# DeepSeek V4 Flash

> 284B MoE. 1M context. Fast + cheap V4 tier.

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

## Facts

- **Model ID**: `deepseek-v4-flash` — 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**: $0.187 in / $0.3741 out per 1M, cached input 10%
- **Capabilities**: tools, reasoning, caching
- **Alias**: `cheap` resolves to this model

## 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-flash", "messages": [{"role": "user", "content": "Hello"}]}'
```

## Positioning

DeepSeek's fast-and-cheap V4-tier model with a 1M-token context window — currently the fourth most-used model on Kyma. Reach for it when you want strong quality at value pricing for coding, general tasks, and long-context work.

## About

DeepSeek V4 Flash is the fast, cheap entry in DeepSeek's V4 tier — a 284B mixture-of-experts model that sits in Kyma's strong quality tier. It's built as a value workhorse: general tasks, coding, and long-context jobs where you want most of the quality at a fraction of the cost.

In production on Kyma it ranks #4 of 62 models by tokens served, carrying 7.7% of platform traffic with a 100% success rate across recent requests. OpenClaw is its single biggest app — roughly half of all its tokens — with Roo Code and Cline also in its top five. Every call gets Kyma's automatic failover, and prompt caching is fully supported, so repeated prompt prefixes bill at 10% of the input rate.

Capability-wise it checks every box for agent work: a 1M-token context window, up to 65K tokens of output per request, function calling, structured outputs, and extended reasoning. Input and output are text-only.

## Use cases

- **Coding** — A core recommended use, and where its production traffic goes — OpenClaw, Roo Code, and Cline are among its top apps on Kyma, with OpenClaw alone at roughly half its tokens.
- **Long-context analysis** — The 1M-token window takes entire codebases, document collections, or long agent transcripts in one request.
- **High-volume pipelines** — Cheap-tier pricing makes it a sensible default for background jobs, batch processing, and anything that runs thousands of times a day.
- **Structured agent backbones** — Function calling plus structured outputs keep multi-step agents and extraction pipelines on schema.
- **Reasoning on a budget** — Extended reasoning support handles planning and analysis steps without paying flagship rates.

## Not ideal for

Image inputs — it's text-only, so anything that needs to look at screenshots or photos should go to a vision model instead.

## Pick something else when

- You need the strongest V4 quality → `deepseek-v4-pro`
- You want the best general default overall → `qwen-3.6-plus`
- You want the previous-gen DeepSeek flagship at value pricing → `deepseek-v3`
- You need vision / multimodal input → `gemma-4-31b`, `kimi-k2.6`

## 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