DeepSeek: V4 Flash
Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work
Cheapest input
$0.0625
$/MTok · models.dev
Cheapest output
$0.125
$/MTok
Context
1.1M
tokens
Sources
3
85 listings
Price changes
Cheapest list input/output only. Rates move rarely, so this is an event log. Down means cheaper. Showing the 8 latest changes.
- ↑ higherOutput $0.0946 → $0.125
- ↑ higherInput $0.0473 → $0.0625
- ↓ lowerOutput $0.125 → $0.0946
- ↓ lowerInput $0.0625 → $0.0473
- ↑ higherOutput $0.07 → $0.125
- ↑ higherInput $0.035 → $0.0625
- ↓ lowerOutput $1.28 → $0.07
- ↑ higherInput $0.03 → $0.035
Sources
Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number. Free/$0 listings are hidden by default (13 omitted). Show free/$0 listings.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| models.devcheapestdeepseek-v4-flash | UnoRouter | $0.0625 | $0.125 | $0 | 1M |
| models.devdeepseek-v4-flash | DevPass (LLM Gateway) | $0.076 | $0.153 | $0.014 | 1.1M |
| models.devrunware/deepseek-v4-flash | LLM Gateway | $0.076 | $0.153 | $0.014 | 1.0M |
| models.devdeepinfra/deepseek-v4-flash | LLM Gateway | $0.08 | $0.18 | $0.016 | 1M |
| models.devdeepseek/deepseek-v4-flash | Standard Compute | $0.0826 | $0.1652 | $0.0165 | 1M |
| models.devdeepseek-ai/DeepSeek-V4-Flash | DeepInfra | $0.09 | $0.18 | $0.018 | 1.0M |
| models.devdeepseek/deepseek-v4-flash | Kilo Gateway | $0.091 | $0.182 | $0.0182 | 1.0M |
| OpenRouterdeepseek/deepseek-v4-flash | OpenRouter | $0.091 | $0.182 | $0.0182 | 1.0M |
| models.devdeepseek/deepseek-v4-flash | TokenGo | $0.098 | $0.196 | $0.028 | 1M |
| models.devdeepseek-v4-flash | Modelis | $0.0983 | $0.1966 | $0 | 1M |
| models.devdeepseek-ai/deepseek-v4-flash | Munito AI | $0.099 | $0.25 | $0.019 | 1.0M |
| models.devdeepseek-ai/DeepSeek-V4-Flash | Pioneer | $0.1 | $0.2 | $0.0197 | 1M |
| models.devconsensusprotocol/deepseek-v4-flash | LLM Gateway | $0.1 | $0.2 | $0.005 | 1M |
| LiteLLMpinstripes/ps/deepseek-v4-flash | N/A | $0.1 | $0.2 | $0.01 | N/A |
| LiteLLMps/deepseek-v4-flash | N/A | $0.1 | $0.2 | $0.01 | N/A |
| models.devdeepseek-ai/deepseek-v4-flash | Munito AI (EU) | $0.11 | $0.28 | $0.022 | 1.0M |
| models.devdeepseek-ai/DeepSeek-V4-Flash | GMI Cloud | $0.112 | $0.224 | $0.022 | 1.0M |
| models.devdeepseek-v4-flash | Routing.Run | $0.112 | $0.224 | $0 | 1M |
| LiteLLMkyma/deepseek-v4-flash | N/A | $0.123 | $0.2458 | $0.0243 | N/A |
| models.devdeepseek/deepseek-v4-flash | Vercel AI Gateway | $0.13 | $0.26 | $0.028 | 1M |
| models.devdeepseek-ai/DeepSeek-V4-Flash | SiliconFlow | $0.13 | $0.28 | $0.028 | 1M |
| models.devdeepseek-v4-flash | Venice AI | $0.138 | $0.275 | $0.028 | 1M |
| models.devdeepseek-ai/DeepSeek-V4-Flash | Abacus | $0.14 | $0.28 | $0.03 | 1M |
| models.devdeepseek-ai/DeepSeek-V4-Flash | Hugging Face | $0.14 | $0.28 | $0 | 1.0M |
