Accelerate your AI development with Lambda, The Superintelligence Cloud. Access AI supercomputers, NVIDIA GB300 NVL72, HGX B300, B200, and H200 GPUs, and private, secure clusters for training and inference at scale.
| Model Name | Context Window | Input Cost (1M) | Output Cost (1M) | Capabilities | |
|---|---|---|---|---|---|
lambda_ai/deepseek-llama3.3-70b | 131,072 | $0.20 | $0.60 | toolstextfunction calling | |
lambda_ai/deepseek-r1-0528 | 131,072 | $0.20 | $0.60 | toolstextfunction calling | |
lambda_ai/deepseek-r1-671b | 131,072 | $0.80 | $0.80 | toolstextfunction calling | |
lambda_ai/deepseek-v3-0324 | 131,072 | $0.20 | $0.60 | toolstextfunction calling | |
lambda_ai/hermes3-405b | 131,072 | $0.80 | $0.80 | toolstextfunction calling | |
lambda_ai/hermes3-70b | 131,072 | $0.12 | $0.30 | toolstextfunction calling | |
lambda_ai/hermes3-8b | 131,072 | $0.025 | $0.04 | toolstextfunction calling | |
lambda_ai/lfm-40b | 131,072 | $0.10 | $0.20 | toolstextfunction calling | |
lambda_ai/lfm-7b | 131,072 | $0.025 | $0.04 | toolstextfunction calling | |
lambda_ai/llama-4-maverick-17b-128e-instruct-fp8 | 131,072 | $0.05 | $0.10 | toolstextfunction calling | |
lambda_ai/llama-4-scout-17b-16e-instruct | 16,384 | $0.05 | $0.10 | toolstextfunction calling | |
lambda_ai/llama3.1-405b-instruct-fp8 | 131,072 | $0.80 | $0.80 | toolstextfunction calling | |
lambda_ai/llama3.1-70b-instruct-fp8 | 131,072 | $0.12 | $0.30 | toolstextfunction calling | |
lambda_ai/llama3.1-8b-instruct | 131,072 | $0.025 | $0.04 | toolstextfunction calling | |
lambda_ai/llama3.1-nemotron-70b-instruct-fp8 | 131,072 | $0.12 | $0.30 | toolstextfunction calling | |
lambda_ai/llama3.2-11b-vision-instruct | 131,072 | $0.015 | $0.025 | toolstextimagefunction calling | |
lambda_ai/llama3.2-3b-instruct | 131,072 | $0.015 | $0.025 | toolstextfunction calling | |
lambda_ai/llama3.3-70b-instruct-fp8 | 131,072 | $0.12 | $0.30 | toolstextfunction calling | |
lambda_ai/qwen25-coder-32b-instruct | 131,072 | $0.05 | $0.10 | toolstextfunction calling | |
lambda_ai/qwen3-32b-fp8 | 131,072 | $0.05 | $0.10 | toolstextfunction calling |
Monthly plans, quota windows, weighted premium credits, and API access entitlement for this provider.
Status: active
Price not published
Partial data: verify provider docs for complete plan terms.
Quota windows: No quota windows documented
Premium credits: No premium credit rules documented
API access: unknown
Production-ready clusters from 16 to 2,000+ NVIDIA B200 or H100 GPUs. Pricing is per hour. Monthly billing amount is not explicitly published on the source page.
Source: https://lambda.ai/pricing · Verified: 2026-03-18T09:08:48.684Z · Confidence: high
Status: active
Price not published
Partial data: verify provider docs for complete plan terms.
Quota windows: No quota windows documented
Premium credits: No premium credit rules documented
API access: unknown
Reserved capacity plans available for 1, 2, and 3 years; pricing requires contacting sales. Monthly billing amount is not explicitly published on the source page.
Source: https://lambda.ai/pricing · Verified: 2026-03-18T09:08:48.684Z · Confidence: high