Compare model prices
Input, output, cached and batch prices, every route and a month of tokens, side by side.
Llama 3.1 8B InstructMuse Spark 1.3A month of tokens
100M input and 20M output tokens, list price. Use your own numbers.
Side by side
| Llama 3.1 8B Instruct | Muse Spark 1.3 | |
|---|---|---|
| Input per 1M | $0.02 | $1.25 |
| Output per 1M | $0.04 | $4.25 |
| Cached input | n/a | $0.15 |
| Batch in / out | n/a | n/a |
| Blended (3:1) | $0.025 | $2 |
| Context | 131K | 1M |
| Routes | 5 | 1 |
| Released | Jul 23, 2024 | 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 3.1 8B Instruct
| Way to buy | Input | Output | In / out per 1M | Cached | Vs list |
|---|---|---|---|---|---|
 DeepInfrafp8 | $0.02 | $0.04 | $0.02 / $0.04Same as list | n/a | Same as list |
 Novita AIfp8 | $0.02 | $0.05 | $0.02 / $0.05+10% vs list | n/a | +10% vs list |
 GroqDefault region · cached $0.025 | $0.05 | $0.08 | $0.05 / $0.08+130% vs list | $0.025 | +130% vs list |
 Cloudflare Workers AIfp8 | $0.152 | $0.287 | $0.152 / $0.287+643% vs list | n/a | +643% vs list |
 CoreWeavebf16 · cached $0.22 | $0.22 | $0.22 | $0.22 / $0.22+780% vs list | $0.22 | +780% 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.