Llama 3.3 70B Instruct
Novita textnovita/meta-llama/llama-3.3-70b-instruct
Input
$0.1350
per 1M input tokens
Output
$0.4000
per 1M output tokens
Cache read
n/a
per 1M cached read tokens
Cache write
n/a
per 1M cache write tokens
Context window
12,288
Max output
12,288
Effective date
Aug 28, 2026
Estimate a workload
Enter token counts to see the cost at this model's rates.
Estimated cost:
$0.00
Price history
blended $ per 1M tokens (3:1)| Effective | Input | Output | Blended |
|---|---|---|---|
| Aug 28, 2026 | $0.14 | $0.40 | $0.20 |
| Jun 15, 2026 | $0.14 | $0.40 | $0.20 |
Llama 3.3 70B Instruct on other providers
Hyperbolic
· $0.1200 in / $0.3000 out
Nebius
· $0.1300 in / $0.4000 out
Crusoe
· $0.2000 in / $0.2000 out
Inferenceapis
· $0.2000 in / $0.5000 out
Inferenceapis
· $0.2000 in / $0.5000 out
Nscale
· $0.2000 in / $0.2000 out
Openrouter
· $0.2200 in / $0.5000 out
Deepinfra
· $0.2300 in / $0.4000 out
Gmi
· $0.2500 in / $0.7500 out
Azure OpenAI
· $0.7100 in / $0.7100 out
Wandb
· $0.7100 in / $0.7100 out
Scaleway
· $0.9000 in / $0.9000 out
Other Novita models
novita/baai/bge-m3
· $0.0100/Mtok out
novita/baai/bge-reranker-v2-m3
· $0.0100/Mtok out
novita/paddlepaddle/paddleocr-vl
· $0.0200/Mtok out
novita/meta-llama/llama-3.1-8b-instruct
· $0.0500/Mtok out
novita/meta-llama/llama-3.2-1b-instruct
· $0.0200/Mtok out
novita/qwen/qwen3-4b-fp8
· $0.0300/Mtok out
Source: litellm. Confirm against the provider's official pricing before relying on these figures.