Is DeepSeek V3.1 Terminus a good deal?

Whether anything in this catalogue beats DeepSeek V3.1 Terminus on both quality and price, and what you give up if it does. A computation on the current catalogue, not an opinion.

12 undominated of 144 · Nov 22, 2026

As of Nov 22, 2026, DeepSeek V3.1 Terminus is dominated for Balanced on LMArena. DeepSeek V4.1 Flash scores 45.7 higher and costs 50% less, with a covering envelope. 12 of 144 rated, priced standard models are undominated.

Inspect model evidence Compare differences & requirements

Current model

DeepSeek V3.1 Terminus

Balanced

3 tokens in per 1 out

DeepSeek V4.1 Flash is both better and cheaper than DeepSeek V3.1 Terminus: 45.7 points higher on LMArena and 50% less per million tokens, $0.225 cheaper at this mix.

DeepSeek V3.1 Terminus

LMArena Elo · higher is better

Scale starts at 1040 Elo

1417.3

Effective $/M · Balanced · lower is better

$0.453/M

DeepSeek V4.1 Flash

LMArena Elo · higher is better

Scale starts at 1040 Elo

1463.0

Effective $/M · Balanced · lower is better

$0.227/M

DeepSeek V3.1 Terminus takes text, returns up to 147,456 tokens from a 163,840-token context, and is listed by 1 seller.

Compared against 144 rated, priced models on this lens: 7 models dominate it and give up nothing, 5 more dominate it but give something up. DeepSeek V3.1 Terminus scores 1417.3 at $0.453 per million tokens for this mix.

Envelope-safe replacements

Each row scores at least as high, costs no more, and covers this model’s context, output, modalities, tools, and reasoning. A cheaper narrower model is not listed here.

ModelLMArenaEffective $/MYou save
DeepSeek V4.1 Flash1463.0 +45.7$0.227/M50%
Hy31439.0 +21.7$0.231/M49%
Gemma 4 26B A4B 1434.2 +16.9$0.123/M73%
DeepSeek V4 Flash 04231431.9 +14.6$0.113/M75%
DeepSeek V3.21424.6 +7.3$0.394/M13%
DeepSeek V3.2 Exp1422.3 +5.0$0.305/M33%
DeepSeek V3.11419.8 +2.5$0.453/M0%

Higher score, lower price, named losses

Not a drop-in. The loss is why these are not a recommendation.

ModelLMArenaEffective $/MYou give up
GLM 5.3 Flash1471.4$0.148/Mmax output
MiMo-V2.6-Flash1449.8$0.175/Mmax output
Gemma 4 31B1442.5$0.205/Mmax output
GPT-5.6 Luna1430.9$0.450/Mmax output
Qwen3 VL 235B A22B Instruct1420.0$0.370/Mmax output, reasoning
DeepSeek V4.1 Flash1463.0 · $0.227/MDeepSeek V3.1 Terminus1417.3 · $0.453/MLMArena EloEffective $/M · Balanced
144 rated, priced standard models. Chartreuse is the frontier. Cobalt is the model you named, when it is not on the staircase.

Open the frontier

The link keeps the model and mix, using the current catalogue. Monthly spend and switching cost stay in this browser tab and are left out of the link.

Saved decision references

Save the model, workload, catalogue date and capability-preservation rule in this browser. Spend, switching cost and bill contents are not saved. No account or notifications.

Constraint: replacements must preserve the model’s capabilities; any losses remain named trade-offs.

Historical decisions cannot be fully replayed from saved references: past prices, scores and capability evidence are not stored.

Evidence & Ask