DeepseekFastReleased 10 September 2026
DeepSeek V4.1 Flash pricing, context and benchmark
DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture.
1.05M
Input context
944K
Output context
$0.051
Official input
$0.567
Official output
n/a
AA index
01 · Model Overview
Everything that matters, in one table
Context, pricing, cache, modalities and tooling, from the model registry and Artificial Analysis.
| Model | DeepSeek V4.1 Flash |
| Model ID | deepseek/deepseek-v4.1-flash |
| Provider | Deepseek |
| Release date | 10 September 2026 |
| Status | Generally available |
| Input context | 1,048,576 tokens |
| Output context | 943,718 tokens |
| Official input pricing | $0.051 per 1M tokens |
| Official output pricing | $0.567 per 1M tokens |
| Cache read pricing | $0.0058 per 1M tokens (98% off input) |
| Market input pricing | $0.006 per 1M (cheapest route) |
| Market output pricing | $0.5 per 1M (cheapest route) |
| Highest route pricing | $0.039 in, $1.2 out per 1M |
| Input modalities | text · image |
| Output modalities | text |
| Reasoning control | Not exposed |
| Tool support | Text generation only |
| Tokenizer | DeepSeek |
| Provider routes | 8 endpoints |
| Artificial Analysis index | Not published |
| Speed | 225 tokens/s, 37.19s to first token |
| Knowledge cutoff | Not publicly stated |
Input and output support
| Modality | Input | Output | Billed at |
|---|---|---|---|
| Text | ✓ yes | ✓ yes | $0.051 in |
| Image | ✓ yes | no | $0.051 in |
| Audio | no | no | not supported |
| Video | no | no | not supported |
| File (PDF) | no | no | not supported |
02 · Overview
What is DeepSeek V4.1 Flash?
DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture.
It activates 8B parameters on input and 16B on...
DeepSeek V4.1 Flash carries a 1.05M token window, uses the DeepSeek tokenizer and is served by Deepseek. On Hoodgen it sits in the Fast tier of the model menu next to its siblings, so you can switch mid conversation without losing the thread.
03 · Release
Release and what changed from the previous version
Released10 September 2026
| Property | V4 Flash Vision Exp | DeepSeek V4.1 Flash | Change |
|---|---|---|---|
| Released | 2026 | Sep 2026 | Newer release |
| Context | 1.05M | 1.05M | Unchanged |
| Max output | 944K | 944K | Changed |
| Input price | $0.216 | $0.051 | Cheaper |
| Output price | $0.647 | $0.567 | Cheaper |
| Input modalities | text, image | text, image | Unchanged |
| AA index | n/a | n/a | Newer benchmark run |
04 · Capabilities
Features and capabilities
◉
Vision
Screenshots, charts and photographed documents are read at the text token rate.
⚡
Prompt caching
Cached input costs $0.0058 per million instead of $0.051, so stable prefixes get cheaper.
07 · Use cases
What can you do with DeepSeek V4.1 Flash?
High volume drafts
Captions, titles, product blurbs and rewrite passes where cost per call dominates.
Inline assistants
Autocomplete, quick replies and menu helpers that must answer inside a second.
Batch classification
Tagging, routing and extraction across thousands of short inputs.
Cheap agent loops
Tool calling loops that do not need frontier grade reasoning.
08 · Cost levers
Prompt caching and how to cut the bill
Cached input bills at $0.0058 per million instead of $0.051, a 98% discount. Keep the system prompt and documents first and the changing question last, so every call hits the cache.
09 · Pricing
DeepSeek V4.1 Flash pricing
Official pricing
List price
$0.051 / 1M in
$0.567 / 1M out
- $0.0058 cached input
- 1.05M context
- text, image input
Cheapest route
$0.006 / 1M in
$0.5 / 1M out
- 8 routes on OpenRouter
- What Hoodgen routes to first
- Same model, lower bill
Highest route
$0.039 / 1M in
$1.2 / 1M out
- Priority or premium tier
- Best under load
- Use for latency critical calls
Market pricing, every route
| Provider | Tier | Input | Output | Cache read | Uptime 24h |
|---|---|---|---|---|---|
| Relace | standard | $0.006 | $0.5 | $0.005 | 100.0% |
| Morph | standard | $0.022 | $0.4 | $0.004 | 98.5% |
| PrimeIntellect | standard | $0.039 | $1.2 | $0.0012 | 99.6% |
| OpenInference | standard | $0.05 | $0.8 | $0.006 | 100.0% |
| Wafer | standard | $0.051 | $0.567 | $0.018 | 100.0% |
| InferenceNet | standard | $0.103 | $0.6 | $0.008 | 100.0% |
| InferenceNet | standard | $0.103 | $0.6 | $0.008 | 100.0% |
| DeepInfra | flex | $0.112 | $0.336 | $0.00336 | 10.9% |
API pricing and cost calculator
| Rate | Per call | Total | Credits |
|---|---|---|---|
| Cheapest route | $0.0009 | $0.43 | 408 |
| List price | $0.0013 | $0.66 | 631 |
| Highest route | $0.0026 | $1.29 | 1226 |
10 · Developers
API and developer information
| Model ID | deepseek/deepseek-v4.1-flash |
| Endpoint | https://openrouter.ai/api/v1/chat/completions |
| Parameters | prompt and max_tokens |
| Streaming | Yes, server sent events |
| Modality string | text+image->text |
| Max prompt tokens | 1,048,576 |
| Max completion tokens | 943,718 |
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek/deepseek-v4.1-flash",
"messages": [{ "role": "user", "content": "Summarise this document." }],
"max_tokens": 1024
}'11 · Limitations
Model limitations
| Text only output | It cannot generate images, audio or video. Pair it with an image model on Hoodgen when you need visuals. |
| Output cap | 943,718 tokens per request. Long deliverables have to be chunked. |
| Benchmarks not published | Artificial Analysis does not publish an Intelligence Index for this release, so no benchmark score is claimed here. |
| Knowledge cutoff | The provider does not state a fixed cutoff for every release. Verify very recent events against search. |
| Depth ceiling | Fast tier: strong on throughput, weaker than flagship tiers on long multi step reasoning. |
12 · Comparison
DeepSeek V4.1 Flash vs other Deepseek models
| Model | Context | Input /1M | Output /1M | AA index | Released |
|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 1.05M | $0.051 | $0.567 | n/a | Sep 2026 |
| DeepSeek V4 Pro 0423 | 1.05M | $0.9 | $1.5 | n/a | 2026 |
| R1 0528 | 164K | $0.5 | $2.15 | n/a | 2025 |
| DeepSeek V3.1 | 164K | $0.25 | $0.95 | n/a | 2025 |
| V4 Flash Vision Exp | 1.05M | $0.216 | $0.647 | n/a | 2026 |
| DeepSeek V4 Pro 0813 | 1.05M | $0.1 | $8 | n/a | 2026 |
13 · Privacy
Privacy and data policy
- On Hoodgen, prompts and attachments answer that request and stay in your conversation history so you can reopen it. They are not used to train models.
- Requests route through OpenRouter to Deepseek and are covered by that provider's API terms.
- Do not paste secrets or personal data you would not send to any hosted model.
14 · FAQ
DeepSeek V4.1 Flash questions, answered
DeepSeek V4.1 Flash is a fast model from Deepseek, released 10 September 2026. DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture.
✦
Start chatting with DeepSeek V4.1 Flash
Free to try on Hoodgen AI, with a live credit estimate before every send. No API key, no setup.