DeepSeek · Text model
DeepSeek V4.1 Flash API model through CorvusLLM
Visual and coding workflows. Provider description; Corvus feature support needs verification.
deepseek-v4.1-flashCurrently unavailable through CorvusLLM
Saved catalog snapshot. Live availability has not been confirmed on this page.
Overview
DeepSeek V4.1 Flash uses the public Corvus model ID deepseek-v4.1-flash. Input, output and cache usage have separate rates. Use the exact ID when configuring an OpenAI-compatible client.
Provider references & limitations
Reference checked 2026-10-26. External specifications do not verify the Corvus supplier route, context limit, output maximum, tools, reasoning or media support.
Official DeepSeek model reference · Provider ID deepseek-flash
OpenRouter reference: 1,048,576 tokens of context. Input: text, image. Output: text. These are external endpoint specifications.
Direct-provider ID deepseek-flash now serves 1017 release. Corvus exposes separate deepseek-v4.1-flash ID. Exact supplier version unconfirmed.
OpenRouter aggregate/top-provider context and output maxima are provider-specific; official direct API currently says 1M context and 384K maximum output.
Pricing
Historical saved rates · USD / 1M tokens. Current catalog · Machine-readable model data.
| Usage | Rate | Unit |
|---|---|---|
| Input tokens | $0.105 | USD / 1M tokens |
| Output tokens | $0.42 | USD / 1M tokens |
| Cache read tokens | $0.0021 | USD / 1M tokens |
| Cache write tokens (5 min) | $0 | USD / 1M tokens |
| Cache write tokens (1 hour) | $0 | USD / 1M tokens |
Estimate usage cost
Local arithmetic only. Input tokens × input rate / 1,000,000 + output tokens × output rate / 1,000,000. Cache usage is separate. No request is sent.
Saved pricing reference date: 2026-09-18. This is not an availability check. Stored comparison source. External comparison prices may differ by date, context and billing unit; no like-for-like savings claim is made here.
API example
OpenAI-compatible base URL: https://base.corvusllm.com/v1. Replace the placeholder with your private Corvus key.
curl https://base.corvusllm.com/v1/chat/completions \
-H "Authorization: Bearer YOUR_CORVUS_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"deepseek-v4.1-flash","messages":[{"role":"user","content":"Hello"}]}'Related models
Saved catalog alternatives; check current availability before use.
Model FAQ & service boundaries
What slug should I use for DeepSeek V4.1 Flash?
Use deepseek-v4.1-flash as the exact public CorvusLLM model ID. Check the current catalog before sending a request.
Which base URL should I use with DeepSeek V4.1 Flash?
Use https://base.corvusllm.com/v1 for OpenAI-compatible clients. Anthropic-style clients use https://base.corvusllm.com/anthropic only where documented.
Is DeepSeek V4.1 Flash an official provider account?
No. CorvusLLM is an independent prepaid access layer and is not affiliated with OpenAI, Anthropic, Google, or Z.AI.
What should I check before using DeepSeek V4.1 Flash heavily?
Confirm current availability, pricing units and supported API options. Corvus route context and feature limits are not confirmed by external provider references.
Independent AI API proxy. Not affiliated with OpenAI, Anthropic, Google, or Z.AI. Prepaid balance. Card, wallet, or crypto checkout. No financially backed SLA. Do not send sensitive or regulated data. Prompt content is forwarded upstream through shared proxy infrastructure.