Llama 3.1 70B Instruct
Superseded at the same size and cost by Llama 3.3 70B — keep it only for pinned reproducibility of existing 3.1 evaluations or fine-tunes.
Data checked 2026-09-06
Meta
ga
open weights
meta-llama/Llama-3.1-70B-Instruct
- Context window
- 128K tokens in
- Max output
- —
- Input
- — per 1M tokens
- Output
- — per 1M tokens
- Knowledge cutoff
- 2023-12
- Released
- 2024-07-23
- Parameters
- 70B
- Licence
- Llama 3.1 Community License Agreement
A What it is for
Weights only, so both prices -1.
B Capabilities
chat multilingual tool-calling fine-tuning
| Input modalities | text |
|---|---|
| Output modalities | text |
C Others from Meta
| Model | Context | Max out | In $/M | Out $/M | Blended | Status |
|---|---|---|---|---|---|---|
Muse Spark 1.3
muse-spark-1.3
|
1M | — | $1.25 | $4.25 | $2.00 | ga |
Muse Spark 1.3 (Contributor tier)
muse-spark-1.3-contributor
|
1M | — | $0.10 | $0.20 | $0.13 | ga |
Muse Spark 1.2
muse-spark-1.2
|
1M | — | $1.25 | $4.25 | $2.00 | ga |
Muse Spark 1.2 (Contributor tier)
muse-spark-1.2-contributor
|
1M | — | $0.10 | $0.20 | $0.13 | ga |
Muse Spark 1.1
muse-spark-1.1
|
1M | — | $1.25 | $4.25 | $2.00 | ga |
Muse Image 1.0
muse-image-1.0
|
— | — | — | — | — | ga |
Muse Voice Transcribe 1.0
muse-voice-transcribe-1.0
|
— | — | — | — | — | ga |
Muse Glimmer 30B
meta-models/Muse-Glimmer-30B
|
131.1K | — | — | — | — | ga open |
Llama 4 Scout
meta-llama/Llama-4-Scout-17B-16E-Instruct
|
10M | — | — | — | — | ga open |
Llama 4 Maverick
meta-llama/Llama-4-Maverick-17B-128E-Instruct
|
1M | — | — | — | — | ga open |
Llama 3.3 70B Instruct
meta-llama/Llama-3.3-70B-Instruct
|
128K | — | — | — | — | ga open |
Llama 3.2 90B Vision Instruct
meta-llama/Llama-3.2-90B-Vision-Instruct
|
128K | — | — | — | — | ga open |
D Verify before you commit
Model pricing changes without notice and this page is a snapshot. Confirm against the vendor's own page before you build a budget on it.
Source: github.com · checked 2026-09-06 · Meta pricing · API docs