The Known Good Updated 25 Jul 2026
DeepSeek: DeepSeek V4 Pro vs MoonshotAI: Kimi K2.6 ·DeepSeek vs Moonshot AI

DeepSeek: DeepSeek V4 Pro vs MoonshotAI: Kimi K2.6 — head-to-head comparison

DeepSeek: DeepSeek V4 Pro profile MoonshotAI: Kimi K2.6 profile All comparisons
DeepSeek: DeepSeek V4 Pro — DeepSeek
Quality
#6 of 61
93based on 3 of 6 evaluations
Known Good Index
Speed
#182 of 316
45.2
Output tokens per second
Price
#145 of 340
$0.54
Blended per 1M tokens
In $0.43 · Out $0.87
Cache hit price
#12 of 206
$0.004
per 1M tokens (−99%)
Context
#25 of 345
1.05M
tokens (~1,600 pages)
MoonshotAI: Kimi K2.6 — Moonshot AI
Quality
#7 of 61
93based on 3 of 6 evaluations
Known Good Index
Speed
#112 of 316
65.7
Output tokens per second
Price
#211 of 340
$1.16
Blended per 1M tokens
In $0.65 · Out $2.72
Cache hit price
#99 of 206
$0.11
per 1M tokens (−83%)
Context
#172 of 345
262k
tokens (~400 pages)
Summary

On the Known Good Index, DeepSeek: DeepSeek V4 Pro scores 93 and MoonshotAI: Kimi K2.6 scores 93, which puts them level. They share 3 published evaluations, with DeepSeek: DeepSeek V4 Pro ahead on 2 and MoonshotAI: Kimi K2.6 ahead on 1.

Blended pricing is $0.54 per 1M tokens for DeepSeek: DeepSeek V4 Pro and $1.16 for MoonshotAI: Kimi K2.6 — DeepSeek: DeepSeek V4 Pro is about 2.1× cheaper.

Throughput is 45 tokens per second for DeepSeek: DeepSeek V4 Pro and 66 for MoonshotAI: Kimi K2.6, with time to first token at 2.0s and 1.1s. DeepSeek: DeepSeek V4 Pro accepts 1.05M tokens of context against 262k.

DeepSeek: DeepSeek V4 Pro is open weights under Open weights (unrestricted); MoonshotAI: Kimi K2.6 is open weights under Open weights (unrestricted). 26 tracked hosts serve one or both, and 13 serve both.

Generated from tracked data on 25 Jul 2026 · how these comparisons are computed →

At a glance
MetricDeepSeek: DeepSeek V4 ProMoonshotAI: Kimi K2.6
Known Good Index 93 based on 3 of 6 evaluations 93 based on 3 of 6 evaluations
Blended $/1M $0.54 $1.16
Output tok/s 45 66
Context window 1.05M 262k
Providers 18 21
Jump to section

Quality

Known Good Index and the capability indices, side by side

IndicesComponents
Index scores

Each index is min-max normalised across tracked models and scaled 0–100 from published evaluations. We do not run these evaluations.

MetricDeepSeek: DeepSeek V4 ProMoonshotAI: Kimi K2.6
Known Good Index 93 93
Mathematics Index 97 96
Science Index 94 95
Agentic Index 89 87
Openness Index 60 60
The Known Good

Quality Breakdown

Every evaluation both models report a published score for

Evaluations both models report

Bar = DeepSeek: DeepSeek V4 Pro · marker = MoonshotAI: Kimi K2.6 · scores ingested from Epoch AI (CC-BY 4.0)

GPQA Diamond90 / 91
MATH / AIME97 / 96
SWE-bench Verified78 / 77

Right-hand figures read DeepSeek: DeepSeek V4 Pro / MoonshotAI: Kimi K2.6. DeepSeek: DeepSeek V4 Pro leads on 2 of 3, MoonshotAI: Kimi K2.6 on 1.

The Known Good

Arena Elo

Human preference rating from blind pairwise votes

Arena ratings

Elo from blind pairwise votes, ingested from Arena. Higher is better.

MetricDeepSeek: DeepSeek V4 ProMoonshotAI: Kimi K2.6
Text Arena 1,449 1,455
Text Arena (style controlled) 1,457 1,461
The Known Good

Price & Cost

Published API pricing by token type

Per token typeCache discount
Published pricing

USD per 1M tokens. Blended is a 3:1 input:output mix. Live from OpenRouter, cross-checked against models.dev. Lower is better.

MetricDeepSeek: DeepSeek V4 ProMoonshotAI: Kimi K2.6
Input $/1M $0.43 $0.65
Output $/1M $0.87 $2.72
Blended $/1M $0.54 $1.16
Cache read $/1M $0.004 $0.109
The Known Good
We publish blended price rather than cost-per-task. Cost-per-task requires token counts from an evaluation suite we do not run. Blended price is computed from published rates and is fully reproducible — see the pricing methodology.

Context Window

Maximum input accepted and maximum output emitted

Context and output limits

Provider-declared limits, from metadata via models.dev and OpenRouter. Higher is better.

MetricDeepSeek: DeepSeek V4 ProMoonshotAI: Kimi K2.6
Context window 1.05M 262k
Max output tokens 384k 262k
The Known Good

Speed & Latency

Median throughput and time to first token across hosting providers

Output speedTime to first token
Throughput and latency

Medians across all tracked providers, derived from OpenRouter endpoint telemetry.

MetricDeepSeek: DeepSeek V4 ProMoonshotAI: Kimi K2.6
Output tokens/s 45 66
Time to first token 2.0s 1.1s
The Known Good

Providers

Which hosts serve each model, and at what price and speed

26 hosts · 13 serve both
Full provider benchmarks →
Provider DeepSeek: DeepSeek V4 Pro blendedDeepSeek: DeepSeek V4 Pro tok/s MoonshotAI: Kimi K2.6 blendedMoonshotAI: Kimi K2.6 tok/s
BaseTen $2.17 110 $1.71 —
Fireworks $2.17 66 $1.71 111
Novita $1.46 66 $1.45 43
DeepInfra $1.62 65 $1.44 57
GMICloud $0.85 62 — —
Venice $2.06 61 $1.44 54
Baidu · first party $0.78 58 $1.16 32
Together $2.17 53 $2.02 130
Alibaba · first party $1.77 52 — —
AtlasCloud $2.10 46 $1.71 44
Wafer $1.50 45 — —
DeepSeek · first party $0.54 44 — —
SiliconFlow $1.91 41 $1.43 50
StreamLake $0.84 41 $1.54 44
CoreWeave $2.17 28 $1.34 156
Ionstream $1.41 20 — —
DigitalOcean $1.74 6 $1.37 53
Parasail $2.17 — $1.44 42
Decart — — $1.35 123
ModelRun — — $1.38 99
Crusoe — — $1.40 69
Cloudflare — — $1.71 56
Chutes — — $1.37 49
Moonshot AI · first party — — $1.71 40
Inceptron — — $1.30 39
Phala — — $1.97 —

Per-host pricing and telemetry from OpenRouter. A dash means that host does not serve that model.

The Known Good
Sources for this page
Pricing & providers — OpenRouter Metadata — models.dev Benchmarks — Epoch AI (CC-BY 4.0)Elo — Arena Full attribution →