Lambda AI
Inference
Models
20
Frontier
0
Cheaper here
2
than the headline price
Dearer here
0
than the headline price
Cheapest listing per model, USD per million tokens.
| Model | Here, input / output | Released |
|---|---|---|
| DeepSeek R1 DeepSeekdeepseek-r1-0528 | $0.20 / $0.60 −69% vs DeepSeek | May 2025 |
| Qwen3 32B Alibaba Qwenqwen3-32b-fp8 | $0.05 / $0.10 | Apr 2025 |
| Llama 4 Scout 17B 16e Instruct | $0.05 / $0.10 | Apr 2025 |
| Llama 4 Maverick 17B 128e Instruct Metallama-4-maverick-17b-128e-instruct-fp8 | $0.05 / $0.10 | Apr 2025 |
| Llama3.3 70B Instruct Metallama3.3-70b-instruct-fp8 | $0.12 / $0.30 | Dec 2024 |
| Qwen25 Coder 32B Instruct | $0.05 / $0.10 | Nov 2024 |
| Llama3.2 3B Instruct Metallama3.2-3b-instruct | $0.015 / $0.025 | Sep 2024 |
| Llama3.1 70B Instruct Metallama3.1-70b-instruct-fp8 | $0.12 / $0.30 | Jul 2024 |
| Llama3.1 8B Instruct Metallama3.1-8b-instruct | $0.025 / $0.04 | Jul 2024 |
| DeepSeek V3 DeepSeekdeepseek-v3-0324 | $0.20 / $0.60 −66% vs Novita AI | - |
| Llama3.1 405B Instruct Metallama3.1-405b-instruct-fp8 | $0.80 / $0.80 | - |
| DeepSeek Llama3.3 70B DeepSeekdeepseek-llama3.3-70b | $0.20 / $0.60 | - |
| DeepSeek R1 671B | $0.80 / $0.80 | - |
| Llama3.1 Nemotron 70B Instruct NVIDIAllama3.1-nemotron-70b-instruct-fp8 | $0.12 / $0.30 | - |
| Llama3.2 11B Vision Instruct Metallama3.2-11b-vision-instruct | $0.015 / $0.025 | - |
| Hermes3 405B | $0.80 / $0.80 | - |
| Hermes3 70B | $0.12 / $0.30 | - |
| Hermes3 8B | $0.025 / $0.04 | - |
| Lfm 40B | $0.10 / $0.20 | - |
| Lfm 7B | $0.025 / $0.04 | - |