DeepSeek: DeepSeek V4 Flash Vision Exp

Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work

Source-linked deepseek-flash Closed weights Released 2026-08-21

API record Report

InputT

OutputT

Input price$0.15/M

Output price$0.6/M

Context1M

Max output384K

Providers19

Inference availability

Providers

Provider-specific identifiers, limits, and listed prices per million tokens. Every row links back to the provider's own documentation.

Report a price

Providers offering DeepSeek V4 Flash Vision Exp
Provider	Provider model ID	Context	Max output	Input	Output	Cache read	Capabilities	Docs
CrofAI	`deepseek-v4-flash-vision-exp`	1M	131.072K	$0.08	$0.2	$0.007	ReasoningToolsJSON	Docs ↗
OpenCode Zen	`deepseek-v4-flash-vision-exp`	1M	384K	$0.14	$0.28	$0.028	ReasoningToolsJSON	Docs ↗
LLM Gateway	`deepseek/deepseek-v4-flash-vision-exp`	1.05M	393.216K	$0.14	$0.28	$0.003	ReasoningTools	Docs ↗
DevPass (LLM Gateway)	`deepseek-v4-flash-vision-exp`	1.05M	384K	$0.14	$0.28	$0.003	ReasoningToolsJSON	Docs ↗
AMD	`DeepSeek-V4-Flash-Vision-Exp`	1M	384K	$0.14	$0.28	$0.003	ReasoningToolsJSON	Docs ↗
OrcaRouter	`deepseek/deepseek-v4-flash-vision-exp`	1M	384K	$0.147	$0.295	$0.02	ReasoningToolsJSON	Docs ↗
DeepSeek	`deepseek-v4-flash-vision-exp`	1M	384K	$0.15	$0.6	$0.003	ReasoningToolsJSON	Docs ↗
OpenCode Go	`deepseek-v4-flash-vision-exp`	1M	384K	$0.15	$0.6	$0.003	ReasoningToolsJSON	Docs ↗
NanoGPT	`deepseek/deepseek-v4-flash-vision-exp`	1.04858M	384K	$0.22	$0.66	$0.007	ReasoningToolsJSON	Docs ↗
Eden AI	`deepseek/deepseek-v4-flash-vision-exp`	1.04858M	384K	$0.22	$0.66	$0.007	ReasoningToolsJSON	Docs ↗
Vancine	`deepseek-v4-flash-vision-exp`	1M	384K	$0.22	$0.66	$0.007	ReasoningToolsJSON	Docs ↗
OpenRouter	`deepseek/deepseek-v4-flash-vision-exp`	1.04858M	943.718K	$0.22	$0.66	$0.007	ReasoningToolsJSON	Docs ↗
Fireworks AI	`accounts/fireworks/models/deepseek-v4-flash-vision-exp`	1M	384K	$0.22	$0.66	$0.007	ReasoningToolsJSON	Docs ↗
Vercel AI Gateway	`deepseek/deepseek-v4-flash-vision-exp`	1.04858M	1.04858M	$0.22	$0.66	$0.007	ReasoningToolsJSON	Docs ↗
CrossModel	`deepseek/deepseek-v4-flash-vision-exp`	1M	384K	$0.27	$1.08	$0.005	ReasoningToolsJSON	Docs ↗
Kilo Gateway	`deepseek/deepseek-v4-flash-vision-exp`	1.04858M	943.718K	$0.44	$1.32	$0.028	ReasoningToolsJSON	Docs ↗
Hugging Face	`deepseek-ai/DeepSeek-V4-Flash-Vision-Exp`	1.04858M	384K	$0.44	$1.32	—	ReasoningToolsJSON	Docs ↗
Deep Infra	`deepseek-ai/DeepSeek-V4-Flash-Vision-Exp`	1.04858M	384K	$0.44	$1.32	$0.014	ReasoningToolsJSON	Docs ↗
Ofox	`deepseek/deepseek-v4-flash-vision-exp`	1M	384K	$0.44	$1.32	$0.014	ReasoningToolsJSON	Docs ↗

Capability badges appear only where the provider catalog explicitly lists support. A blank cell means the source is silent, not that the feature is absent.

Listed rates

Price across providers

Input price per million tokens as published by each provider. Bars are drawn from listed rates only — no traffic weighting, since the catalog observes no requests.

