Lambda Labs: Models Intelligence, Performance & Price
Analysis of Lambda Labs's models across key metrics including quality, price, output speed, latency, context window & more. This analysis is intended to support you in choosing the best model provided by Lambda Labs for your use-case. For more details including relating to our methodology, see our FAQs. Models analyzed: Llama 3.3 70B (FP8), Llama 3.1 405B (FP8), Llama 4 Maverick (FP8), Llama 4 Scout, DeepSeek R1, DeepSeek R1 Distill Llama 70B, LFM 40B, Llama 3.1 Nemotron 70B (FP8), Llama 3.1 70B (FP8), Llama 3.1 8B, Llama 3.2 3B (FP8), and Qwen2.5 Coder 32B.
Link:
Lambda Labs Model Comparison Summary
Intelligence:
DeepSeek R1 and 
Llama 4 Maverick (FP8) are the highest quality models offered by Lambda Labs, followed by DeepSeek R1 Distill Llama 70B, Llama 4 Scout & Llama 3.3 70B (FP8).Output Speed (tokens/s): Llama 3.2 3B (FP8) (223 t/s) and 
LFM 40B (165 t/s) are the fastest models offered by Lambda Labs, followed by Llama 3.1 8B, Llama 4 Maverick (FP8) & Llama 4 Scout.Latency (seconds): LFM 40B (0.19s) and Llama 3.2 3B (FP8) (0.22s) are the lowest latency models offered by Lambda Labs, followed by Llama 3.1 8B, Llama 4 Scout & Llama 3.3 70B (FP8).Blended Price ($/M tokens): Llama 3.2 3B (FP8) ($0.02) and Llama 3.1 8B ($0.03) are the cheapest models offered by Lambda Labs, followed by 
Qwen2.5 Coder 32B, Llama 4 Scout & LFM 40B.Context Window Size: Llama 4 Maverick (FP8) (1m) and Llama 4 Scout (1m) are the largest context window models offered by Lambda Labs, followed by DeepSeek R1, Llama 3.3 70B (FP8) & Llama 3.1 405B (FP8).
DeepSeek R1 and Llama 4 Maverick (FP8) are the highest quality models offered by Lambda Labs, followed by DeepSeek R1 Distill Llama 70B, Llama 4 Scout & Llama 3.3 70B (FP8).Output Speed (tokens/s): Llama 3.2 3B (FP8) (223 t/s) and LFM 40B (165 t/s) are the fastest models offered by Lambda Labs, followed by Llama 3.1 8B, Llama 4 Maverick (FP8) & Llama 4 Scout.Latency (seconds): LFM 40B (0.19s) and Llama 3.2 3B (FP8) (0.22s) are the lowest latency models offered by Lambda Labs, followed by Llama 3.1 8B, Llama 4 Scout & Llama 3.3 70B (FP8).Blended Price ($/M tokens): Llama 3.2 3B (FP8) ($0.02) and Llama 3.1 8B ($0.03) are the cheapest models offered by Lambda Labs, followed by Qwen2.5 Coder 32B, Llama 4 Scout & LFM 40B.Context Window Size: Llama 4 Maverick (FP8) (1m) and Llama 4 Scout (1m) are the largest context window models offered by Lambda Labs, followed by DeepSeek R1, Llama 3.3 70B (FP8) & Llama 3.1 405B (FP8).Highlights
Intelligence
Artificial Analysis Intelligence Index; Higher is better
Speed
Output Tokens per Second; Higher is better
Price
USD per 1M Tokens; Lower is better
Parallel Queries:
Prompt Length:
Features | Model Intelligence | Price | Output tokens/s | Latency | End-to-End Response Time | ||||
|---|---|---|---|---|---|---|---|---|---|
Further Analysis | |||||||||
 | DeepSeek R1 | 164k | 60 | $0.95 | 38.3 | 0.37 | 74.63 | 61.21 | |
| Llama 4 Maverick (FP8) | 1m | 51 | $0.28 | 125.7 | 0.35 | 4.33 | N/A | |
| DeepSeek R1 Distill Llama 70B | 128k | 48 | $0.30 | 64.3 | 0.31 | 39.21 | 31.12 | |
| Llama 4 Scout | 1m | 43 | $0.14 | 107.7 | 0.30 | 4.95 | N/A | |
| Llama 3.3 70B (FP8) | 128k | 41 | $0.17 | 48.0 | 0.31 | 10.73 | N/A | |
| Llama 3.1 405B (FP8) | 128k | 40 | $0.80 | 32.6 | 0.34 | 15.67 | N/A | |
|  Llama 3.1 Nemotron 70B (FP8) | 128k | 37 | $0.17 | 50.7 | 0.31 | 10.18 | N/A | |
| Qwen2.5 Coder 32B | 33k | 36 | $0.09 | 42.7 | 0.32 | 12.03 | N/A | |
| Llama 3.1 70B (FP8) | 128k | 35 | $0.17 | 50.6 | 0.31 | 10.20 | N/A | |
| Llama 3.1 8B | 128k | 24 | $0.03 | 141.6 | 0.23 | 3.76 | N/A | |
| LFM 40B | 32k | 22 | $0.15 | 164.7 | 0.19 | 3.23 | N/A | |
| Llama 3.2 3B (FP8) | 128k | 20 | $0.02 | 222.9 | 0.22 | 2.46 | N/A | |
Key definitions
Context window: Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).
Output Speed: Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).
Latency (Time to First Token): Time to first token received, in seconds, after API request sent. For reasoning models which share reasoning tokens, this will be the first reasoning token. For models which do not support streaming, this represents time to receive the completion.
Price: Price per token, represented as USD per million Tokens. Price is a blend of Input & Output token prices (3:1 ratio).
Output Price: Price per token generated by the model (received from the API), represented as USD per million Tokens.
Input Price: Price per token included in the request/message sent to the API, represented as USD per million Tokens.
Time period: Metrics are 'live' and are based on the past 72 hours of measurements, measurements are taken 8 times a day for single requests and 2 times per day for parallel requests.