Lambda Pricing
Lambda charges from $0.025 per 1 million output tokens, depending on the model. Llama3.2 11B Vision Instruct is the cheapest at $0.025/1M output and $0.015/1M input; its current flagship DeepSeek R1 671B costs $0.800/1M output. The largest context window is 131K tokens (DeepSeek Llama3.3 70B). Prices are USD, current as of August 11, 2026.
Last updated · synced weekly from the upstream model catalog
Cheapest input
$0.015/1M
Llama3.2 11B Vision Instruct
Cheapest output
$0.025/1M
Llama3.2 11B Vision Instruct
Longest context
131K
DeepSeek Llama3.3 70B
Models priced
20
Avg $0.308/1M output
Pricing by model
All prices in USD per 1 million tokens. All 20 priced models, cheapest first.
| Model | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| Llama3.2 11B Vision Instruct | $0.015 | $0.025 | 131K |
| Llama3.2 3B Instruct | $0.015 | $0.025 | 131K |
| Hermes3 8B | $0.025 | $0.040 | 131K |
| Lfm 7B | $0.025 | $0.040 | 131K |
| Llama3.1 8B Instruct | $0.025 | $0.040 | 131K |
| Llama 4 Maverick 17B 128e Instruct Fp8 | $0.050 | $0.100 | 131K |
| Llama 4 Scout 17B 16e Instruct | $0.050 | $0.100 | 16K |
| Qwen25 Coder 32B Instruct | $0.050 | $0.100 | 131K |
| Qwen3 32B Fp8 | $0.050 | $0.100 | 131K |
| Lfm 40B | $0.100 | $0.200 | 131K |
| Hermes3 70B | $0.120 | $0.300 | 131K |
| Llama3.1 70B Instruct Fp8 | $0.120 | $0.300 | 131K |
| Llama3.1 Nemotron 70B Instruct Fp8 | $0.120 | $0.300 | 131K |
| Llama3.3 70B Instruct Fp8 | $0.120 | $0.300 | 131K |
| DeepSeek Llama3.3 70B | $0.200 | $0.600 | 131K |
| DeepSeek R1 0528 | $0.200 | $0.600 | 131K |
| DeepSeek V3 0324 | $0.200 | $0.600 | 131K |
| DeepSeek R1 671B | $0.800 | $0.800 | 131K |
| Hermes3 405B | $0.800 | $0.800 | 131K |
| Llama3.1 405B Instruct Fp8 | $0.800 | $0.800 | 131K |
Frequently asked questions
How much does Lambda cost per 1M tokens?
Lambda pricing starts at $0.025 per 1 million output tokens (Llama3.2 11B Vision Instruct) across 20 models, with its current flagship DeepSeek R1 671B at $0.800. Older premium models in the catalog list higher. Rates current as of August 11, 2026.
What is the cheapest Lambda model?
Llama3.2 11B Vision Instruct is the cheapest Lambda model on both axes — $0.015 per 1M input tokens and $0.025 per 1M output. It is the right default for high-volume, low-complexity work such as classification, extraction and routing.
What is the largest Lambda context window?
DeepSeek Llama3.3 70B has the largest context window in the Lambda catalog at 131K input tokens, with up to 131K output tokens per response.
How do I calculate my actual Lambda bill?
Multiply your input tokens by the input rate and your output tokens by the output rate, both per million, then add retries and any conversation history resent on each turn. Calcaas does this against your real usage pattern and shows the margin left at your price point.
Other providers
What will this actually cost you?
Per-token rates only tell you half the story. Calcaas multiplies them by your real usage — prompt size, response length, retries and conversation history — then shows the margin left at your price point.
Open the free cost calculator