DeepSeek V4 Flash Vision Exp
DeepSeekhuggingface.co/deepseek-ai/DeepSeek-V4-Flash-Vis
DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of [DeepSeek V4 Flash 0731](https://openrouter.ai/deepseek/deepseek-v4-flash-0731) from DeepSeek, adding image understanding while matching the base model on text capabilities including agents,...
Updated 3 min ago · first seen 11 Sept 2026
model_01M294AJ4V6A3PXCEM2FCQ5NQV
- Parameters
- 304.6B
- T2 · 22 min ago
- Context
- 1.05M tokens
- T2 · 23 min ago
- Released
- 31 Aug 2026
- T2 · 3 min ago
- License
- mit
- T2 · 3 min ago
Specification
- Release date
- 31 Aug 2026
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 min agomedium
- Openness
- open-weights
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 22 min agomedium
- License
- mit
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 min agomedium
- Architecture
- DeepseekV4ForCausalLM
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 min agomedium
- Parameters
- 304.6B
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 22 min agomedium
- Context window
- 1.05M tokens
Source:OpenRouter public model & pricing listingT2observed 23 min agomedium
- Max output
- 943.7K tokens
Source:OpenRouter public model & pricing listingT2observed 23 min agomedium
- Modalities
- image, text
Source:OpenRouter public model & pricing listingT2observed 23 min agomedium
- Input modalities
- image, text
Source:OpenRouter public model & pricing listingT2observed 23 min agomedium
- Output modalities
- text
Source:OpenRouter public model & pricing listingT2observed 23 min agomedium
- Tokenizer
- DeepSeek
Source:OpenRouter public model & pricing listingT2observed 23 min agomedium
- Quantization format
- fp8
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 min agomedium
- File size
- 167.8 GB
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 min agomedium
- Hugging Face repo
- deepseek-ai/DeepSeek-V4-Flash-Vision-Exp
Source:OpenRouter public model & pricing listingT2observed 23 min agomedium
- Pipeline tag
- image-text-to-text
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 22 min agomedium
- Model card
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 22 min agomedium
- Downloads
- 443,954
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 min agomedium
- Likes
- 864
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 min agomedium
- Gated
- No
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 min agomedium
- Hf inference providers
- deepinfra, fireworks-ai, novita
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 min agomedium
- Is quantized
- Yes
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 min agomedium
- Last modified
- 2026-09-01T09:22:10+00:00
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 22 min agomedium
- Library name
- transformers
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 min agomedium
- Downloads all time
- 443,954
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 min agomedium
- Model type
- deepseek_v4
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 min agomedium
- Openrouter id
- deepseek/deepseek-v4-flash-vision-exp
Source:OpenRouter public model & pricing listingT2observed 23 min agomedium
- Supported parameters
- frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, reasoning_effort, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p
Source:OpenRouter public model & pricing listingT2observed 23 min agomedium
- Tags
- transformers, safetensors, deepseek_v4, text-generation, image-text-to-text, 8-bit, fp8
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 min agomedium
- Weights dtype
- BF16, F32, F8_E4M3, I64, I8
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 min agomedium
Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →
Provenance
Attributed facts
34
Source tiers
T234
Freshest observation
3 min ago
Conflicts
None
Modalities
- Modalities
- imagetext
- Input
- imagetext
- Output
- text
Capabilities
Tool calling
Yes
OpenRouter public model & pricing listing · T2
Structured output
Yes
OpenRouter public model & pricing listing · T2
Reasoning
Yes
OpenRouter public model & pricing listing · T2
Vision
Yes
OpenRouter public model & pricing listing · T2
Audio
Unavailable
Fine-tuning available
Unavailable
- Context window
- 1.05M tokens
Source:OpenRouter public model & pricing listingT2observed 23 min agomedium
- Max output
- 943.7K tokens
Source:OpenRouter public model & pricing listingT2observed 23 min agomedium
- Tokenizer
- DeepSeek
Source:OpenRouter public model & pricing listingT2observed 23 min agomedium
No benchmark results recorded
Current prices
| Provider | Input / 1M | Output / 1M | Cached in | Batch in / out | Context | Observed | Source |
|---|---|---|---|---|---|---|---|
| DeepSeek APIdeepseek/deepseek-v4-flash-vision-exp:batch | $0.11 | $0.33 | $0.0035 | — | 1.05M | 23 min ago | openrouter.aiT2 |
| DeepSeek APIdeepseek/deepseek-v4-flash-vision-exp | $0.22 | $0.66 | $0.007 | — | 1.05M | 23 min ago | openrouter.aiT2 |
| Fireworks AIfireworks/deepseek-v4-flash-vision-exp | $0.22 | $0.66 | $0.007 | — | — | 33 min ago | app.fireworks.aiT1 |
USD per 1M tokens as published by each provider (USD). Rows are append-only: every change is kept in the history below.
