Llama-3.3-70B-Instruct-Turbo pricing
Llama-3.3-70B-Instruct-Turbo, Mid-tier from DeepInfra, costs $0.10 per 1M input tokens and $0.32 per 1M output tokens.
Input$0.10per 1M tokens
Output$0.32per 1M tokens
Context window128Ktokens
TierMidDeepInfra
Price your own workload against Llama-3.3-70B-Instruct-Turbo in the calculator →
Specs and pricing
| Provider | DeepInfra |
| Tier | Mid |
| Context window | 128K tokens |
| Max output | — |
| Input price | $0.10 / 1M tokens |
| Output price | $0.32 / 1M tokens |
| Modalities | text |
Note. Widely used open-weights model; context listed on page as '128k'.
What it costs at realistic volumes
Assuming a 4:1 input:output token ratio, a common shape for chat and RAG-style workloads:
| Volume (4:1 in:out ratio) | Input cost | Output cost | Total / month |
|---|---|---|---|
| 1,000,000 in / 250,000 out | $0.10 | $0.08 | $0.18 |
| 10,000,000 in / 2,500,000 out | $1.00 | $0.80 | $1.80 |
| 100,000,000 in / 25,000,000 out | $10.00 | $8.00 | $18.00 |
Cheaper alternatives
Same tier (Mid), a different provider, and a lower blended cost at the 4:1 ratio used above:
| Model | Provider | $/1M in | $/1M out | At the 4:1 ratio |
|---|---|---|---|---|
| GPT-OSS 120B | OpenRouter | $0.037 | $0.17 | 55.8% cheaper blended |
| GPT-OSS 120B | Novita AI | $0.05 | $0.25 | 37.5% cheaper blended |