# DeepSeek V4 Pro

> 1.6T MoE flagship. 1M context. Top reasoning tier.

Human version: https://kymaapi.com/models/deepseek-v4-pro
Live JSON: `GET https://kymaapi.com/v1/models` (no auth required)

## Facts

- **Model ID**: `deepseek-v4-pro` — pass this as `model` in the request body
- **Creator**: DeepSeek
- **Released**: 2026-04-23
- **Context window**: 1M tokens
- **Max output**: 66K tokens per response — a hard ceiling, not a default
- **Price**: $0.6901 in / $1.38 out per 1M, cached input 10%
- **Capabilities**: tools, reasoning, caching

## Call it

```bash
curl https://kymaapi.com/v1/chat/completions \
  -H "Authorization: Bearer $KYMA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "deepseek-v4-pro", "messages": [{"role": "user", "content": "Hello"}]}'
```

## Positioning

DeepSeek's 1.6T-parameter MoE flagship, in Kyma's frontier-open quality tier — the model to reach for when reasoning depth matters more than speed or price.

## About

DeepSeek V4 Pro is DeepSeek's flagship: a 1.6T mixture-of-experts model built for top-tier reasoning, complex coding, and long-context work. It sits in Kyma's frontier-open quality tier at premium pricing — the option you pick when the task is hard enough that output quality pays for itself.

On Kyma it ranks #12 of 62 models by production tokens served, with a 99.2% success rate across recent traffic. OpenClaw is its top app by tokens, and Claude Code and Cline also rank among its top five consumers. Every request gets automatic failover, and prompt caching is fully supported: repeated prompt prefixes bill at 10% of the input rate — a discount that matters most at this price tier, where agents resend long prompts on every turn.

The 1M-token context window pairs with a 64K max output, function calling, structured outputs, and extended reasoning — headroom for very long inputs and long, structured generations.

## Use cases

- **Hard reasoning problems** — A top-reasoning-tier model with extended reasoning, built for the math, planning, and analysis tasks where depth matters more than turnaround time.
- **Agentic coding** — Coding agents already run production traffic through it on Kyma: OpenClaw is its top app by tokens, with Claude Code and Cline also in its top five.
- **Long-context work** — The 1M-token window handles long documents, large specs, and large codebases in a single request.
- **Long structured generations** — A 64K output ceiling plus structured outputs supports big refactors, detailed reports, and large JSON payloads.
- **Tool-driven pipelines** — Function calling and structured outputs keep multi-step agent loops reliable when each step's correctness compounds.

## Not ideal for

Image inputs (it is text-only) or latency-sensitive, high-volume workloads — it is a medium-speed, premium-priced model, so bulk background tasks run faster and cheaper on a fast-tier model.

## Pick something else when

- You want a cheaper V4 option with the same family behavior → `deepseek-v4-flash`
- You want the strongest agentic flagship → `kimi-k2.6`
- You want the best general default at lower cost → `qwen-3.6-plus`
- You only need the previous-gen DeepSeek flagship → `deepseek-v3`

## See also

- All models: https://kymaapi.com/models.md
- Pricing: https://kymaapi.com/pricing.md
- Other models by DeepSeek: https://kymaapi.com/models?q=DeepSeek