DeepSeek — Coding Model
DeepSeek V4.1 Flash API — 1M tokens context.
DeepSeek V4.1 Flash is the cheapest way to run a DeepSeek model at scale, and it is included on the free plan. It serves a 1M-token context window at $0.22 per million input tokens, which makes it practical for repository-scale context, bulk classification and high-volume agent loops where per-token cost dominates.
Model ID
deepseek-v4p1-flash
DeepSeek V4.1 Flash specifications
| Model ID | deepseek-v4p1-flash |
|---|---|
| Vendor | DeepSeek |
| Usage tier | Tier 1 |
| Context window | 1M tokens |
| Quantization | FP4 |
| Input | $0.22 per 1M tokens |
| Output | $0.66 per 1M tokens |
| Cache read | $0.04 per 1M tokens |
| Approx. output speed | ~200 tokens/sec |
Legacy model IDs that resolve to DeepSeek V4.1 Flash: deepseek-v4-flashdeepseek-v4-flash-0731. Aliases only resolve when your plan includes the model.
Why run DeepSeek V4.1 Flash on IN2PETA
- 1M-token context window
- Included on the free plan
- Fastest generation in the catalog
- FP4 quantised for low memory traffic
- OpenAI-compatible endpoint — switch providers by changing one base URL, not by rewriting your client.
Calling the DeepSeek V4.1 Flash API
DeepSeek V4.1 Flash is served from an OpenAI-compatible gateway. Change your base URL and API key, and existing OpenAI clients work unchanged.
curl https://code.in2peta.com/v1/coding/chat/completions \
-H "Authorization: Bearer $IN2PETA_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v4p1-flash",
"messages": [{"role": "user", "content": "Explain this function"}]
}'Set ANTHROPIC_BASE_URL to the same host to point Claude Code at the same gateway. See Getting Started for key setup, and Coding Endpoints for the full API reference.
Plans that include DeepSeek V4.1 Flash
Includes this model
Includes this model
Includes this model
Includes this model
Frequently asked questions
How do I access the DeepSeek V4.1 Flash API?
Point any OpenAI-compatible client at https://code.in2peta.com and send requests to /v1/coding/chat/completions with "model": "deepseek-v4p1-flash". The gateway is OpenAI-compatible, so existing SDKs work by changing the base URL and API key.
How much does the DeepSeek V4.1 Flash API cost?
DeepSeek V4.1 Flash is $0.22 per million input tokens and $0.66 per million output tokens, with cache reads at $0.044 per million. There is no per-request fee on top of token usage.
Which IN2PETA plans include DeepSeek V4.1 Flash?
DeepSeek V4.1 Flash is available on Free ($0/mo), Starter ($2/mo), Go ($5/mo), Pro ($15/mo). Requests for a model outside your plan return HTTP 403 with the allowed model list in the error body.
What is the context window of DeepSeek V4.1 Flash?
DeepSeek V4.1 Flash serves a 1M tokens context window and runs FP4 quantised on IN2PETA.
Start with DeepSeek V4.1 Flash today
This model is included on the free plan — no credit card required.