AI Rate CardDeepSeek V4 Flash 0731 vs Llama-3.1-70B-Instruct: API price and specs
DeepSeek V4 Flash 0731 is 82% cheaper than Llama-3.1-70B-Instruct on input price.
DeepSeek V4 Flash 0731 is 76% cheaper than Llama-3.1-70B-Instruct on output price.
DeepSeek V4 Flash 0731 is 80% cheaper than Llama-3.1-70B-Instruct on a 1M-in / 200k-out workload.
DeepSeek V4 Flash 0731 has a 700% larger context than Llama-3.1-70B-Instruct.
| Field | DeepSeek V4 Flash 0731 | Llama-3.1-70B-Instruct |
|---|---|---|
| Lowest input, per 1M | $0.0422 | $0.23 +445% |
| Median input, per 1M | $0.14 | $0.52 +268.8% |
| Lowest output, per 1M | $0.09495 | $0.40 +321.3% |
| Median output, per 1M | $0.30 | $0.72 +140% |
| Lowest unit price | — | — |
| Cost of 1M in + 200k out | $0.06119 | $0.31 +406.6% |
| Context | 1M | 131K +87.5% |
| Max output | 1M | 8K +99.2% |
| Providers | 43 | 9 +79.1% |
| Regions | CN, EU, GLOBAL, US | EU, GLOBAL, US |
| Accepts | text | text |
| Returns | text | text |
| Type | Text models | Text models |
| Free option | no | no |
| Cheapest provider | trustedrouter | 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 Flash 0731 or Llama-3.1-70B-Instruct?
DeepSeek V4 Flash 0731 is 82% cheaper than Llama-3.1-70B-Instruct on input price. DeepSeek V4 Flash 0731 is 76% cheaper than Llama-3.1-70B-Instruct on output price. DeepSeek V4 Flash 0731 is 80% cheaper than Llama-3.1-70B-Instruct on a 1M-in / 200k-out workload.
Which has the larger context, DeepSeek V4 Flash 0731 or Llama-3.1-70B-Instruct?
DeepSeek V4 Flash 0731: 1M tokens; Llama-3.1-70B-Instruct: 131K tokens.
Where can I use both DeepSeek V4 Flash 0731 and Llama-3.1-70B-Instruct?
aihubmix, cloudflare-workers-ai, deepinfra, edenai, kilo, openrouter, requesty, trustedrouter, vercel