Llama 3.3 70B
Best-quality Llama 3.x 70B; updated Dec 2024, text-only, widely hosted.
- Input
- $0.59 / 1M tokens
- Output
- $0.79 / 1M tokens
- Cached read
- — / 1M tokens
- Cached write
- — / 1M tokens
- Batch discount
- —%
- Source
- Llama 3.3 70B pricing
- Verified
- Apr 5, 2026 (High)
Capabilities
- Modalities
- text→text
- Capabilities
- batchSupportpromptCachingfunctionCallingstructuredOutputs
- Strengths
- Best open 70B text model, Wide hosting options
- Tradeoffs
- Text-only, no vision
Official Links
Benchmark Coverage
| Benchmark | Version | Score | Date | Source | Notes |
|---|---|---|---|---|---|
| MMLU | 2024 | 86 % | Dec 1, 2024 | Meta | Vendor-reported |
| HumanEval | 2024 | 88.4 % | Dec 1, 2024 | Meta | Vendor-reported |
| IFEval | 2024 | 92.1 % | Dec 1, 2024 | Meta | Vendor-reported |
Release History
| Release | Alias | Lifecycle | Release Date | Deprecation | Shutdown | Summary |
|---|---|---|---|---|---|---|
| Llama 3.3 70B | llama-3-3-70b | Active | Dec 6, 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 |
| Together AI | cloud | 128.0K | $0.88/$0.88 per MTok. | — |
Migration Guidance
Go-to 70B open model. Use Llama 4 for vision or very long context.
Replacement models: llama-4-scout
Change Events
| Date | Type | Title | Description | Source |
|---|---|---|---|---|
| Dec 6, 2024 | family_added | Llama 3.3 70B published | Initial public model family launch. | Llama 3.3 70B release notes |
Other models from Meta AI
Llama 3.1 405B, Llama 3.1 70B, Llama 3.1 8B, Llama 3.2 11B Vision, Llama 3.2 90B Vision, Llama 4 Maverick, Llama 4 Scout