Back to all models

DeepSeek V4 Flash

DeepSeek's fast and cost-efficient V4 model with extended context and reasoning.

deepseek-v4-flash
STABLEGet StartedView uptime
1,050,000 context
Released April 24, 2026
Starting at $0.05/M input tokens
Starting at $0.10/M output tokens
Streaming
Tools
Reasoning
Reasoning Budget
JSON Output
Structured JSON
No ratings yetSign in to rate

Select Provider

All Providers for DeepSeek V4 Flash

PassingRight routes requests to the best providers that are able to handle your prompt size and parameters.

Alibaba Cloud
Context: 1M
Input
$0.2
/M tokens
Cache Read
$0.04
/M tokens
Output
$0.4
/M tokens
Get Started
Gonka24
Context: 390k
Input
$0.051
/M tokens
Cache Read
$0.0097
/M tokens
Output
$0.104
/M tokens
Get Started
RanoAI
Context: 1MQuant: fp4
Input
$0.14
/M tokens
Cache Read
$0.028
/M tokens
Output
$0.28
/M tokens
Get Started
Together AI
Context: 163.8k
Input
$0.14
/M tokens
Cache Read
$0.03
/M tokens
Output
$0.28
/M tokens
Get Started
Baidu
Context: 1.0M
Input
$0.44
/M tokens
Cache Read
$0.014
/M tokens
Output
$1.32
/M tokens
Get Started
CanopyWave
Context: 1MQuant: fp8
Input
$0.14
/M tokens
Cache Read
$0.03
/M tokens
Output
$0.28
/M tokens
Get Started
Consensus Protocol
Context: 524.3kQuant: int8
Input
$0.13
/M tokens
Cache Read
$0.02
/M tokens
Output
$0.27
/M tokens
Get Started
Tencent Cloud
Context: 1M
Input
$0.14
/M tokens
Cache Read
$0.0028
/M tokens
Output
$0.28
/M tokens
Get Started
DeepInfra
Context: 1MQuant: fp8
Input
$0.08
/M tokens
Cache Read
$0.016
/M tokens
Output
$0.18
/M tokens
Get Started
Fireworks AI
Context: 1.0M
Input
$0.22
/M tokens
Cache Read
$0.007
/M tokens
Output
$0.66
/M tokens
Get Started
Runware
Context: 1.0MQuant: fp8
Input
$0.076
/M tokens
Cache Read
$0.014
/M tokens
Output
$0.153
/M tokens
Get Started
ByteDance
Context: 1.0M
Input
$0.44
/M tokens
Cache Read
$0.014
/M tokens
Output
$1.32
/M tokens
Get Started
NovitaAI
Context: 1.1MQuant: fp8
Input
$0.14
/M tokens
Cache Read
$0.028
/M tokens
Output
$0.28
/M tokens
Get Started

Frequently asked questions

What is DeepSeek V4 Flash?

DeepSeek's fast and cost-efficient V4 model with extended context and reasoning. You can access it through PassingRight's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.

How much does DeepSeek V4 Flash cost?

Pricing for DeepSeek V4 Flash on PassingRight starts at $0.05 per million input tokens and $0.10 per million output tokens, depending on the provider. The pricing table above always reflects the current per-provider rates.

What is the context length of DeepSeek V4 Flash?

DeepSeek V4 Flash supports a context window of up to 1,050,000 tokens on its largest provider deployment.

Which providers serve DeepSeek V4 Flash?

DeepSeek V4 Flash is served by Alibaba Cloud, Gonka24, RanoAI, Together AI, Baidu, CanopyWave, Consensus Protocol, Tencent Cloud, DeepInfra, Fireworks AI, Runware, ByteDance, NovitaAI through PassingRight. Requests are automatically routed to the best available provider, with fallback when a provider has issues.

Does DeepSeek V4 Flash support tool calling and structured outputs?

Yes. DeepSeek V4 Flash supports both tool (function) calling and strict JSON output schema (upstream-enforced) through PassingRight.

When was DeepSeek V4 Flash released?

DeepSeek V4 Flash was released on April 24, 2026.

More DeepSeek models

Browse all models

DeepSeek V4.1 Flash

Up to 15% off

1,050,000 context$0.13 in / $0.51 out per 1M

DeepSeek V4 Pro

Up to 15% off

1,050,000 context$0.37 in / $0.74 out per 1M

DeepSeek V3.2

163,840 context$0.26 in / $0.38 out per 1M