--- title: "DeepSeek: DeepSeek V4 Flash 0423 — price, capability and what beats it · Undominated.ai" canonical: https://undominated.ai/models/deepseek__deepseek-v4-flash/ description: "DeepSeek: DeepSeek V4 Flash 0423: $0.090/M in, $0.180/M out. Independent capability scores, and alternatives compared under recorded workload and capability requirements." --- # DeepSeek: DeepSeek V4 Flash 0423 — price, capability and what beats it · Undominated.ai > DeepSeek: DeepSeek V4 Flash 0423: $0.090/M in, $0.180/M out. Independent capability scores, and alternatives compared under recorded workload and capability requirements. [Check base rates for this workload](/check/deepseek__deepseek-v4-flash/) [Cheaper alternatives](/alternatives/deepseek__deepseek-v4-flash/) [Family](/families/deepseek/) [Compare models](https://undominated.ai/compare/?models=deepseek%2Fdeepseek-v4-flash) Comparison context Choose up to three standard models in Compare. Requirements and prompt length apply in Compare. This page keeps its stated price basis and workload controls. MODEL PROOF # DeepSeek V4 Flash 0423 DeepSeek · 24 Apr 2026 Balanced Summarise Chat Code gen Agentic FRONTIER ## Nothing is both better and cheaper under this workload. **$0.113** / 1M tokens Balanced · 3 tokens in per 1 out Serving precision differs between offers. Evidence as of 06 Oct 2026 [openrouter/models](https://openrouter.ai/api/v1/models) [Vendor cross-check](https://api-docs.deepseek.com/quick_start/pricing) [LMArena · cc-by-4.0](https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset) Independent LMArena score 1,432.1 ± 4.03 · 51,850 votes Context window 1.05M Maximum output 943.72K Input modalities text Output modalities text Published input price $0.090 / 1M tokens Published output price $0.180 / 1M tokens Pricing kind fixed Inspect [complete billing conditions](#billing-details) and endpoint terms below. Price from DeepInfra: the cheapest offer that is serving, at standard delivery and at a declared precision that is not 4-bit (fp8), at its standard rate. The maker’s own precision is not known. Cheaper right now: $0.053/M at StreamLake — promotion 70% It does not pass the like-for-like test, so it never sets a rank. Every price dimension · USD per million tokens | Input | $0.090 /M | | --- | --- | | Output | $0.180 /M | | Cached input | $0.018 /M | | Cache write | Unknown /M | | Cache write 1h | Unknown /M | | Reasoning | Unknown /M | ### Who sells it The same weights, different shops. Cheapest is not like-for-like when serving precision differs. Headline cheapest is a lower precision. Like-for-like at the best declared precision is $0.090/M from DeepInfra. 16 provider offers · rates, limits and conditions Rates are USD per million tokens. Endpoint terms can differ even when the quoted price and precision match. A listed parameter is a provider declaration, not a task-success test. | Seller | Input | Output | Precision | Uptime (1d) | | --- | --- | --- | --- | --- | | Seller Relace relace/fp4 Endpoint terms Cached input /M $0.0009 Context limit 1,048,576 tokens Output limit 943,718 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 99.83% | Input $0.0009 | Output $1.28 | Precision fp4 | Uptime (1d) 99.91% | | Seller OpenInference open-inference/fp4 Endpoint terms Cached input /M $0.0010 Context limit 1,048,576 tokens Output limit 943,718 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 99.62% | Input $0.0010 | Output $1.41 | Precision fp4 | Uptime (1d) 99.20% | | Seller StreamLake streamlake/fp8 Endpoint terms Cached input /M $0.0084 Context limit 1,024,000 tokens Output limit 384,000 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount 70% · already included in these rates Uptime · last 30 minutes 