Llama 3.1 8B Instruct pricing
Llama 3.1 8B Instruct from Meta runs on 4 providers. The lowest price is $0.02 input and $0.04 output per 1M tokens, on DeepInfra. On CoreWeave it costs 8.8× as much.
Updated
- Lab
- Meta
- Context
- 131K
- Input
- Text
- Providers
- 4
DeepInfra$0.025Lowest
Groq$0.05752.3×
Cloudflare Workers AI$0.1867.4×- CoreWeave$0.228.8×
Every price, by provider
| Provider | Input | Output | Cached | Cache write | Batch in | Batch out | Context | Max output |
|---|---|---|---|---|---|---|---|---|
| DeepInfrafp8 | $0.02 | $0.04 | – | – | – | – | 131K | 16K |
| Groq | $0.05 | $0.08 | $0.025 | – | $0.025 | $0.04 | 131K | 118K |
| Cloudflare Workers AIfp8 | $0.152 | $0.287 | – | – | – | – | 32K | 29K |
| CoreWeavebf16 | $0.22 | $0.22 | $0.22 | – | – | – | 131K | 118K |
Prices in US dollars. Token prices are per 1 million tokens. abracadabra compiles them from each provider’s listing on OpenRouter, the LiteLLM price list and the providers’ own pricing pages, and refreshes them daily. The dataset is free to use: /api/ai-pricing.
See which tasks your agent finishes.
A price says what a call costs. abracadabra reads every conversation your agent has and shows the topics people bring, the tasks that get done and the turn where the rest stop.
Free to start, no card. Or open the playground (opens in a new tab).