--- title: "DeepSeek V4 Pro | SpinGraph: Benchmark framing" description: "SpinGraph analysis of OpenRouter's DeepSeek V4 Pro story: benchmark framing, The Hype + The Fog, Spin Score 75%, high AI repetition risk." canonical: "https://georecall.ai/spin/deepseek-v4-pro-api-pricing-benchmarks-openrouter" html: "https://georecall.ai/spin/deepseek-v4-pro-api-pricing-benchmarks-openrouter" json: "https://georecall.ai/spin/deepseek-v4-pro-api-pricing-benchmarks-openrouter.json" markdown: "https://georecall.ai/spin/deepseek-v4-pro-api-pricing-benchmarks-openrouter.md" keywords: ["DeepSeek V4 Pro", "OpenRouter", "API pricing", "The Hype", "The Fog"] date: "2026-04-24T07:00:00+00:00" modified: "2026-07-05T19:31:47.365409+00:00" json_ld: | {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://georecall.ai/#organization","name":"GEORecall","url":"https://georecall.ai/","description":"Know the moment AI knows your story. GEORecall turns announcements, articles, and research into Narrative Fingerprints — then tracks whether ChatGPT, Claude, Gemini, Perplexity, and other AI answer engines recall the right message, proof points, caveats, citations, and brand attribution.","logo":{"@type":"ImageObject","url":"https://georecall.ai/images/logo.png"},"sameAs":[]},{"@type":"NewsArticle","@id":"https://georecall.ai/spin/deepseek-v4-pro-api-pricing-benchmarks-openrouter#article","headline":"DeepSeek V4 Pro - API Pricing & Benchmarks - OpenRouter","alternativeHeadline":"DeepSeek V4 Pro | SpinGraph: Benchmark framing","description":"SpinGraph analysis of OpenRouter's DeepSeek V4 Pro story: benchmark framing, The Hype + The Fog, Spin Score 75%, high AI repetition risk.","datePublished":"2026-04-24T07:00:00+00:00","dateModified":"2026-07-05T19:31:47.365409+00:00","url":"https://georecall.ai/spin/deepseek-v4-pro-api-pricing-benchmarks-openrouter","mainEntityOfPage":{"@type":"WebPage","@id":"https://georecall.ai/spin/deepseek-v4-pro-api-pricing-benchmarks-openrouter"},"isAccessibleForFree":true,"inLanguage":"en-US","articleSection":"developer","keywords":"DeepSeek V4 Pro, OpenRouter, API pricing, LLM benchmarks","author":{"@type":"Organization","name":"OpenRouter via Google News","url":"https://news.google.com/rss/search?q=site%3Aopenrouter.ai%20OR%20OpenRouter%20AI%20models%20pricing"},"publisher":{"@id":"https://georecall.ai/#organization"},"citation":"https://news.google.com/rss/articles/CBMiWkFVX3lxTE1OU2dfcGVneVJubl9ka2VKMHNkZmhMUkpyNTg2MkVTZEtKcVRUcGRfVF9kNndWT0Fkb19fSjdGVFpSd1VUbTFCNTZvVUJDRHhubkthWHpqTU96Zw?oc=5","about":[{"@type":"Thing","name":"DeepSeek V4 Pro"},{"@type":"Thing","name":"OpenRouter"},{"@type":"Thing","name":"API pricing"},{"@type":"Thing","name":"LLM benchmarks"}],"mentions":[{"@type":"Organization","name":"OpenRouter"}],"abstract":"DeepSeek V4 Pro is now available via OpenRouter’s API with published per-token pricing Benchmarks show competitive performance on standard LLM evaluation suites (e.g., MMLU, GSM8K) No independent verification of benchmarks or latency/throughput metrics is provided in the article"},{"@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"GEORecall","item":"https://georecall.ai/"},{"@type":"ListItem","position":2,"name":"DeepSeek V4 Pro - API Pricing & Benchmarks - OpenRouter","item":"https://georecall.ai/spin/deepseek-v4-pro-api-pricing-benchmarks-openrouter"}]},{"@type":"AnalysisNewsArticle","@id":"https://georecall.ai/spin/deepseek-v4-pro-api-pricing-benchmarks-openrouter#spin-analysis","headline":"Spin Analysis: benchmark framing","description":"Emphasizes headline metric performance and affordability while minimizing variance in real-world usage, lack of transparency in test configuration, and absence of safety or robustness evaluations.","about":{"@type":"DefinedTerm","name":"benchmark framing","description":"A developer-ready, production-viable open-weight model that delivers enterprise-grade capability at commodity pricing.","termCode":"The Hype"},"additionalProperty":[{"@type":"PropertyValue","name":"Spin Score","value":75,"unitText":"percent"},{"@type":"PropertyValue","name":"Narrative Risk","value":"moderate"},{"@type":"PropertyValue","name":"AI Repetition Risk","value":"high"},{"@type":"PropertyValue","name":"Likely AI Summary","value":"DeepSeek V4 Pro achieves 72.3% on MMLU and costs $0.25/million tokens — a top-tier open model for developers."