DeepSeek V3.1
DeepSeek released 2025-08-21
$0.825 per million tokens, balanced
No independent quality score.
No benchmark we track has measured this model. That is not the same as measuring it and finding it wanting — we simply cannot rank it, so we do not.
Every price dimension
| Input | $0.550/M |
|---|---|
| Output | $1.65/M |
| Cached input | $0.550/M |
Independent scores
| LMArena Elo | 1419.1default |
|---|
Sources are listed separately rather than averaged. Across the 62 models both have scored they correlate at r = 0.806 — close agreement overall, but four models rank very differently between them, and a blended score would hide exactly those.
Capability
| Context window | 164K |
|---|---|
| Max output | 161K |
| Input modes | text |
| Tool use | yes |
| Reasoning | optional |
| Knowledge cutoff | 2025-03-31 |
Provenance
| Price source | openrouter.ai |
|---|---|
| Fetched | 2026-08-24 |
| Quality data | unrated |
DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...