DeepSeek's fast and cost-efficient V4 model with extended context and reasoning.
LLM Gateway routes requests to the best providers that are able to handle your prompt size and parameters.
Peak: Monday–Friday, 09:00–12:00 and 14:00–18:00 Beijing time.
Off-peak: Monday–Friday outside those hours, plus all day Saturday and Sunday.
DeepSeek's fast and cost-efficient V4 model with extended context and reasoning. You can access it through LLM Gateway's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.
Pricing for DeepSeek V4 Flash on LLM Gateway 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.
DeepSeek V4 Flash supports a context window of up to 1,050,000 tokens on its largest provider deployment.
DeepSeek V4 Flash is served by GapGPT, AvalAI, OpenRouter, DeepSeek, Runware, NovitaAI, Alibaba Cloud, DeepInfra, ByteDance, Fireworks AI, Together AI, RanoAI, CanopyWave, Gonka24, Baidu, Consensus Protocol through LLM Gateway. Requests are automatically routed to the best available provider, with fallback when a provider has issues.
Yes. DeepSeek V4 Flash supports both tool (function) calling and strict JSON output schema (upstream-enforced) through LLM Gateway.
DeepSeek V4 Flash was released on April 24, 2026.
DeepSeek V4.1 Flash
1,000,000 context$0.15 in / $0.60 out per 1M
DeepSeek V4 Flash Vision Exp
1,050,000 context$0.14 in / $0.28 out per 1M
DeepSeek V4 Pro
1,050,000 context$0.43 in / $0.87 out per 1M
DeepSeek V3.2
163,840 context$0.26 in / $0.38 out per 1M
DeepSeek V3.1
163,840 context$0.56 in / $1.68 out per 1M
DeepSeek R1 (0528)
163,840 context$0.50 in / $2.15 out per 1M