Llama 4 Scout vs Mixtral 8x7B Instruct
Side-by-side comparison of API pricing, specs, benchmarks, and capabilities
|
Dby DeepInfra
3 providers:
Groq $0.110/$0.340
Meta $0.110/$0.340
DeepInfra $0.100/$0.300
|
Mby Mistral
|
|
|---|---|---|
| Overview | ||
| Status | Current open weights Open weights | Current open weights Open weights |
| Released | Apr 6, 2025 | Jul 1, 2024 |
| Pricing per million tokens | ||
| Input | $0.100/Mtok | $0.700/Mtok |
| Output | $0.300/Mtok | $0.700/Mtok |
| Blended avg | $0.200/Mtok | $0.700/Mtok |
| Specifications | ||
| Context window | 10M tokens | 32K tokens |
| Parameters | 17B (16 experts) | 46.7B (8x7B MoE) |
| Speed (TPS) | — | — |
| Modalities | ||
| Input |
textimage
|
text
|
| Providers | ||
| Available from |
Groq — $0.110/$0.340/Mtok
Meta — $0.110/$0.340/Mtok
DeepInfra — $0.100/$0.300/Mtok
|
Mistral — $0.700/$0.700/Mtok
|
Cost at scale — 1M tokens (50/50 input/output)
| Volume | Llama 4 Scout | Mixtral 8x7B Instruct | Savings |
|---|---|---|---|
| 1M tokens | $0.2 | $0.7 | $0.5 (71.4%) |
| 10M tokens | $2 | $7 | $5 (71.4%) |
| 100M tokens | $20 | $70 | $50 (71.4%) |
| 1000M tokens | $200 | $700 | $500 (71.4%) |
Summary
Llama 4 Scout by DeepInfra costs $0.100/Mtok input and $0.300/Mtok output, with a 10M-token context window. It supports text, image input and is available from 3 providers.
Mixtral 8x7B Instruct by Mistral costs $0.700/Mtok input and $0.700/Mtok output, with a 32K-token context window. It supports text input.
On a blended cost basis, Llama 4 Scout is 71.4% cheaper than Mixtral 8x7B Instruct. It also has a larger context window.
Note: Pricing is per million tokens. Actual costs vary with usage patterns, prompt caching, and batch discounts. Always verify against official provider pricing pages.