Retired · 10 Sep 2026
DeepSeek removed V4 Flash from its API on 10 September 2026, replacing it with V4.1 Flash. The replacement is cheaper on both input and output ($0.30/$1.20 per million tokens against $0.44/$1.32) and keeps the million-token context window.
Use DeepSeek V4.1 Flash. It runs on the same endpoint and the same key, so switching is a one-line change to the model id.
Switch
What to use instead
DeepSeek V4 Flash is no longer callable. DeepSeek points to DeepSeek V4.1 Flash, and every model below runs on the same endpoint and the same key, switching is a one-line change to the model id.
- "model": "deepseek/deepseek-v4-flash"
+ "model": "deepseek/deepseek-v4-1-flash"DeepSeek V4.1 Flash
RecommendedDeepSeek
DeepSeek's cheapest current model, a million-token window at flash rates.
$0.3 / M input · $1.2 / M output · $0.006 / M cached input
DeepSeek V4 Pro
DeepSeek
Retired by DeepSeek on 14 Sep 2026. Requests are served by V4.1 Flash from then, and billed at Flash's rate.
$1.32 / M input · $3.96 / M output · $0.044 / M cached input
Gemini 3 Flash (preview)
The Gemini 3 Flash preview line.
$0.5 / M input · $3 / M output
Claude Haiku 4.5
Anthropic
Fast, cheap frontier-family model for high-volume tasks.
$1 / M input · $5 / M output
DeepSeek V4 Flash API
The V4 family's speed tier, near-V4 quality on everyday calls at the lowest price in the family.
Model spec
- Input
- $0.44per 1M tokens
- Output
- $1.32per 1M tokens
- Context
- 128K
Model ID
OpenAI-compatible · api.companyfabric.com/v1
Overview
About DeepSeek V4 Flash
The V4 family's speed tier, near-V4 quality on everyday calls at the lowest price in the family. Every model on CompanyFabric shares the same API key, billing balance, and rate-limit envelope, one integration covers the entire library.
Facts
At a glance
Availability
Retired
Added 10 Aug 2026
Pricing
$0.44 in · $1.32 out
Per 1M tokens, metered exactly per call
Context window
128K tokens
Commercial use
See license
Open weights; commercial use permitted (MIT-style model license).
Variants
All endpoints
DeepSeek V4
Retired$0.3/Mtok inOpen-weight frontier-adjacent reasoning at commodity prices.
Chat Completions
DeepSeek V4.1 Flash
$0.3/Mtok inDeepSeek's cheapest current model, a million-token window at flash rates.
Chat Completions
DeepSeek V4 Pro
$1.32/Mtok inRetired by DeepSeek on 14 Sep 2026. Requests are served by V4.1 Flash from then, and billed at Flash's rate.
Chat Completions
DeepSeek V4 Flash
Retired$0.44/Mtok inThe V4 family's speed tier, near-V4 quality on everyday calls at the lowest price in the family.
Chat Completions
Quickstart
How to use the DeepSeek V4 Flash API
- 1
Create a free CompanyFabric account, starter credits are included, no card required.
- 2
Copy your API key from the dashboard. One key covers every model in the library.
- 3
Point any OpenAI SDK at api.companyfabric.com/v1 and set model to "deepseek/deepseek-v4-flash".
- 4
Read the exact metered cost of the call from the response, the same number shown in the playground.
Use cases
What teams build with it
Agents & copilots
Drive agent loops, tool calls, and user-facing assistants over the OpenAI-compatible endpoint.
agentstool useassistants
Content pipelines
Summarization, rewriting, and structured generation at metered per-token cost.
contentsummarization
Extraction & classification
Turn unstructured input into typed JSON with schema-constrained output.
extractionjson mode
Get better output
Prompting tips
- State the output format before the task, models follow contracts declared early.
- Few-shot beats description: two worked examples outperform a paragraph of rules.
- Cap output length explicitly when cost matters; output tokens dominate most bills.
Exact, metered, prepaid
DeepSeek V4 Flash pricing
DeepSeek V4 Flash pricing is per token: $0.44 / M input · $1.32 / M output. Output tokens cost 3× input tokens, so long generations, not long prompts, are what actually drive most bills. A typical call with a 2k-token prompt and a 1k-token answer costs about $0.0022.
Every call is metered exactly and attributed to your key, the dashboard, the API usage response, and your invoice all read from the same ledger row. Cap any key's monthly spend with a budget cap, and bring your own provider key (BYOK) at 0% platform fee if you already have a direct contract.
| Endpoint | Type | Price |
|---|---|---|
| DeepSeek V4 | Chat | $0.3 / M input · $0.9 / M output |
| DeepSeek V4.1 Flash | Chat | $0.3 / M input · $1.2 / M output · $0.006 / M cached input |
| DeepSeek V4 Pro | Chat | $1.32 / M input · $3.96 / M output · $0.044 / M cached input |
| DeepSeek V4 Flash | Chat | $0.44 / M input · $1.32 / M output |
Comparisons
DeepSeek V4 Flash vs the alternatives
DeepSeek V4 Flash vs Gemini 3 Flash (preview)
DeepSeek V4 Flash and Gemini 3 Flash (preview) compete for the same text workloads. Both run behind the same CompanyFabric key at exact metered prices, A/B them on your real prompts and let the outputs decide, then switch with a one-line change.
Full comparison: DeepSeek V4 Flash vs Gemini 3 Flash (preview) →DeepSeek V4 Flash vs Claude Haiku 4.5
DeepSeek V4 Flash and Claude Haiku 4.5 compete for the same text workloads. Both run behind the same CompanyFabric key at exact metered prices, A/B them on your real prompts and let the outputs decide, then switch with a one-line change.
Full comparison: DeepSeek V4 Flash vs Claude Haiku 4.5 →Compare
DeepSeek V4 Flash head to head
FAQ
Frequently asked questions
How much does the DeepSeek V4 Flash API cost?
$0.44 / M input · $1.32 / M output. Every call is metered exactly and shown before you run it.
How do I get a DeepSeek V4 Flash API key?
Create a CompanyFabric account, and one key unlocks DeepSeek V4 Flash and every other model in the library. Free starter credits are included, no subscription, no card required to try it.
Why use DeepSeek V4 Flash on CompanyFabric instead of going direct?
One key, one prepaid balance, and one rate-limit envelope across the whole library, at pricing at parity with or below the direct API. Model switching is a one-line change, and BYOK routing is 0% fee.
Is the API OpenAI-compatible?
Yes, point any OpenAI SDK at api.companyfabric.com/v1 and set model to "deepseek/deepseek-v4-flash".
Can I use the output commercially?
Open weights; commercial use permitted (MIT-style model license).
How does billing work?
Prepaid credits via card, or BYOK with your own provider keys at 0% platform fee. No subscription required; balances never expire.
Provider
About DeepSeek
DeepSeek publishes the deepseek family. Also in this family: DeepSeek V4, DeepSeek V4.1 Flash, DeepSeek V4 Pro. License: Open weights; commercial use permitted (MIT-style model license).
One key. Every model. Exact prices.
Run DeepSeek V4 Flash with free starter credits. Free starter credits included, no subscription required.