# DeepSeek V4 Pro vs Kimi K3

As of October 21, 2026, Kimi K3 costs 127% more per input token than DeepSeek V4 Pro ($3.00 vs $1.32 per 1M) and has a 1,048,576-token context window versus 1,000,000.

- Page: https://models.litellm.ai/compare/deepseek-v4-pro-vs-kimi-k3
- DeepSeek V4 Pro: https://models.litellm.ai/models/deepseek-v4-pro
- Kimi K3: https://models.litellm.ai/models/kimi-k3

## Side by side

| | DeepSeek V4 Pro | Kimi K3 |
|---|---|---|
| Input, per 1M tokens | $1.32 | $3.00 |
| Output, per 1M tokens | $3.96 | $15.00 |
| Cache read, per 1M tokens | $0.044 | $0.30 |
| Cache write, per 1M tokens | $0 | – |
| Context window | 1,000,000 tokens | 1,048,576 tokens |
| Max output | 393,216 tokens | 1,048,576 tokens |
| Image input | No | Yes |
| Tool calling | Yes | Yes |
| Structured output (JSON) | Yes | Yes |
| Prompt caching | Yes | Yes |
| Reasoning | Yes | Yes |
| Providers on LiteLLM | 18 | 15 |
| Price shown is from | DeepSeek | Moonshot AI |
| Added to LiteLLM | June 2026 | August 16, 2026 |

Headline prices in USD per 1M tokens, from LiteLLM's model price file.

## Cheapest provider for each

- DeepSeek V4 Pro: Sail at $0.92 input per 1M tokens (`sail/deepseek-ai/DeepSeek-V4-Pro-0813`)
- Kimi K3: Sail at $2.50 input per 1M tokens (`sail/moonshotai/Kimi-K3`)

## Benchmark scores

| Benchmark | DeepSeek V4 Pro | Kimi K3 |
|---|---|---|
| FrontierCode (Coding and agents) | 17.6% (none) | 44.2% |
| APEX-Agents (Coding and agents) | 47.3% | 47.8% |
| GPQA Diamond (Reasoning and knowledge) | 90.9% (high) | 93.1% (max) |
| ARC-AGI-2 (Reasoning and knowledge) | 61.3% (max) | 60.4% (max) |
| SimpleQA Verified (Reasoning and knowledge) | 47.0% (max) | 50.6% (max) |
| FrontierMath (tiers 1-3) (Math) | 45.3% (max) | 72.2% (max) |
| FrontierMath (tier 4) (Math) | 2.4% (max) | 39.0% (max) |
| OTIS Mock AIME 2024-2025 (Math) | 96.7% (max) | 97.2% (max) |

From the Epoch AI Benchmarking Hub (https://epoch.ai/benchmarks), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/), data as of August 27, 2026: Epoch's own runs and results it collects from each benchmark's leaderboard. Higher is better.

## When to pick which

- DeepSeek V4 Pro: Costs 56% less per input token: $1.32 vs $3.00 per 1M.
- Kimi K3: Supports image input, which DeepSeek V4 Pro doesn't list.
- Kimi K3: Returns up to 1,048,576 tokens per response, vs 393,216.

## FAQ

### Which is cheaper, DeepSeek V4 Pro or Kimi K3?

DeepSeek V4 Pro is cheaper at 3 input tokens per output token: $1.98 per 1M tokens blended ($1.32 input, $3.96 output), versus $6.00 ($3.00 and $15.00) for Kimi K3, as of October 21, 2026.

### Which has the larger context window, DeepSeek V4 Pro or Kimi K3?

Kimi K3 has the larger context window: 1,048,576 tokens, versus 1,000,000 for DeepSeek V4 Pro.

### Can I switch from DeepSeek V4 Pro to Kimi K3 without changing my code?

Yes. Through LiteLLM both use the OpenAI format, so switching means changing the model name from "deepseek-v4-pro" to "moonshot/kimi-k3", or pointing a LiteLLM gateway model alias at the other model. You can also use one as a fallback for the other.