# DeepSeek V3

> Previous-gen flagship. Stable, proven.

Human version: https://kymaapi.com/models/deepseek-v3
Live JSON: `GET https://kymaapi.com/v1/models` (no auth required)

## Facts

- **Model ID**: `deepseek-v3` — pass this as `model` in the request body
- **Creator**: DeepSeek
- **Released**: 2025-12-01
- **Context window**: 160K tokens
- **Max output**: 8K tokens per response — a hard ceiling, not a default
- **Price**: $0.351 in / $0.513 out per 1M
- **Capabilities**: tools, reasoning

## Call it

```bash
curl https://kymaapi.com/v1/chat/completions \
  -H "Authorization: Bearer $KYMA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "deepseek-v3", "messages": [{"role": "user", "content": "Hello"}]}'
```

## Positioning

DeepSeek's previous-generation flagship and the #3 model on Kyma by tokens served — the stable, proven choice for frontier-open quality at balanced pricing.

## About

DeepSeek V3 is the previous-generation flagship from DeepSeek, built for reasoning, coding, and general-purpose work. It sits in Kyma's frontier-open quality tier, and its appeal is exactly what the label says: stable and proven — a fit for teams that value predictable behavior over chasing the latest checkpoint.

On Kyma it ranks third of 62 models by production tokens, serving over 166 million tokens (8.3% of platform traffic) across 18,500+ requests at a 100% success rate. OpenClaw is its top application by tokens, followed by Python and Node.js apps. Every request gets the platform's automatic failover, and each response reports its exact cost in usage.cost.

The 160K-token context window pairs with function calling, structured outputs, and extended reasoning, so it can run multi-step agent loops, not just single-turn chat. It sits in the frontier-open tier as the value pick — see the pricing table above for the current rate.

## Use cases

- **Coding agents** — Its top production app on Kyma by tokens is OpenClaw, a coding agent — code generation, review, and refactoring inside agent harnesses.
- **Reasoning pipelines** — Extended reasoning support handles analysis and planning tasks that need more than pattern matching.
- **Cost-conscious production** — Frontier-open quality at balanced pricing makes it a sensible default for high-volume general workloads where value matters.
- **Structured extraction** — Structured outputs plus the 160K context let it pull reliable JSON from long documents and codebases in one pass.
- **Tool-calling backends** — Function calling support makes it a dependable engine behind Python and Node.js services that orchestrate tools.

## Not ideal for

Image inputs (it's text-only), latency-critical UX where its medium speed tier shows, or single responses longer than the 8K output cap.

## Pick something else when

- You want the strongest default quality → `qwen-3.6-plus`
- You need deeper reasoning specifically → `deepseek-r1`
- You need multimodal or vision input → `kimi-k2.6`, `gemma-4-31b`

## 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