Llama 3.1 70B Instruct
Open Llama instruction model for multilingual chat, reasoning, and coding
- Context
- 131K
- Released
- —
- Parameters
- 70B
- Input / 1M tokens
- $0.40
- Output / 1M tokens
- $0.40
Sources:models.devOpenRouter
Benchmarks
DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.
Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.
Other published benchmarks
| Evaluation | Reported score and source |
|---|---|
| GPQA diamond | |
| OTIS Mock AIME 2024-2025 |
Benchmark compilation: Epoch AI, Capabilities & benchmarking (CC BY attribution). Scores are converted to percentages and model names matched to the Vertical Tabs catalog. Individual evaluations are credited to their original sources. External results may carry separate licences and evaluation configurations; do not interpret scores from different harnesses as directly comparable.
Specifications
- Developer
- Meta
- Model family
- Llama
- Type
- Language model
- Predecessor
- —
- Successor
- —
- Released
- —
- Model ID
meta-llama/llama-3.1-70b-instruct- Openness
- Open weights
- License
- —
- Parameters
- 70B
- Input modalities
- text
- Output modalities
- text
- Modality
- text->text
- Native context
- 128K
- Tokenizer
- Llama3
- Max output tokens
- 16K
- Knowledge cutoff
- 2023-12
- Hugging Face
- meta-llama/Meta-Llama-3.1-70B-Instruct
- Source freshness
- Metadata synced Oct 8, 2026, 10:17 PM UTC
Additional source evidence
- Source model
- meta/llama-3.1-70b-instruct
- Source family
- llama
- Last updated
- 2024-07-23
- Knowledge cutoff
- 2023-12
- Model context
- 128K
- Model output limit
- 4K
- Open weights
- Yes
- File attachments
- No
- Reasoning
- No
- Tool calling
- Yes
- Temperature control
- Yes
Downloadable weights
Complete source record (JSON)
{
"id": "meta/llama-3.1-70b-instruct",
"name": "Llama-3.1-70B-Instruct",
"description": "Open Llama instruction model for multilingual chat, reasoning, and coding",
"family": "llama",
"last_updated": "2024-07-23",
"knowledge": "2023-12",
"attachment": false,
"reasoning": false,
"tool_call": true,
"temperature": true,
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 4096
},
"release_date": "2024-07-23",
"open_weights": true,
"weights": [
{
"label": "Hugging Face",
"url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct"
}
]
}Infrastructure
Provider availability
| Provider | Endpoint | Context | Input /M tokens | Output /M tokens | Cached input /M tokens | Cache write /M tokens | Uptime 1d | Data handling |
|---|---|---|---|---|---|---|---|---|
| deepinfra/turbo | 131K | $0.40 | $0.40 | — | — | 96.29% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
 Amazon Bedrock | amazon-bedrock | 131K | $0.72 | $0.72 | — | — | 100.00% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 |
Provider data:OpenRouter
Deployment graph
Can I run this?
Vertical Tabs only shows compatibility when it has structured evidence tying this exact model to hardware, runtime, quantization, memory use, and observed performance.