Compare model prices
Input, output, cached and batch prices, every route and a month of tokens, side by side.
Llama 4 MaverickMuse Spark 1.3A month of tokens
100M input and 20M output tokens, list price. Use your own numbers.
Side by side
| Llama 4 Maverick | Muse Spark 1.3 | |
|---|---|---|
| Input per 1M | $0.188 | $1.25 |
| Output per 1M | $0.653 | $4.25 |
| Cached input | n/a | $0.15 |
| Batch in / out | n/a | n/a |
| Blended (3:1) | $0.304 | $2 |
| Context | 1M | 1M |
| Routes | 6 | 1 |
| Released | Apr 5, 2025 | Sep 2, 2026 |
| Leadersboard score | n/a | 19 (#8) |
On the price map
Size: context window, 8K to 2MEqual blended cost (3:1) 243 models, lower left is cheaper
Every route
Llama 4 Maverick
| Way to buy | Input | Output | In / out per 1M | Cached | Vs list |
|---|---|---|---|---|---|
 DigitalOceanDefault region | $0.188 | $0.653 | $0.188 / $0.653Same as list | n/a | Same as list |
 DeepInfrabase, fp8 | $0.2 | $0.8 | $0.2 / $0.8+15% vs list | n/a | +15% vs list |
 Novita AIfp8 | $0.27 | $0.85 | $0.27 / $0.85+37% vs list | n/a | +37% vs list |
 Parasailfp8 · cached $0.17 | $0.35 | $1 | $0.35 / $1+69% vs list | $0.17 | +69% vs list |
 Google Vertex AIus-east5 | $0.35 | $1.15 | $0.35 / $1.15+81% vs list | n/a | +81% vs list |
 IBM watsonx.aiFrom the platform pricing page | $0.371 | $1.48 | $0.371 / $1.48+114% vs list | n/a | +114% vs list |
Muse Spark 1.3
| Way to buy | Input | Output | In / out per 1M | Cached | Vs list |
|---|---|---|---|---|---|
| Meta API The lab's own API · cached $0.15 | $1.25 | $4.25 | $1.25 / $4.25List price | $0.15 | List price |
List prices from providers' pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.