AI model comparison
DeepSeek V3.1 Terminus vs Kimi K2 0905
Pricing, context window, benchmarks, and features compared side by side. Or skip the guesswork and send one prompt to both.
DeepSeek
DeepSeek V3.1 Terminus
DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's
- Input / 1M
- $0.27
- Output / 1M
- $1
- Context
- 164K
Moonshot AI
Kimi K2 0905
Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2).
- Input / 1M
- $0.60
- Output / 1M
- $2.50
- Context
- 262K
At a glance
Quick verdict
How the two models stack up on the things people ask about most.
Lower price
DeepSeek V3.1 Terminus
2.4x cheaper for a typical chat
Higher intelligence score
Kimi K2 0905
15.3 vs 14.8 on Artificial Analysis
Larger context window
Kimi K2 0905
262K vs 164K tokens
Newer release
DeepSeek V3.1 Terminus
Released September 22, 2025
Benchmarks
Benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
DeepSeek V3.1 Terminus14.8Coding index
DeepSeek V3.1 Terminus43.5Agentic index
DeepSeek V3.1 Terminus6.8Pricing
DeepSeek V3.1 Terminus vs Kimi K2 0905 API pricing
Per-token API rates. Cheaper option highlighted.
| Metric | DeepSeek V3.1 Terminus | |
|---|---|---|
| Input tokensPer 1M tokens | $0.27 | $0.60 |
| Output tokensPer 1M tokens | $1 | $2.50 |
| Cached input (read)Per 1M tokens | Not available | Not available |
| Cache writePer 1M tokens | Not available | Not available |
What it costs in practice
Estimated cost per 1,000 requests at standard rates. Coding and long-document figures also show the cost when the input is already cached.
Chat message
2K in, 500 out
DeepSeek V3.1 Terminus$1.04Coding task
30K in, 4K out
DeepSeek V3.1 Terminus$12.10Long document summary
150K in, 2K out
DeepSeek V3.1 Terminus$42.50Specs
Context window and capabilities
How much each model can read, how much it can write, and what it accepts as input.
| Metric | DeepSeek V3.1 Terminus | |
|---|---|---|
| Context window | 164K tokens | 262K tokens |
| Max output | 147K tokens | 98K tokens |
| Input types | Text | Text |
| Output types | Text | Text |
| Reasoning effort levels | Not available | Not available |
| Default reasoning effort | Not available | Not available |
| Release date | September 22, 2025 | September 4, 2025 |
Features
Supported features
API features available for each model.
| Metric | DeepSeek V3.1 Terminus | |
|---|---|---|
| Tool calling | Supported | Supported |
| Structured outputs | Supported | Supported |
| JSON mode | Supported | Supported |
| Reasoning | Supported | Not supported |
| Temperature | Supported | Supported |
| Stop sequences | Supported | Supported |
| Deterministic seed | Not supported | Supported |
| Verbosity control | Not supported | Not supported |
Keep exploring
More on these models
Other head-to-heads, the full model page, and the alternatives list for each model.
DeepSeek V3.1 TerminusView full model details- DeepSeek V3.1 Terminus vs DeepSeek V4 Flash 0423
- DeepSeek V3.1 Terminus vs Qwen3.6 35B A3B
- DeepSeek V3.1 Terminus vs Gemini 3.1 Flash Lite
- DeepSeek V3.1 Terminus vs Gemini 2.5 Flash
- DeepSeek V3.1 Terminus vs Gemma 4 31B
- DeepSeek V3.1 Terminus vs DeepSeek V3.2 Exp
- DeepSeek V3.1 Terminus vs Mercury 2
- DeepSeek V3.1 Terminus vs DeepSeek V3.1
- DeepSeek V3.1 Terminus vs R1 0528
- DeepSeek V3.1 Terminus vs DeepSeek V3 0324
Our take
DeepSeek V3.1 Terminus is 2.4x cheaper for a typical chat. Kimi K2 0905 scores higher on the Artificial Analysis Intelligence Index (15.3 vs 14.8). Kimi K2 0905 has the larger context window (262K vs 164K tokens). The right pick depends on your workload, so the quickest way to settle it is to send the same prompt to both and compare.
FAQ
Frequently asked questions
Is DeepSeek V3.1 Terminus or Kimi K2 0905 cheaper?
DeepSeek V3.1 Terminus is cheaper for a typical chat (2K input tokens and 500 output tokens). DeepSeek V3.1 Terminus costs $0.27 per 1M input tokens and $1 per 1M output tokens, while Kimi K2 0905 costs $0.60 per 1M input tokens and $2.50 per 1M output tokens.
Which has a bigger context window, DeepSeek V3.1 Terminus or Kimi K2 0905?
Kimi K2 0905 supports up to 262K tokens of context, compared with 164K for DeepSeek V3.1 Terminus.
Is DeepSeek V3.1 Terminus smarter than Kimi K2 0905?
On the Artificial Analysis Intelligence Index, DeepSeek V3.1 Terminus scores 14.8 and Kimi K2 0905 scores 15.3, putting Kimi K2 0905 ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.
Can I use DeepSeek V3.1 Terminus and Kimi K2 0905 at the same time?
Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see DeepSeek V3.1 Terminus and Kimi K2 0905 answer side by side and keep the better response.
Why choose? Ask both.
Send one prompt to DeepSeek V3.1 Terminus and Kimi K2 0905 at the same time. Compare the answers side by side and keep the best one.