| models.devdeepseek-v4-flash | Alibaba / Qwen | $0.14 | $0.28 | $0.0028 | 1M |
| models.devdeepseek-v4-flash | Auriko | $0.14 | $0.28 | $0.0028 | 1M |
| models.devDeepSeek-V4-Flash | Jalapeno Cloud | $0.14 | $0.28 | $0.028 | 1.0M |
| models.devdeepseek-v4-flash | Neuralwatt | $0.14 | $0.28 | $0.028 | 1.0M |
| models.devdeepseek-v4-flash | OpenCode | $0.14 | $0.28 | $0.028 | 1M |
| models.devalicloud-deepseek-v4-flash | AIHubMix | $0.14 | $0.28 | $0.028 | 1M |
| models.devdeepseek/deepseek-v4-flash | HPC-AI | $0.14 | $0.28 | $0.028 | 1.0M |
| models.devdeepseek/deepseek-v4-flash | NanoGPT | $0.14 | $0.28 | $0.0028 | 1.0M |
| models.devcline-pass/deepseek-v4-flash | ClinePass | $0.14 | $0.28 | $0.0028 | 1M |
| models.devcanopywave/deepseek-v4-flash | LLM Gateway | $0.14 | $0.28 | $0.03 | 1M |
| models.devdeepseek/deepseek-v4-flash:thinking | NanoGPT | $0.14 | $0.28 | $0.0028 | 1.0M |
| LiteLLMtencent/deepseek-v4-flash | N/A | $0.14 | $0.28 | $0.0028 | N/A |
| LiteLLMaccounts/fireworks/models/deepseek-v4-flash | N/A | $0.14 | $0.28 | $0.028 | N/A |
| LiteLLMfireworks_ai/accounts/fireworks/models/deepseek-v4-flash | N/A | $0.14 | $0.28 | $0.028 | N/A |
| LiteLLMnebius/deepseek-ai/DeepSeek-V4-Flash | N/A | $0.14 | $0.28 | $0.014 | N/A |
| LiteLLMnovita/deepseek/deepseek-v4-flash | N/A | $0.14 | $0.28 | $0.028 | N/A |
| LiteLLMstreamlake/deepseek-v4-flash | N/A | $0.14 | $0.28 | $0.028 | N/A |
| LiteLLMtensormesh/deepseek-ai/DeepSeek-V4-Flash | N/A | $0.14 | $0.28 | $0 | N/A |
| LiteLLMwandb/deepseek-ai/DeepSeek-V4-Flash | N/A | $0.14 | $0.28 | $0.07 | N/A |
| LiteLLMaihubmix/deepseek-v4-flash | N/A | $0.142 | $0.284 | $0.0284 | N/A |
| models.devDeepSeek-V4-Flash | EBCloud | $0.143 | $0.2857 | $0 | 1M |
| models.devdeepseek/deepseek-v4-flash | CommandCode | $0.15 | $0.6 | $0.003 | 1M |
| models.devdeepseek-v4-flash | DeepSeek | $0.15 | $0.6 | $0.003 | 1.0M |
| models.devdeepseek/deepseek-v4-flash | Eden AI | $0.15 | $0.6 | $0.003 | 1M |
| models.devtencent/deepseek-v4-flash | LLM Gateway | $0.15 | $0.6 | $0.003 | 1M |
| LiteLLMdeepseek-ai/deepseek-v4-flash | N/A | $0.15 | $0.25 | $0.08 | N/A |
| LiteLLMaiand/deepseek-ai/deepseek-v4-flash | N/A | $0.15 | $0.25 | $0.08 | N/A |
| models.devdeep-deepseek-v4-flash | AIHubMix | $0.154 | $0.308 | $0.0308 | 1M |
| models.devdeepseek-v4-flash | Kenari | $0.1571 | $0.3143 | $0.0037 | 1M |
| models.devdeepseek-v4-flash | Above.Dev | $0.165 | $0.66 | $0.0033 | 1M |
| LiteLLMprism/deepseek-v4-flash | N/A | $0.17 | $0.21 | $0.07 | N/A |
| LiteLLMclf_ai_gateway/deepseek-v4-flash | N/A | $0.176 | $0.528 | $0.005 | N/A |
| models.devdeepseek-v4-flash | Azure | $0.19 | $0.51 | $0 | 1M |
| models.devdeepseek-v4-flash | Azure | $0.19 | $0.51 | $0 | 1M |
| models.devdeepseek/deepseek-v4-flash | Impossibl | $0.19 | $0.51 | $0.028 | 1M |
