# DeepSeek V4 is live on Kyma

Markdown version of https://kymaapi.com/blog/deepseek-v4-on-kyma, for agents and crawlers. Same content as the HTML page.

- Generated: 2026-10-09T21:45:05.588Z
- HTML page: https://kymaapi.com/blog/deepseek-v4-on-kyma
- Model catalog: https://kymaapi.com/models.md
- Pricing: https://kymaapi.com/pricing.md

2026-04-25 · 5 min read

> **Update, 2026-09-14.** `deepseek-v4-pro` is retired and no longer served on Kyma. Use `deepseek-v4.1-flash`, its successor. The pinned code sample and the docs link below use it; the rest of this post is the April launch record.

![DeepSeek V4 on Kyma](/blog/deepseek-v4-hero-cobrand.jpeg)

DeepSeek shipped **V4** as a preview release on April 24, 2026. We rolled it onto Kyma the next day. Two variants are live: `deepseek-v4-pro` for top-tier reasoning, and `deepseek-v4-flash` for the cheapest 1M-context model on the platform.

## What V4 actually is

In DeepSeek's own words from the V4-Pro model card:

> A new series of Mixture-of-Experts language models — DeepSeek-V4-Pro with 1.6T parameters (49B activated) and DeepSeek-V4-Flash with 284B parameters (13B activated) — both supporting a context length of one million tokens.

The architectural story under the hood:

- **Hybrid attention** combining Compressed Sparse Attention (CSA) and Heavily Compressed Attention (HCA). At 1M-token context, V4-Pro uses **27% of V3.2's inference FLOPs** and **10% of its KV cache**. This is what makes 1M-context-by-default economically real, not just technically possible.
- **Manifold-Constrained Hyper-Connections (mHC)** — a residual-connection upgrade for cleaner signal flow at depth.
- **Muon optimizer** — DeepSeek's first frontier-scale model trained with it; faster convergence, more stable runs.
- **32T+ pre-training tokens**, then a two-stage post-training pipeline that cultivates domain-specific experts and consolidates them via on-policy distillation.

Translation for builders: V4 is not a polish pass on V3. The attention rewrite is what's underneath the 1M context, the V4-Flash price drop, and reasoning-by-default without the cost blowing up.

## What changed

V4 is a clean step over V3 across the things builders actually feel:

- **1M context** by default on both variants (V3 was 128K). DeepSeek's new sparse-attention design means 1M is the standard service tier, not a degraded long-context mode.
- **Native reasoning** baked in. V4-Pro and V4-Flash both spend completion tokens on `reasoning_content` before emitting `content`, the same pattern as R1.
- **MoE architecture**:
  - V4-Pro: 1.6T total, 49B active per token.
  - V4-Flash: 284B total, 13B active per token.
- **MIT license** on both repositories and weights.
- **65,536 max output tokens**, tool calling, structured outputs, and prompt caching all supported.

V4-Flash is the surprise. DeepSeek positions it as "on par with V4-Pro on simple agent tasks", and the price difference is roughly 12x.

## Benchmarks (DeepSeek's own numbers)

These are taken from the [DeepSeek-V4-Pro model card on HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro). Vendor-published, not Kyma's measurement. We will publish independent numbers once we have real production traffic.

| Benchmark | DS V4-Pro | Opus 4.6 | GPT-5.4 | Gemini 3.1 Pro | Kimi K2.6 |
|-----------|:---------:|:--------:|:-------:|:--------------:|:---------:|
| LiveCodeBench (Pass@1) | **93.5** | 88.8 | - | 91.7 | 89.6 |
| Codeforces (Rating) | **3206** | - | 3168 | 3052 | - |
| Apex Shortlist (Pass@1) | **90.2** | 85.9 | 78.1 | 89.1 | 75.5 |
| HMMT 2026 Feb (Pass@1) | 95.2 | 96.2 | **97.7** | 94.7 | 92.7 |
| GPQA Diamond (Pass@1) | 90.1 | 91.3 | 93.0 | **94.3** | 90.5 |
| SWE Verified (Resolved) | 80.6 | **80.8** | - | 80.6 | 80.2 |
| SWE Pro (Resolved) | 55.4 | 57.3 | 57.7 | 54.2 | **58.6** |
| HLE w/ tools (Pass@1) | 48.2 | 53.1 | 52.0 | 51.6 | **54.0** |
| Toolathlon (Pass@1) | 51.8 | 47.2 | **54.6** | 48.8 | 50.0 |
| BrowseComp (Pass@1) | 83.4 | 83.7 | 82.7 | **85.9** | 83.2 |

**Bold** = leader for that row. The honest reading: V4-Pro is a competitive coding flagship. It tops LiveCodeBench, Codeforces, and Apex Shortlist outright, and it stays within a point or two of the best closed-source models on contest math (HMMT) and GPQA Diamond. SWE-Bench Verified is essentially a four-way tie at the top (80.2-80.8).

