-2.0-Mini open | OpenRouter | $0.100 | $0.400 |
| 45 | GPT-4.1 Nano | OpenRouter | $0.100 | $0.400 |
| 46 | Gemma 3 27B open | Parasail | $0.080 | $0.450 |
| 47 | Gemma 4 27B open | Parasail | $0.130 | $0.400 |
| 48 | Llama 3.3 70B open | Nebius | $0.130 | $0.400 |
| 49 | Llama 3.3 70B open | Novita AI | $0.135 | $0.400 |
| 50 | Gemma 4 27B open | Novita AI | $0.140 | $0.400 |