// Meta
Llama 3.1 8B Instruct
A Meta model. 3 prices across 3 channels side by side, each with its source and check date – plus specs, licence, speed and benchmarks.
- Official in/out per 1M
- —
- Lowest (DeepInfra)
- $0.02 / $0.04
- Context
- 131K
- AA index
- 6.9
Prices checked 2026-10-22Official sources linked on every rowNo estimatesCheapest LLM APIs →
01Specs at a glance
Official values first; gaps filled from OpenRouter’s API where the vendor page is silent.
| Vendor | Meta |
|---|---|
| Context window | 131K (131,072 tokens) |
| Max output | 16K |
| Input | Text |
| Output | Text |
| Tool calling / JSON | Yes / Yes |
| Weights & licence | Open weights · Llama 3.1 Community · Hugging Face gated – request access |
| Parameters | 8B (from weight files) |
| Released | Jul 23, 2024 |
| Model IDs | meta-llama/llama-3.1-8b-instruct |
02Prices on 3 channels
Per 1M tokens, in the currency each source publishes (1 USD = 6.7 CNY for the blended column). Sorted: official first, then cheapest.
| Channel | Source | Input | Output | Cache hit | Blended $ | Context | Notes |
|---|---|---|---|---|---|---|---|
| DeepInfra · fp8 Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.02 | $0.04 | — | 0.025 | 131K | DeepInfra price as listed on OpenRouter (pass-through; quantization=fp8; discount field=0); not checked against DeepInfra's own page |
| Novita · fp8 Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.02 | $0.05 | — | 0.028 | 16K | Novita price as listed on OpenRouter (pass-through; quantization=fp8; discount field=0); not checked against Novita's own page |
| Groq · unknown Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.05 | $0.08 | $0.025 | 0.058 | 131K | Groq price as listed on OpenRouter (pass-through; quantization=unknown; discount field=0); not checked against Groq's own page |
“Official” = vendor pricing page; “Platform” = the platform’s own pricing page; “OpenRouter” = price listed on OpenRouter, not checked on the platform’s site. Click a source tag to open the original page.
03Where you can use it
Derived only from the price sources above. Country restrictions are set by each vendor – check their terms before you sign up.
- Via OpenRouter / provider listed there
DeepInfra · Novita · Groq - Self-host the open weights
GPU / VRAM sizing and build plans→ - Free option
Llama-3.1-8B-Instruct→
04Performance
All results →Speed and AA index from Artificial Analysis public leaderboards (not our own tests); benchmark scores from our benchmark library, best result per benchmark.
- AA indexLlama 3.1 Instruct 8B
- 6.9
- Output speed (median)
- 137 tok/s
- Time to first token
- 0.85s
- AA index per $ (blended)
- 277.34
| Benchmark | Best score | Source | Date |
|---|---|---|---|
| LMArena Text | 1211 | official | 2026-10-08 |
| Open LLM Leaderboard v2 | 23.8% | official | 2025-03-13 |
| GPQA Diamond | 27.0% | independent | 2026-08-27 |
| MMLU | 56.1% | official | 2024-07-23 |
| MMLU-Pro | 36.6% | official | 2026-03-11 |
| AIME (OTIS Mock AIME 2024–2025) | 1.7% | independent | 2026-08-27 |
| MATH Level 5 | 22.9% | independent | 2025-01-27 |
| BFCL v4 (function calling) | 25.8% | official | 2026-10-17 |
05Price changes we recorded
All price changes →From our daily re-checks of the sources above.
No price change recorded since we started tracking (2026-10-10).
06More from Meta
FAQ
How much does the Llama 3.1 8B Instruct API cost?
There is no official pay-as-you-go price in our data. The lowest listed price is $0.02 / $0.04 on DeepInfra.
What is the context window of Llama 3.1 8B Instruct?
131K tokens of context, up to 16K output tokens. Platforms may cap it lower – see the table.
Is Llama 3.1 8B Instruct open source?
Yes, the weights are published on Hugging Face (meta-llama/Meta-Llama-3.1-8B-Instruct). Licence: Llama 3.1 Community.