AI Rate CardDeepSeek V4 Pro 0813 vs Llama-3.1-70B-Instruct: API price and specs
DeepSeek V4 Pro 0813 is 50% cheaper than Llama-3.1-70B-Instruct on input price.
Llama-3.1-70B-Instruct is 69% cheaper than DeepSeek V4 Pro 0813 on output price.
Llama-3.1-70B-Instruct is 17% cheaper than DeepSeek V4 Pro 0813 on a 1M-in / 200k-out workload.
DeepSeek V4 Pro 0813 has a 700% larger context than Llama-3.1-70B-Instruct.
| Field | DeepSeek V4 Pro 0813 | Llama-3.1-70B-Instruct |
|---|---|---|
| Lowest input, per 1M | $0.12 | $0.23 +100% |
| Median input, per 1M | $1.32 +153.8% | $0.52 |
| Lowest output, per 1M | $1.29 +221.7% | $0.40 |
| Median output, per 1M | $3.96 +450% | $0.72 |
| Lowest unit price | — | — |
| Cost of 1M in + 200k out | $0.37 +20.1% | $0.31 |
| Context | 1M | 131K +87.5% |
| Max output | 1M | 8K +99.2% |
| Providers | 37 | 9 +75.7% |
| Regions | APAC, EU, GLOBAL, US | EU, GLOBAL, US |
| Accepts | text | text |
| Returns | text | text |
| Type | Text models | Text models |
| Free option | no | no |
| Cheapest provider | openrouter | requesty |
Your own workload: how many tokens the model gets (input) and gives back (output) - for example, in a month. The "Cost" row of the table above is recalculated for these numbers, for each model.
Computed from current offers each time the page opens; the best value of a row is bold, the percent is how far behind the best.
Providers selling both
aihubmix, cloudflare-workers-ai, deepinfra, edenai, kilo, openrouter, requesty, trustedrouter, vercel
Frequently asked questions
Which is cheaper, DeepSeek V4 Pro 0813 or Llama-3.1-70B-Instruct?
DeepSeek V4 Pro 0813 is 50% cheaper than Llama-3.1-70B-Instruct on input price. Llama-3.1-70B-Instruct is 69% cheaper than DeepSeek V4 Pro 0813 on output price. Llama-3.1-70B-Instruct is 17% cheaper than DeepSeek V4 Pro 0813 on a 1M-in / 200k-out workload.
Which has the larger context, DeepSeek V4 Pro 0813 or Llama-3.1-70B-Instruct?
DeepSeek V4 Pro 0813: 1M tokens; Llama-3.1-70B-Instruct: 131K tokens.
Where can I use both DeepSeek V4 Pro 0813 and Llama-3.1-70B-Instruct?
aihubmix, cloudflare-workers-ai, deepinfra, edenai, kilo, openrouter, requesty, trustedrouter, vercel