99.47% | Input $0.042 | Output $0.084 | Precision fp8 | Uptime (1d) 99.38% | | Seller DeepInfra deepinfra/fp8 Endpoint terms Cached input /M $0.018 Context limit 1,048,576 tokens Output limit 65,536 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 99.48% | Input $0.090 | Output $0.180 | Precision fp8 | Uptime (1d) 99.62% | | Seller GMICloud gmicloud/fp8 Endpoint terms Cached input /M $0.018 Context limit 1,048,575 tokens Output limit 943,717 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount 35% · already included in these rates Uptime · last 30 minutes 99.95% | Input $0.091 | Output $0.182 | Precision fp8 | Uptime (1d) 99.93% | | Seller Venice venice Endpoint terms Cached input /M $0.020 Context limit 1,000,000 tokens Output limit 32,768 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount 30% · already included in these rates Uptime · last 30 minutes 99.10% | Input $0.097 | Output $0.193 | Precision undeclared | Uptime (1d) 95.11% | | Seller DigitalOcean digitalocean Endpoint terms Cached input /M $0.020 Context limit 1,048,576 tokens Output limit 384,000 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 99.84% | Input $0.098 | Output $0.196 | Precision undeclared | Uptime (1d) 99.77% | | Seller SiliconFlow siliconflow/fp8 Endpoint terms Cached input /M $0.028 Context limit 1,048,576 tokens Output limit 393,216 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 99.87% | Input $0.130 | Output $0.280 | Precision fp8 | Uptime (1d) 99.80% | | Seller Alibaba alibaba/fp8 Endpoint terms Cached input /M $0.027 Context limit 1,000,000 tokens Output limit 393,216 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 99.09% | Input $0.134 | Output $0.268 | Precision fp8 | Uptime (1d) 99.28% | | Seller Baidu baidu/fp8 Endpoint terms Cached input /M $0.028 Context limit 1,048,576 tokens Output limit 131,072 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 99.99% | Input $0.140 | Output $0.280 | Precision fp8 | Uptime (1d) 99.06% | | Seller Novita novita/fp8 Endpoint terms Cached input /M $0.028 Context limit 1,048,576 tokens Output limit 393,216 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 99.74% | Input $0.140 | Output $0.280 | Precision fp8 | Uptime (1d) 99.85% | | Seller Parasail parasail/fp8 Endpoint terms Cached input /M $0.070 Context limit 1,048,576 tokens Output limit 943,718 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 99.50% | Input $0.140 | Output $0.280 | Precision fp8 | Uptime (1d) 99.73% | | Seller AtlasCloud atlas-cloud/fp4 Endpoint terms Cached input /M $0.028 Context limit 1,048,576 tokens Output limit 393,216 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 99.49% | Input $0.140 | Output $0.280 | Precision fp4 | Uptime (1d) 99.36% | | Seller Mancer 2 mancer/fp8 Endpoint terms Cached input /M Unknown Context limit 1,048,576 tokens Output limit 943,718 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 98.99% | Input $0.190 | Output $0.500 | Precision fp8 | Uptime (1d) 94.89% | | Seller Azure azure/us Endpoint terms Cached input /M $0.031 Context limit 1,048,576 tokens Output limit 384,000 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 98.58% | Input $0.210 | Output $0.560 | Precision undeclared | Uptime (1d) 95.83% | | Seller Cloudflare cloudflare Endpoint terms Cached input /M $0.014 Context limit 384,000 tokens Output limit 345,600 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 100.00% | Input $0.440 | Output $1.32 | Precision undeclared | Uptime (1d) 98.01% | ### Independent scores | LMArena Elo | 1432.1 default | | --- | --- | LMArena Elo under CC BY 4.0. Absence of another board is not a score of zero. #### Best rankings by task - SVG #40 1155 - Game development #46 1210 - 3D #46 1196 - Code