It loses on a few rows, and we are showing them on purpose. K2.6 is still ahead on SWE-Bench Pro (the harder, multi-step engineering benchmark) and on tool-augmented HLE. Gemini 3.1 Pro is ahead on raw GPQA Diamond and BrowseComp. If your workload is dominated by very long agent chains or web research, K2.6 or Gemini may still be the right call. `deepseek-v4-pro` is not a strict superset.

## Pricing on Kyma

| | V4-Pro | V4-Flash |
|--|:--:|:--:|
| Input (per 1M) | **$2.349** | **$0.189** |
| Output (per 1M) | **$4.698** | **$0.378** |

V4-Flash is the headline on price. At $0.19 input it is cheaper than `deepseek-v3` ($0.81 input) while adding reasoning, 1M context, and the V4 family architecture. If you are running bulk agent traffic on V3 today, V4-Flash is a likely net win on both quality and cost.

V4-Pro is the premium tier. For comparison: `deepseek-v3` runs $0.81 / $2.30, `kimi-k2.6` runs $1.28 / $5.40, and the closed-source flagships you see in the table above are 5-30x more expensive per 1M output token. Your price on Kyma is fixed regardless of which inference backend serves the request, and we fall over to a secondary if the primary degrades (4-layer routing).

## How to use it

**Easiest path - use an alias instead of a model ID:**

```python
from openai import OpenAI

client = OpenAI(base_url="https://kymaapi.com/v1", api_key="kyma-...")

response = client.chat.completions.create(
    model="reasoning",  # an alias; GET /v1/models lists the model it routes to today
    messages=[{"role": "user", "content": "Walk through the proof, then suggest a tighter bound."}]
)
```

**Pin the exact version when you want reproducibility:**

```python
response = client.chat.completions.create(
    model="deepseek-v4.1-flash",  # or "deepseek-v4-flash"
    messages=[...],
    max_tokens=4096,
)
```

**Heads up on `max_tokens`.** V4-Pro and V4-Flash are reasoning models. They spend completion tokens on `reasoning_content` before emitting the user-facing `content`. If you set `max_tokens: 50` and the model spends 40 on reasoning, you will get an empty `content`. Give it at least a few hundred tokens of headroom for any non-trivial query, and several thousand for multi-step agent work.

## Upgrading from V3

If you hardcoded `"model": "deepseek-v3"`, you have three choices:

- **Drop-in cheaper:** switch to `deepseek-v4-flash`. Cheaper input ($0.19 vs $0.81), 1M context vs 128K, adds reasoning. The behavior shifts because V4-Flash thinks before answering, so size your `max_tokens` accordingly.
- **Drop-in stronger:** switch to `deepseek-v4-pro`. Higher quality on coding and reasoning, more expensive than V3, same family ergonomics.
- **Stay on V3:** keep it. `deepseek-v3` remains a first-class active model on Kyma with the same routing and SLA. We do not deprecate without notice.

The family page at [`/models/text/deepseek`](https://docs.kymaapi.com/models/text/deepseek) documents all four (V4-Pro, V4-Flash, R1, V3) so you can compare side by side.

## What's next

We are watching V4's production behavior over the next week: route stability, tail latency on the long reasoning traces, and how much of the 1M context window real workloads actually fill. If anything changes in the routing (primary swap, prompt caching enablement, etc.) the model pages stay current.

Want to compare on your own workload? Sign in at [kymaapi.com](https://kymaapi.com) - the free-tier credit on signup covers several million tokens of V4-Flash, which is enough to run a real evaluation before you commit.

## Links

- [`deepseek-v4.1-flash` on Kyma docs](https://docs.kymaapi.com/models/deepseek-v4.1-flash)
- [`deepseek-v4-flash` on Kyma docs](https://docs.kymaapi.com/models/deepseek-v4-flash)
- [DeepSeek V4 preview announcement](https://api-docs.deepseek.com/news/news260424)
- [Model weights on HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro) (MIT)
- [Pricing page](https://docs.kymaapi.com/pricing)