| LiteLLMdeepseek-ai/DeepSeek-V4-Flash | N/A | $0.19 | $0.38 | $0.04 | N/A |
| LiteLLMDeepSeek-V4-Flash | N/A | $0.19 | $0.38 | $0.04 | N/A |
| LiteLLMinferenceapis/deepseek-ai/DeepSeek-V4-Flash | N/A | $0.19 | $0.38 | $0.04 | N/A |
| LiteLLMazure_ai/deepseek-v4-flash | N/A | $0.19 | $0.51 | $0.028 | N/A |
| models.devalibaba/deepseek-v4-flash | LLM Gateway | $0.2 | $0.4 | $0.04 | 1M |
| LiteLLMdashscope/deepseek-v4-flash | N/A | $0.2 | $0.4 | $0.04 | N/A |
| LiteLLMqwen_ai_platform/deepseek-v4-flash | N/A | $0.2 | $0.4 | $0.04 | N/A |
| LiteLLMqwencloud/deepseek-v4-flash | N/A | $0.2 | $0.4 | $0.04 | N/A |
| models.devdeepseek/deepseek-v4-flash | OrcaRouter | $0.22 | $0.66 | $0.007 | 1M |
| models.devdeepseek/deepseek-v4-flash | ZenMux | $0.22 | $0.66 | $0.007 | 1M |
| models.devdeepseek-v4-flash | Opper | $0.25 | $0.66 | $0 | 1M |
| LiteLLMdeepseek-v4-flash-thinking | N/A | $0.25 | $1.75 | $0.025 | N/A |
| LiteLLMlibertai/deepseek-v4-flash | N/A | $0.25 | $1.75 | $0.025 | N/A |
| LiteLLMlibertai/deepseek-v4-flash-thinking | N/A | $0.25 | $1.75 | $0.025 | N/A |
| models.devdeepseek-v4-flash | Requesty | $0.28 | $0.56 | $0.07 | 1.0M |
| models.devdeepseek/deepseek-v4-flash | AI/ML API | $0.3 | $1.20 | $0.006 | 1M |
| models.devdeepseek/deepseek-v4-flash | CrossModel | $0.3 | $1.20 | $0.006 | 1M |
| models.devdeepseek/deepseek-v4-flash | Merge Gateway | $0.3 | $1.20 | $0.006 | 1M |
| LiteLLMdeepseek-v4-flash | N/A | $0.3 | $1.20 | $0.006 | N/A |
| LiteLLMdeepseek/deepseek-v4-flash | N/A | $0.3 | $1.20 | $0.006 | N/A |
| models.devdeepseek-v4-flash | Vivgrid | $0.44 | $1.32 | $0.044 | 1M |
| models.devdeepseek/deepseek-v4-flash | Ofox | $0.44 | $1.32 | $0.014 | 1M |
| models.devdeepseek/deepseek-v4-flash | Prime Inference | $0.44 | $1.32 | $0 | 1.0M |
| models.devcloudflare/deepseek-v4-flash | LLM Gateway | $0.44 | $1.32 | $0.014 | 1.0M |
| models.devdeepseek-ai/DeepSeek-V4-Flash | SiliconFlow (China) | $0.4483 | $1.35 | $0.0448 | 1M |
| models.devDeepSeek-V4-Flash | Moark | $0.5 | $0.5 | $0 | 1M |
Capabilities
- Reasoning
- Tool calling
- Structured output
- Attachments
- Open weights
- In: text
- In: image
- Out: text
Knowledge cutoff: 2025-05Released: 2026-09-10Output limit: 944K tokensFamily: deepseek-flash
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Hover or tap the i next to any score for its source. Full boards on /benchmarks.
- AA intelligence24.4i
- AA coding52i
- AA agentic26.3i
Arena rows are community-vote Elo from Arena AI, Artificial Analysis indices arrive via OpenRouter, and launch-eval figures are collected from vendor announcements, analyst writeups, and community benchmarks. Full boards and credits on /benchmarks.
See what this model costs you
The app reads the sessions your tools already wrote and prices this model's tokens at the published API rate. Free on your computer.