categories #49 1211 - Websites #51 1214 - ASCII art #56 1122 - UI components #66 1171 - Data visualisation #83 1134 Per-task Elo and rank from [Design Arena](https://designarena.ai), via OpenRouter’s model feed. The rank is the feed’s, and it counts models OpenRouter does not list. ### Capability | Context window | 1M | | --- | --- | | Max output | 943K | | Input modes | text | | Tool use | yes | | Reasoning | optional | | Open weights | yes | ### Provenance | Price source | [openrouter.ai](https://openrouter.ai/api/v1/models) | | --- | --- | | Fetched | 2026-10-06 | | Quality data | verified | | Cross-checked | [vendor page](https://api-docs.deepseek.com/quick_start/pricing) | DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and... ## Questions this page answers What does DeepSeek V4 Flash 0423 cost? $0.090/M in, $0.180/M out in this catalogue, as of the fetch date on this page. That is the API row, not a subscription. Does DeepSeek V4 Flash 0423 have an independent quality score? DeepSeek V4 Flash 0423 has an LMArena score in this catalogue. What beats DeepSeek V4 Flash 0423? Nothing is both better and cheaper than DeepSeek V4 Flash 0423. Does this page use Artificial Analysis scores for DeepSeek V4 Flash 0423? No. Artificial Analysis figures are not published here. Quality on this page is LMArena Elo where a score exists; otherwise the row is unrated. Is the cheapest DeepSeek V4 Flash 0423 endpoint the same product? Headline cheapest is a lower precision. Like-for-like at the best declared precision is $0.090/M from DeepInfra. MODEL MONUMENT ## Save or share this proof Download proof card · 1200 × 630 Preview and more sharing options DeepSeek: DeepSeek V4 Flash 0423. Balanced workload. Frontier. Evidence as of 06 Oct 2026. Copy model link Download square card · 1080 × 1080 Copy landscape image Share landscape card ## Related - Side by side [Gemma 4 26B A4B](/compare/deepseek__deepseek-v4-flash--vs--google__gemma-4-26b-a4b-it/) - Nearby on the capability axis [MiniMax M3](/models/minimax__minimax-m3/) - Same vendor [R1 0528](/models/deepseek__deepseek-r1-0528/) - DeepSeek models [DeepSeek](/providers/deepseek/) - Where this model appears [frontier](/frontier/) - Side by side [Nemotron 3 Super](/compare/deepseek__deepseek-v4-flash--vs--nvidia__nemotron-3-super-120b-a12b/) - Nearby on the capability axis [GPT-5.6 Luna](/models/openai__gpt-5.6-luna/) - Same vendor [DeepSeek V3.2](/models/deepseek__deepseek-v3.2/) - Where this model appears [knee](/knee/) - Side by side [gpt-oss-120b](/compare/deepseek__deepseek-v4-flash--vs--openai__gpt-oss-120b/) - Nearby on the capability axis [GLM 4.5](/models/z-ai__glm-4.5/) - Same vendor [DeepSeek V3.2 Exp](/models/deepseek__deepseek-v3.2-exp/) ## Badge The verdict as one SVG, for a README or a docs page. It states this model's dominance status at the balanced workload on the LMArena lens, with the date it was computed, and it is rebuilt with the catalogue — so it changes when the verdict changes, including to one you would rather it did not. Markdown Copy [![DeepSeek V4 Flash 0423 — Undominated.ai dominance verdict](https://undominated.ai/badge/deepseek__deepseek-v4-flash.svg)](https://undominated.ai/models/deepseek__deepseek-v4-flash/) HTML Copy DeepSeek V4 Flash 0423 — Undominated.ai dominance verdict Direct file: [https://undominated.ai/badge/deepseek__deepseek-v4-flash.svg](https://undominated.ai/badge/deepseek__deepseek-v4-flash.svg) — a static SVG, written by scripts/build-badges.mjs on every build, so the copy you embed is never older than the last deploy. ## Continue your investigation - [Explore model families](/families/) - [Compare a shortlist](/compare/) - [Check a model](/check/) - [Understand the evidence](/methodology/)