← Compare models
Open all in the calculator — adjust volume and token counts →
GPT-5.4 Mini vs Mistral Medium 3.5 (batch)
List-price comparison ·GPT-5.4 Mini details ·Mistral Medium 3.5 (batch) details
For a typical workload (100,000 requests / mo), Mistral Medium 3.5 (batch) is the cheapest — 11% less than the priciest here ($240.00/mo vs $270.00/mo).
| GPT-5.4 Mini | Mistral Medium 3.5 (batch) | |
|---|---|---|
| Input / 1M tokens | $0.750 | $0.750 |
| Output / 1M tokens | $4.50 | $3.75 |
| Typical request (1,200 in + 400 out) | $0.0027 | $0.0024 |
| Context window | 400k tokens | 262,144 tokens |
| Max output | 128k tokens | 209,715 tokens |
| Quality score | 80/100 | 75/100 |
| Tier | Balanced | Balanced |
| Provider | OpenAI | Mistral AI |
Projected monthly cost
| Requests / mo | GPT-5.4 Mini | Mistral Medium 3.5 (batch) |
|---|---|---|
| 1,000 | $2.70 | $2.40 |
| 10,000 | $27.00 | $24.00 |
| 100,000 | $270.00 | $240.00 |
GPT-5.4 Mini
Good default for everyday chat, summarization, and lightweight agent steps where GPT-5.4-level reasoning isn't required.
Quality gap widens on long, multi-hop reasoning tasks — needs careful prompt design to avoid silent failures on edge cases.
Mistral Medium 3.5 (batch)
Auto-synced from OpenRouter — no editorial write-up yet.
More comparisons
Vendor list rates · per-request examples assume 1,200 input + 400 output tokens.