DeepSeek V4 Flash, lightweight 284B MoE with 1M context and hybrid thinking for cost-efficient agents.
Available on
Pricing from$0.07/ 1M input$0.17/ 1M output$0.01/ 1M cache read1Mcontext
Privacy
- ZDR
- Training
- No
- Region
- Multi, US, EU
Run Kilo Code on DeepSeek V4 Flash
Kilo Code is an open-source AI coding agent for VS Code. It combines autonomous editing, planning and architect modes, and a provider catalogue built from the open models.dev listing, where Opper is one of the providers. Pick Opper, paste your key, and you can run it on any of 700+ models on one gateway, with a choice of region.
Run
Kilo Codeonin
Kilo CodeoninConnect Kilo Code to DeepSeek V4 Flash
Add Opper in Kilo Code
In Kilo Code, open Settings → Providers → Show more providers, search for Opper and paste your Opper key. Then pick DeepSeek V4 Flash.
Model id
Where you can run it
DeepSeek V4 Flash runs on the routes below. Route only to EU providers when your data has to stay in Europe. One route also sells flex and priority processing: the same model at another price, picked per request with service_tier. How service tiers work.
| Provider | Region | Zero data retention | Training | Input | Output | Cache read | ||
|---|---|---|---|---|---|---|---|---|
| EU | No | $0.28 | $0.56 | $0.07 | Not offered on this route | Not offered on this route | ||
| EU | No | $0.25 | $0.30 | $0.06 | Not offered on this route | Not offered on this route | ||
| US | No | $0.09 | $0.18 | $0.02 | ||||
| US | No | $0.07 | $0.17 | $0.02 | Not offered on this route | Not offered on this route | ||
| US | No | $0.09 | $0.24 | $0.04 | Not offered on this route | Not offered on this route | ||
| Multi | — | $0.14 | $0.28 | $0.03 | Not offered on this route | Not offered on this route | ||
| Multi | No | $0.44 | $1.32 | $0.01 | Not offered on this route | Not offered on this route |
The model
Run Kilo Code on other models
Step-by-step setup for running Kilo Code on each of these models through Opper.
Claude Haiku 5.5Mistral Large 4Gemini 4 ArgonGPT-6 SolGPT-6 LunaClaude Opus 5.5Grok 4.7MiMo V2.6 ProMiMo V2.6 FlashLing-3.0-flash-FinDeepSeek V4.1 FlashLing-3.0-flash-VLGPT-6 AstraQwen3.8-MaxGemini 3.8 FlashMuse Spark 1.3 ContributorClaude Fable 5.1GLM-5.3-FlashQwen3.8 Flash-NextGLM-5.3Qwen3.8 27BDeepSeek V4 ProGemini 3.7 FlashGrok 4.6Qwen3.8-2.4T-A95BInkling-SmallClaude Opus 5Gemini 3.6 FlashKimi K3GPT-5.6 SolGPT-5.6 TerraGPT-5.6 LunaGrok 4.5Claude Sonnet 5GLM-5.2Kimi K2.7 CodeClaude Fable 5MiniMax M3Claude Opus 4.8Qwen3.7-MaxKimi K2.6Claude Opus 4.7GLM 5.1Gemini 3.1 Pro PreviewClaude Sonnet 4.6GLM 4.7GPT-5Grok 4.20 ReasoningDeepSeek V4 Flash VisionHy4 PreviewQwen3.8 FlashMiniMax H3SCX-coderMAGPiEGreen LGreen RSee all 700+ models
More apps on Opper
Cursor
Point Cursor's OpenAI base URL at Opper to run it on any of 700+ models.
Editors
OpenAI-compatible
Cline
Cline's OpenAI-Compatible provider points straight at Opper's gateway.
Editors
OpenAI-compatible
Continue
Add Opper as an OpenAI provider in config.yaml and Continue's chat, edit and autocomplete run on any model.
Editors
OpenAI-compatible