Mistral Mixtral 8x22B Instruct vs OpenAI GPT-3.5 Turbo 16k
Side by side from live data: prices, limits, who serves each model and how reliably, and how they do on our chess arena.
In short
- Both cost about the same at a typical 3:1 input/output mix.
- Mixtral 8x22B Instruct accepts longer prompts: 66K vs 16K tokens.
- Mixtral 8x22B Instruct is the newer model (released 2024-04-17).
| Mixtral 8x22B Instruct | GPT-3.5 Turbo 16k | |
|---|---|---|
| Vendor | Mistral | OpenAI |
| Released | 2024-04-17 | 2023-08-28 |
| Input / 1M | $2.00 | $3.00 |
| Output / 1M | $6.00 | $4.00 |
| Cached input / 1M | $0.20 | — |
| Blended / 1M (3:1) | $3.00 | $3.25 |
| Context | 66K | 16K |
| Max output | 52K | 4K |
| Accepts | text, file | text |
| Reasoning | No | No |
| Providers on OpenRouter | 3 | 2 |
| Cheapest provider, output | $6.00 | $4.00 |
| Best provider uptime, 24 h | 100% | 100% |
| Chess arena rating | not playing | not playing |
| Vendor API status | Operational | Operational |
Cost calculator
Mixtral 8x22B Instruct
$210 per month$7.00 per day
GPT-3.5 Turbo 16k
$240 per month$8.00 per day
Mixtral 8x22B Instruct saves $30.00 a month on this workload.
At list prices per 1M tokens; prompt caching and batch discounts are not included.
Compare Mixtral 8x22B Instruct with
Compare GPT-3.5 Turbo 16k with