Llama 3.3 70B Instruct
Toolsmeta/llama-3.3-70b-instructText · 131K context · Dec 2024 · 17 upstreamsupstream上游
Llama 3.3 70B Instruct is Meta's open-weight instruction-tuned model with 70B parameters and a 131072-token context window. It is tuned for multilingual dialogue, with tool use on par with Llama 3.1 70B. It suits chat, reasoning, and coding.
Needs your own keyTo use Llama 3.3 70B Instruct, add a key from FPT Cloud, Hugging Face, OpenRouter or 14 more. AnyRouter adds no fee.
- contextngữ cảnh上下文
- 131K
- inputđầu vào输入 / 1M (list)
- $0.10
- outputđầu ra输出 / 1M (list)
- $0.32
- routestuyến路由
- 17
- speed, 24htốc độ, 24h速度,24h
- No data yetChưa có dữ liệu暂无数据
Upstreams
17- 1FPT CloudBYOKnot addedBilled to your key
- 2Hugging FaceBYOKnot addedBilled to your key
- 3OpenRouterBYOKnot addedBilled to your key
- 4AIHubMixBYOKnot addedBilled to your key
- 5OVHcloudBYOKnot addedBilled to your key
- 6NovitaAIBYOKnot addedBilled to your key
- 7Nous ResearchBYOKnot addedBilled to your key
- 8inference.netBYOKnot addedBilled to your key
- 9LLM GatewayBYOKnot addedBilled to your key
- 10InfronBYOKnot addedBilled to your key
- 11PhalaBYOKnot addedBilled to your key
- 12ZenMuxBYOKnot addedBilled to your key
- 13NanoGPTBYOKnot addedBilled to your key
- 14FluenceBYOKnot addedBilled to your key
- 15CortecsBYOKnot addedBilled to your key
- 16HeliconeBYOKnot addedBilled to your key
- 17Jiekou.AIBYOKnot addedBilled to your key
Benchmarks
- GPQA Diamond
- 47.4%
Benchmark data from Epoch AI (CC-BY 4.0).
Compare
Compared with its other versions and models of similar price and context window.
| Model | In / out per 1M | Context | SciCode | GPQA Diamond | |
|---|---|---|---|---|---|
| Llama 3.3 70B Instruct | $0.10 / $0.32 (second best) | 131K (second best) | 26.0% | 47.4% | |
| Llama 3.1 70B Instruct | $0.40 / $0.40 | 131K (second best) | 26.7% | 40.9% | |
| Llama 4 Scout 17B 16E | $0.10 / $0.30 (best) | 131K (second best) | 17.0% | 51.8% | |
| Llama 4 Maverick | $0.18 / $0.57 | 524K (best) | – | – | |
| Mistral Small 3.1 24B Instruct | $0.10 / $0.30 (best) | 128K | – | – |
Benchmark data from Epoch AI (CC-BY 4.0).
Quick start
curl https://anyrouter.dev/api/v1/chat/completions \
-H "Authorization: Bearer $ANYROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "meta/llama-3.3-70b-instruct",
"messages": [
{
"role": "user",
"content": "Say hi in 3 words."
}
]
}'Details
- Owner
- Meta
- Kind
- Chat
- Released
- Dec 2024
- Context
- 131K
- Data policy
- Provider retention
- Endpoint
/api/v1/chat/completions
- Assistant-style chat
- Synthetic data generation and distillation
- Multilingual commercial and research use
Architecture and licenseKiến trúc và giấy phép架构与许可
- Total parametersTổng tham số总参数
- 70B[1]
- Native contextNgữ cảnh gốc原生上下文
- 131,072[1]
- Training cutoffMốc dữ liệu训练截止
- 2023-12[1]
- LicenseGiấy phép许可
- Llama 3.3 Community License Agreement · Open weightsTrọng số mở开放权重[1]
StrengthsĐiểm mạnh优势[1]
- Tuned for multilingual dialogue
- Tool use on par with Llama 3.1 70B (BFCL v2 77.3)
Known limitsGiới hạn đã biết已知局限[1]
- Eight supported languages; others need fine-tuning
- Can give inaccurate, biased or objectionable answers
- Static model trained on an offline dataset
Links and versionsLiên kết và phiên bản链接与版本
- AnnouncementBài công bố发布公告
- llama.com
- Model cardThẻ mô hình模型卡
- github.com
- Previous versionPhiên bản trước上一版本
- meta/llama-3.1-70b-instruct
SourcesNguồn来源
- [1]Llama 3.3 Model Card (meta-llama/llama-models)accessedtruy cập访问于 2026-10-14
Upstreams and pricingUpstream và giá上游与价格
Share cards18 images


















AliasesBí danh别名 (2)
meta-llama/llama-3.3-70b-instructmeta/llama-3.3-70b-instruct-fp8-fast
Uptime + latency
—recent checks · all routes
No health checks recorded for this model yet.
24h
No traffic in the last 24h.
Across all upstreams
Loading usage…