Llama 3.1 8B Instruct
- Input / output
- $0.02 / $0.04
- Providers
- 4
- Spread
- 8.8×
- 7 days
- 0%
- 30 days
- 0%
- Context
- 128K
Providers
| Provider | Input | Output | Blended | vs ref | Context | Uptime 1d | Price since |
|---|---|---|---|---|---|---|---|
DeepInfraCheapest fp8 | $0.02 | $0.04 | $0.025 | ref | |||
| $0.05 | $0.08 | $0.0575 | +130% | ||||
| fp8 | $0.152 | $0.287 | $0.186 | +643% | |||
| bf16 | $0.22 | $0.22 | $0.22 | +780% |
- DeepInfraCheapest$0.025$0.02 in · $0.04 outref vs ref128K ctx97.8% uptimefp8
- $0.0575$0.05 in · $0.08 out+130% vs ref128K ctx99.9% uptime
- $0.186$0.152 in · $0.287 out+643% vs ref32K ctx99.8% uptimefp8
- $0.22$0.22 in · $0.22 out+780% vs ref128K ctx99.9% uptimebf16
Blended = (3 × input + output) / 4. Ref $0.025 = median of cheapest 20%.
Price history
USD per 1M tokens · each step is a price change
Prices in USD / 1M tokens.
No provider has changed its price since tracking began on Oct 3, 2026.
Other pricing
| Offered by | Cache read |
|---|---|
| Groq | $0.025 |
| CoreWeave | $0.22 |
Changes
- DelistedNo longer served,Delisted
About
The cheapest provider for Llama 3.1 8B Instruct is DeepInfra at $0.025 per 1M tokens (blended), charging $0.02 per 1M input and $0.04 per 1M output tokens. 4 providers serve it; the most expensive charges 8.8× the typical price. Context window: 128K tokens. Prices tracked since Oct 3, 2026.
Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to...
- Released
- Jul 23, 2024
- First tracked
- Oct 3, 2026
- Canonical slug
- meta-llama/llama-3.1-8b-instruct
- Weights
- meta-llama/Meta-Llama-3.1-8B-Instruct