Llama 3 70 B pricing
Source: litellm · updated 2026-10-27
Short answer: Llama 3 70 B costs $0.590 per million input tokens and $0.790 per million output tokens. That is a 3:1 blended rate of $0.640 per million tokens, ranking it #391 of 704 tracked models by input price.
Price breakdown
| Metric | USD |
|---|---|
| Input, per 1M tokens | $0.590 |
| Output, per 1M tokens | $0.790 |
| Output รท input multiple | 1.34× |
| 3:1 blended, per 1M tokens | $0.640 |
| Context window | 8,192 tokens |
What a typical workload costs
| Monthly volume | Input cost | Output cost | Total | 1M in / 250K out | $0.590 | $0.198 | $0.787 |
|---|---|---|---|---|---|---|---|
| 10M in / 2.5M out | $5.90 | $1.98 | $7.88 | ||||
| 100M in / 25M out | $59.00 | $19.75 | $78.75 |
Other vercel_ai_gateway models
| Model | Input | Output |
|---|---|---|
| Ministral 3 B | $0.040 | $0.040 |
| Llama 3.8 B | $0.050 | $0.080 |
| Devstral Small | $0.070 | $0.280 |
| Qwen 3 14 B | $0.080 | $0.240 |
| Qwen 3 30 B | $0.100 | $0.300 |
Compare against
Cheaper alternatives
Next cheaper option: Qwen 3 VL 235 B A22 B Instruct at $0.210 per 1M input tokens. Next step up: Gemma 2 27 B It at $0.650 per 1M input tokens.