Meta: Llama 3.3 70B Instruct
meta-llama/llama-3-3-70b-instructThe Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out).
Providers
11 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
| $0.59 | $0.79 | $0.29 | 0.36s | 226 tps | 100% | |
| $0.22 | $0.50 | $0.11 | 0.57s | 50 tps | 99.84% | |
 CoreWeavefp16 | $0.71 | $0.71 | $0.71 | 0.19s | 75 tps | 99.81% |
| $0.20 | $0.52 | $0.10 | 0.75s | 30 tps | 99.75% | |
 DeepInfra (Turbo)us · fp8 | $0.10 | $0.32 | Variable | 0.44s | 19 tps | 99.49% |
| $0.45 | $0.90 | Variable | 0.83s | 95 tps | 98.69% | |
| $0.29 | $2.25 | Variable | 1.67s | 29 tps | 98.32% | |
| $0.14 | $0.40 | Variable | 1.02s | 40 tps | 97.99% | |
| $1.04 | $1.04 | Variable | 0.99s | 65 tps | 95.83% | |
 Google Vertexus-central1 | $0.72 | $0.72 | Variable | 1.30s | 100 tps | — |
| Google Vertex | $0.72 | $0.72 | Variable | 6.54s | 78 tps | — |
Market-wide measurements, refreshed every 15 minutes. They describe who serves Llama 3.3 70B Instruct in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what Llama 3.3 70B Instruct costs pay-as-you-go elsewhere, not what you pay here.
Performance
Time to first token and output speed across every provider, over the last 3 days.
Uptime
100% of requests were served successfully over the last 3 days, across all providers.
Apps
Tools that most often run Llama 3.3 70B Instruct, by tokens this week.
Activity
167.8B tokens processed market-wide in the last month.
FAQ
Explore
Other models your pass can call.
