Llama 3.1 70B
Workhorse open-weight 70B — good quality/cost ratio, widely hosted.
- Input
- $0.59 / 1M tokens
- Output
- $0.79 / 1M tokens
- Cached read
- — / 1M tokens
- Cached write
- — / 1M tokens
- Batch discount
- —%
- Source
- Llama 3.1 70B pricing
- Verified
- Apr 5, 2026 (High)
Capabilities
- Modalities
- text→text
- Capabilities
- batchSupportpromptCachingfunctionCallingstructuredOutputs
- Strengths
- Widely hosted, Strong open 70B
- Tradeoffs
- Text-only, 8K output
Official Links
Benchmark Coverage
| Benchmark | Version | Score | Date | Source | Notes |
|---|---|---|---|---|---|
| MMLU | 2024 | 86 % | Jul 1, 2024 | Meta | Vendor-reported |
Release History
| Release | Alias | Lifecycle | Release Date | Deprecation | Shutdown | Summary |
|---|---|---|---|---|---|---|
| Llama 3.1 70B | llama-3-1-70b | Active | Jul 23, 2024 | — | — | Current published model family snapshot. |
Host Coverage
| Host | Type | Context | Pricing Note | Differences |
|---|---|---|---|---|
| Groq | cloud | 128.0K | $0.59/$0.79 per MTok. | Fast inference |
| DeepInfra | cloud | 128.0K | $0.23/$0.23 per MTok. | — |
Migration Guidance
Consider Llama 3.3 70B for better quality at similar cost.
Replacement models: llama-3-3-70b
Change Events
| Date | Type | Title | Description | Source |
|---|---|---|---|---|
| Jul 23, 2024 | family_added | Llama 3.1 70B published | Initial public model family launch. | Llama 3.1 70B release notes |
Other models from Meta AI
Llama 3.1 405B, Llama 3.1 8B, Llama 3.2 11B Vision, Llama 3.2 90B Vision, Llama 3.3 70B, Llama 4 Maverick, Llama 4 Scout