Available through 2
Price history
Input price · USD / 1M tokens
Output price · USD / 1M tokens
- Fireworks AI
- DeepSeek API
Memory need = bytes per parameter (4-bit ≈ 0.5 × 1.15 overhead, 8-bit 1.0, fp16 2.0) + a KV-cache allowance. Not a measurement.
| Hardware | Quantization | Memory | Est. need | Fits |
|---|---|---|---|---|
| Apple M3 Ultra | 4bit | — | 175.7 GB | Yes |
| AMD Instinct MI325X | 4bit | 256 GB | 175.7 GB | Yes |
| AMD Instinct MI300X | 4bit | 192 GB | 175.7 GB | Yes |
| Apple M2 Ultra | 4bit | — | 175.7 GB | Yes |
| NVIDIA B200 | 4bit | 180 GB | 175.7 GB | Yes |
| NVIDIA H200 | 4bit | 141 GB | 175.7 GB | No |
| Apple M1 Ultra | 4bit | — | 175.7 GB | No |
| Apple M3 Max | 4bit | — | 175.7 GB | No |
| Apple M4 Max | 4bit | — | 175.7 GB | No |
| NVIDIA DGX Spark | 4bit | 128 GB | 175.7 GB | No |
| Apple M2 Max | 4bit | — | 175.7 GB | No |
| NVIDIA A100 80GB | 4bit | 80 GB | 175.7 GB | No |
| NVIDIA H100 SXM | 4bit | 80 GB | 175.7 GB | No |
| Apple M1 Max | 4bit | — | 175.7 GB | No |
| Apple M4 Pro | 4bit | — | 175.7 GB | No |
| Apple M3 Pro | 4bit | — | 175.7 GB | No |
| Apple M1 Pro | 4bit | — | 175.7 GB | No |
| Apple M2 Pro | 4bit | — | 175.7 GB | No |
| Apple M4 | 4bit | — | 175.7 GB | No |
| NVIDIA GeForce RTX 5090 | 4bit | 32 GB | 175.7 GB | No |
| Apple M2 | 4bit | — | 175.7 GB | No |
| Apple M3 | 4bit | — | 175.7 GB | No |
| NVIDIA GeForce RTX 3090 | 4bit | 24 GB | 175.7 GB | No |
| NVIDIA GeForce RTX 4090 | 4bit | 24 GB | 175.7 GB | No |
| Apple M1 | 4bit | — | 175.7 GB | No |
No lineage recorded
Papers 0
No papers linked yet.
Repositories 0
No repositories linked yet.
As of
Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.
Claim history · Input modalities
Input modalitiesmodalities_input1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| image, text | → current | current | OpenRouter public model & pricing listingT2 | medium | deterministic |
Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →
DeepSeek V4 Flash Vision Exp: release date changed from 2026-08-21 to 2026-08-31
Release date21 Aug 2026→31 Aug 2026huggingfaceDeepSeek API lists DeepSeek V4 Flash Vision Exp at $0.11 in / $0.33 out per 1M tokens
openrouterDeepSeek API lists DeepSeek V4 Flash Vision Exp at $0.22 in / $0.66 out per 1M tokens
openrouterNew model: DeepSeek V4 Flash Vision Exp (DeepSeek)
fireworks_pricingFireworks AI lists DeepSeek V4 Flash Vision Exp at $0.22 in / $0.66 out per 1M tokens
fireworks_pricing
| Source | Document | Type | Tier | Last observed | Snapshots |
|---|---|---|---|---|---|
| Fireworks AI — pricing | docs.fireworks.ai/serverless/pricing.md | pricing | T1· Official | 28 min ago | 1 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/deepseek-ai/DeepSeek-V4-Flash-Vision-Exp | model_page | T2· Quality secondary | 3 min ago | 1 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/models?author=deepseek-ai&p=0&sort=downloads | listing | T2· Quality secondary | 20 min ago | 2 |
| OpenRouter public model & pricing listing | openrouter.ai/api/v1/models | catalogue | T2· Quality secondary | 23 min ago | 1 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.