読み込み中…
Observed 2026-06-03 11:12. Prices are USD per 1M tokens (from OpenRouter public pricing). Input: DeepSeek V3 $0.2002 / Mistral Medium 3.5 $1.5, output: $0.8001 / $7.5.
✓ = the mechanically better side per row (cheaper price / longer context). Magnitude only, not a rating.
| Field | DeepSeek V3 deepseek/deepseek-chat | Mistral Medium 3.5 mistralai/mistral-medium-3-5 |
|---|---|---|
| Input priceUSD/1M | $0.2002✓ | $1.5 |
| Output priceUSD/1M | $0.8001✓ | $7.5 |
| Cache readUSD/1M | Accumulating… | Accumulating… |
| Context windowtokens | 131.072k | 262.144k✓ |
Source: OpenRouter /api/v1/models → collect_prices.py → Source(price)。 · DeepSeek V3: deepseek/deepseek-chat · Mistral Medium 3.5: mistralai/mistral-medium-3-5
Aggregated observations, not predictions. Prices change (observation time noted). © TraceBottle for AI
As observed on 2026-06-03 11:12, input is DeepSeek V3 $0.2002 / Mistral Medium 3.5 $1.5 per 1M tokens — DeepSeek V3 is cheaper. Output is $0.8001 / $7.5 — DeepSeek V3 is cheaper.
DeepSeek V3: 131,072 tokens, Mistral Medium 3.5: 262,144 tokens (observed 2026-06-03 11:12).
Observed 2026-06-03 11:12 (UTC). Source: OpenRouter public pricing (/api/v1/models). Prices change — check each provider's official pricing for the latest. This site publishes only observed values, never predictions.