
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 output from a 552B-parameter backbone, an asymmetric split that keeps per-token compute low relative to the model's total size. Image understanding is native to the architecture, with visual and text embeddings trained jointly from the start of pre-training rather than added afterward as in the earlier experimental V4 Flash Vision Exp(opens in new tab).
It is suited for coding, terminal, and computer-use agents, along with long-horizon tasks that must run to completion across many steps and long-context document and chart analysis. Compressed KV caching cuts cache memory to roughly a quarter of the previous Flash generation, which matters for agent loops that repeatedly re-read large contexts. DeepSeek positions it as the cost-efficient tier of the V4.1 family and reports that it exceeds V4 Pro(opens in new tab) on performance, speed, and task completion time.
Modalities
In / Out Price
$0.15 / $0.60per 1M
Context
1.0M
Released
Sep 10, 2026
Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick — Balanced (price + speed), Nitro (fastest), or Exacto (highest tool-calling accuracy).
The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.
Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).
Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.
Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.
Token volume and request traffic to this model over time.
Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.
| $0.15 | $0.60 | $0.003 | 1.32s | 138 tps | ||
| $0.30 | $1.20 | $0.006 | 1.40s | 142 tps | ||
| $0.30 | $1.20 | $0.006 | 2.91s | 15 tps | ||
| $0.15 | $1.20 | $0.003 | 7.23s | 3 tps |
Throughput
142tok/s
P50, best across providers
Latency
1.32s
P50, best provider
100.00%
99.84%
When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and customization options.

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 output from a 552B-parameter backbone, an asymmetric split that keeps per-token compute low relative to the model's total size.
DeepSeek V4.1 Flash costs $0.15/M input tokens and $0.60/M output tokens, with separate rates for Cache Read at $0.003/M tokens.
DeepSeek V4.1 Flash has a 1,048,576 token context window. It supports up to 384,000 completion tokens.
Yes. DeepSeek V4.1 Flash accepts tools and tool_choice for function calling. It supports response_format for JSON output, without JSON-schema enforcement.
DeepSeek V4.1 Flash accepts text and images as input and returns text.
DeepSeek V4.1 Flash is served by 4 providers on OpenRouter: DeepSeek, io.net, NovitaAI and DeepInfra. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.
DeepSeek V4.1 Flash was released on September 10, 2026.