Model comparison
DeepSeek V4 Pro TEE vs Kimi K2.5 TEE
Price history, scores and specs for both models, line by line. Every value shows where it came from and when we last confirmed it.
Flagship DeepSeek model for coding, reasoning, and agentic work.
Kimi model for long-context chat, coding, and agentic reasoning.
Quick take
Where each one leads
- Kimi K2.5 TEE costs less to send text to: $0.532 per million tokens, against $0.887 per million tokens for DeepSeek V4 Pro TEE.
- DeepSeek V4 Pro TEE costs less per word it writes: $1.77 per million tokens, against $3.33 per million tokens for Kimi K2.5 TEE.
- DeepSeek V4 Pro TEE reads more at once: 1,048,576 tokens, against 262,144 tokens.
- Kimi K2.5 TEE scores higher on the Artificial Analysis Intelligence Index: 23.5 to 12.6.
- DeepSeek V4 Pro TEE scores higher on the Artificial Analysis Coding Index: 59.4 to 46.8.
- More people run DeepSeek V4 Pro TEE through OpenRouter than Kimi K2.5 TEE right now.
Each line comes from a checked value in the tables below. Pick on your workload: price and usage matter for high volume, context and scores for long documents and agent loops.
Price history
Prices side by side, day by day
- DeepSeek V4 Pro TEE
- Kimi K2.5 TEE
- DeepSeek V4 Pro TEE
- Kimi K2.5 TEE
Prices are the listed OpenRouter base rates in US dollars. A day we could not confirm is left out of the line, never filled in.
Price
What each one costs now
| Measure | DeepSeek V4 Pro TEE | Kimi K2.5 TEE |
|---|---|---|
| Input price | $0.887 per million tokens | $0.532 per million tokens Leads |
| Output price | $1.77 per million tokens Leads | $3.33 per million tokens |
Scores
Benchmarks, with source and date
| Measure | DeepSeek V4 Pro TEE | Kimi K2.5 TEE |
|---|---|---|
| Artificial Analysis Intelligence Index | 12.6 | 23.5 Leads |
| Artificial Analysis Coding Index | 59.4 Leads | 46.8 |
| Artificial Analysis Agentic Index | 26.3 | Not checked yet |
| LMArena text rating (Elo) | Not checked yet | 1,445 |
| LMArena web development rating (Elo) | Not checked yet | 1,436 |
| LMArena vision rating (Elo) | Not checked yet | 1,269 |
| Design Arena rating (Elo) | 1,239 | 1,245 Leads |
Specs
Context, modalities and tool use
| Measure | DeepSeek V4 Pro TEE | Kimi K2.5 TEE |
|---|---|---|
| Context window | 1,048,576 tokens Leads | 262,144 tokens |
| Reads | Text | Text, Images |
| Writes | Text | Text |
| Tool calling | Yes | Yes |
| Reasoning mode | Yes | Yes |
| Open weights | Yes | Yes |
| Listed since | 24 Apr 2026 | 27 Jan 2026 |
Usage
How much each one is used
| Measure | DeepSeek V4 Pro TEE | Kimi K2.5 TEE |
|---|---|---|
| Tokens served on OpenRouter in a day | 90.6B Leads (for 10 Nov 2026) | 3.8B (for 10 Nov 2026) |
| Requests on OpenRouter in a day | 3.4M Leads (for 10 Nov 2026) | 261.6K (for 10 Nov 2026) |
| Tool calls on OpenRouter in a day | 861.6K Leads (for 10 Nov 2026) | 46.7K (for 10 Nov 2026) |
| Token usage, last 7 days | Down 6% on the week before (for 10 Nov 2026) | Up 5% on the week before Leads (for 10 Nov 2026) |
- DeepSeek V4 Pro TEE
- Kimi K2.5 TEE
How this works
One link, either order
This link stays the same whichever order you name the two models in, so you can share it as it is. A line appears only when at least one model has a value we confirmed from a source; values we have not confirmed are left out, never guessed. To add a third record of any type, use the open comparison. Read how we check facts.