Lowest input $0.08/M

Across 19 priced providers

Median input $0.22/M

Midpoint of listed rates

Highest input $0.44/M

5.5× the lowest listed rate

Output range $0.2 – $1.32

Per million output tokens

CrofAI $0.08/MLowest

OpenCode Zen $0.14/M

LLM Gateway $0.14/M

DevPass (LLM Gateway) $0.14/M

AMD $0.14/M

OrcaRouter $0.147/M

DeepSeek $0.15/M

OpenCode Go $0.15/M

NanoGPT $0.22/M

Eden AI $0.22/M

Vancine $0.22/M

OpenRouter $0.22/M

Fireworks AI $0.22/M

Vercel AI Gateway $0.22/M

CrossModel $0.27/M

Kilo Gateway $0.44/M

Hugging Face $0.44/M

Deep Infra $0.44/M

Ofox $0.44/M

Cost calculator

Estimate a workload

Provider Input tokens 1,000,000 Output tokens 250,000 Cached input 0%

$0.00

Excludes taxes, non-token charges, and tiered discounts.

Context limits also differ by provider, from 1M to 1.05M tokens. Compare the provider table above before choosing on price alone.

Specification

Capabilities

Recorded from the source catalog and provider listings.

✓ Reasoning Yes

✓ Tool calling Yes

✓ Structured output Yes

✓ Attachments Yes

✓ Vision input Yes

× Open weights No

Creator: DeepSeek
Model family: deepseek-flash
Knowledge cutoff: Not documented
License: Not documented
Release date: 2026-08-21
Model ID: deepseek/deepseek-v4-flash-vision-exp

Published evaluations

Benchmarks

Every result stays attached to its source, version, metric and harness. Scores from different versions are never merged, and the profile below plots each benchmark against its own population rather than on a shared scale.

Benchmark registry

No published benchmark results

ModelBench does not infer quality from price, context size, or model name. When a source publishes a comparable result, it appears here with its version and link.

Read the methodology

Catalog activity

Change log

Field-level changes detected between successful source imports.

Full change log

Sep 11, 2026Max Output Tokens943718 → 384000

Sep 11, 2026Context Length1048576 → 1000000

Sep 11, 2026Price Completion0.66 → 0.6

Sep 11, 2026Price Prompt0.22 → 0.15

Sep 11, 2026Max Output Tokens384000 → 943718

Sep 11, 2026Context Length1000000 → 1048576

Sep 11, 2026Price Completion0.6 → 0.66

Sep 11, 2026Price Prompt0.15 → 0.22

Sep 11, 2026Max Output Tokens943718 → 384000

Sep 11, 2026Context Length1048576 → 1000000

Provenance

Sources & verification

Every figure on this page traces back to one of these records.

Methodology

Last verified: Sep 11, 2026
Status: Source-linked
Confidence: Medium
Catalog source: Models.dev

Public API

Use this record

Fetch the complete source-linked model record. No key, no account, no rate-limited tier.

API documentation

Endpoint

GET https://model.kyssta.lol/api/v1/models/deepseek/deepseek-v4-flash-vision-exp

curl

curl "https://model.kyssta.lol/api/v1/models/deepseek/deepseek-v4-flash-vision-exp"

Common questions

Frequently asked questions

Answered directly from the stored record — nothing here is generated beyond the catalog's own fields.

What is DeepSeek V4 Flash Vision Exp?

Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work. It is published by DeepSeek and catalogued here from Models.dev.

How much does DeepSeek V4 Flash Vision Exp cost?

Listed input pricing starts at $0.08 per million tokens from CrofAI, rising to $0.44 across 19 listed providers.

What is the context length of DeepSeek V4 Flash Vision Exp?

DeepSeek V4 Flash Vision Exp accepts up to 1M tokens of context and returns up to 384K output tokens.

Does DeepSeek V4 Flash Vision Exp support tool calling and structured output?

Provider catalogs list support for tool calling, structured output, reasoning, and image input.

Which providers serve DeepSeek V4 Flash Vision Exp?

19 providers list this model: CrofAI, OpenCode Zen, LLM Gateway, DevPass (LLM Gateway), AMD, OrcaRouter and 13 more.

Are the weights for DeepSeek V4 Flash Vision Exp open?

No. This model is served through hosted APIs only.

When was DeepSeek V4 Flash Vision Exp released?

The catalog records a release date of 2026-08-21, last verified Sep 11, 2026.

More models from DeepSeek

View all →

DeepSeek: DeepSeek V3.1

DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...

163.84K ctx $0.25/M in DeepSeek: R1 Distill Llama 70B

DeepSeek R1 Distill Llama 70B is a distilled large language model based on [Llama-3.3-70B-Instruct](/meta-llama/llama-3.3-70b-instruct), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). The model combines advanced distillation techniques to achieve high performance across...

8.192K ctx $0.8/M in DeepSeek: R1 0528

May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...

163.84K ctx $0.5/M in DeepSeek: DeepSeek V3 0324

DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well...

163.84K ctx $0.25/M in