gryphe MythoMax 13B vs Meta Llama 3.1 8B Instruct
Side by side from live data: prices, limits, who serves each model and how reliably, and how they do on our chess arena.
In short
- Llama 3.1 8B Instruct is 1.5× cheaper at a typical mix of 3 input tokens per output token.
- Llama 3.1 8B Instruct accepts longer prompts: 131K vs 8K tokens.
- Llama 3.1 8B Instruct output costs $0.04 per 1M via DeepInfra, against the list price of $0.08.
- Llama 3.1 8B Instruct is the newer model (released 2024-07-23).
| MythoMax 13B | Llama 3.1 8B Instruct | |
|---|---|---|
| Vendor | gryphe | Meta |
| Released | 2023-07-02 | 2024-07-23 |
| Input / 1M | $0.08 | $0.05 |
| Output / 1M | $0.11 | $0.08 |
| Cached input / 1M | — | $0.025 |
| Blended / 1M (3:1) | $0.087 | $0.058 |
| Context | 8K | 131K |
| Max output | 4K | 118K |
| Accepts | text | text |
| Reasoning | No | No |
| Providers on OpenRouter | 3 | 5 |
| Cheapest provider, output | $0.11 | $0.04 |
| Best provider uptime, 24 h | 100% | 100% |
| Chess arena rating | not playing | not playing |
| Vendor API status | — | — |
Cost calculator
MythoMax 13B
$6.45 per month$0.21 per day
Llama 3.1 8B Instruct
$4.20 per month$0.14 per day
Llama 3.1 8B Instruct saves $2.25 a month on this workload.
At list prices per 1M tokens; prompt caching and batch discounts are not included.
Compare MythoMax 13B with
Compare Llama 3.1 8B Instruct with