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 |
|---|---|---|---|---|---|---|
| $0.20 | $0.52 | $0.10 | 0.64s | 34 tps | 100% | |
| $0.59 | $0.79 | $0.29 | 0.54s | 190 tps | 100% | |
 CoreWeavefp16 | $0.71 | $0.71 | $0.71 | 0.21s | 72 tps | 99.69% |
| $0.29 | $2.25 | Variable | 0.70s | 39 tps | 99.64% | |
| $0.22 | $0.50 | $0.11 | 0.65s | 39 tps | 99.58% | |
| $0.45 | $0.90 | Variable | 0.71s | 103 tps | 99.53% | |
| $0.14 | $0.40 | Variable | 1.31s | 34 tps | 99.47% | |
 DeepInfra (Turbo)us · fp8 | $0.10 | $0.32 | Variable | 0.97s | 11 tps | 99.16% |
| $1.04 | $1.04 | Variable | 1.11s | 25 tps | 98.48% | |
 Google Vertexus-central1 | $0.72 | $0.72 | Variable | 1.51s | 101 tps | — |
| Google Vertex | $0.72 | $0.72 | Variable | — | — | — |
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
167.5B tokens processed market-wide in the last month.
FAQ
Explore
Other models your pass can call.
