Meta: Llama 3.1 8B Instruct
Open Llama instruction model for multilingual chat, reasoning, and coding
Cheapest input
$0.03
$/MTok · LiteLLM
Cheapest output
$0.05
$/MTok
Context
128K
tokens
Offers
5
2 sources
Offers
Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| LiteLLMcheapestllamagate/llama-3.1-8b | — | $0.03 | $0.05 | $0.003 | — |
| LiteLLMmeta/llama-3.1-8b | — | $0.05 | $0.08 | $0.005 | — |
| LiteLLMllama-3.1-8b | — | $0.05 | $0.08 | $0.005 | — |
| LiteLLMvercel_ai_gateway/meta/llama-3.1-8b | — | $0.05 | $0.08 | $0.005 | — |
| models.devmeta/llama-3.1-8b | Vercel AI Gateway | $0.22 | $0.22 | $0 | 128K |
Capabilities
- Tool calling
- In: text
- Out: text
Knowledge cutoff: 2023-12Released: 2024-07-23Family: llama
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Full boards on /benchmarks.
- AA intelligence7.6
- AA coding5.4
- AA agentic0.5
Sources: Arena AI, Artificial Analysis. See /benchmarks.