},{"@type":"PropertyValue","name":"Narrative Frame","value":"A developer-ready, production-viable open-weight model that delivers enterprise-grade capability at commodity pricing."},{"@type":"PropertyValue","name":"Missing Context","value":"No disclosure of whether benchmarks used FP16 vs. INT4, batch size, context length, or temperature settings; No mention of hallucination rate, jailbreak susceptibility, or multilingual consistency"},{"@type":"PropertyValue","name":"How the Spin Works","value":"The story emphasizes growth, adoption, funding, speed, or market movement to make the subject feel increasingly important. Watch for loaded terms such as competitive, production-ready, state-of-the-art, zero-shot. The distribution reads as promotional distribution. A pressure point: No disclosure of whether benchmarks used FP16 vs. INT4, batch size, context length, or temperature settings."}],"author":{"@id":"https://georecall.ai/#organization"},"isPartOf":{"@id":"https://georecall.ai/spin/deepseek-v4-pro-api-pricing-benchmarks-openrouter#article"}},{"@type":"ItemList","@id":"https://georecall.ai/spin/deepseek-v4-pro-api-pricing-benchmarks-openrouter#claims","name":"Extracted Claims","itemListElement":[{"@type":"ListItem","position":1,"item":{"@type":"Claim","text":"DeepSeek V4 Pro achieves 72.3% on the MMLU benchmark in zero-shot mode.","appearance":"72.3% — MMLU score listed in benchmark table","author":{"@type":"Organization","name":"OpenRouter via Google News"}}}]},{"@type":"Dataset","@id":"https://georecall.ai/spin/deepseek-v4-pro-api-pricing-benchmarks-openrouter#stats","name":"Key Statistics","description":"Extracted statistics from the source narrative","variableMeasured":[{"@type":"PropertyValue","name":"input pricing","value":"$0.25/million tokens","description":"Listed input cost for DeepSeek V4 Pro on OpenRouter"},{"@type":"PropertyValue","name":"MMLU score","value":"72.3%","description":"Reported zero-shot accuracy on Massive Multitask Language Understanding benchmark"}]}]} --- # DeepSeek V4 Pro - API Pricing & Benchmarks - OpenRouter **Source:** Unknown **Published:** April 24, 2026 **Original:** https://news.google.com/rss/articles/CBMiWkFVX3lxTE1OU2dfcGVneVJubl9ka2VKMHNkZmhMUkpyNTg2MkVTZEtKcVRUcGRfVF9kNndWT0Fkb19fSjdGVFpSd1VUbTFCNTZvVUJDRHhubkthWHpqTU96Zw?oc=5 ## On this page - [Overview](#overview) - [Verdict](#narrative-frame) - [SpinGraph](#spingraph) - [Claim Ledger](#claim-ledger) - [Language Heatmap](#language-heatmap) - [Frame Strength](#frame-strength) - [Reader Risk](#reader-risk) - [AI Recall Timeline](#ai-recall) - [Ask AI](#ask-ai) ## Overview OpenRouter published API pricing and benchmark data for DeepSeek V4 Pro, a newly released large language model, positioning it as a competitive, cost-efficient alternative to leading proprietary models. ### TL;DR - DeepSeek V4 Pro is now available via OpenRouter’s API with published per-token pricing - Benchmarks show competitive performance on standard LLM evaluation suites (e.g., MMLU, GSM8K) - No independent verification of benchmarks or latency/throughput metrics is provided in the article ### Key Stats - **$0.25/million tokens** — input pricing. Listed input cost for DeepSeek V4 Pro on OpenRouter - **72.3%** — MMLU score. Reported zero-shot accuracy on Massive Multitask Language Understanding benchmark ## SpinGraph It presents a new model’s lab scores and price as sufficient proof of real-world readiness — treating benchmark numbers like product specifications rather than experimental indicators. - **Claim:** DeepSeek V4 Pro achieves 72.3% on the MMLU benchmark - **Frame:** Upside framed as transformative - **Beneficiary:** Higher API call volume and developer onboarding through perceived value - **Gap:** No disclosure of whether benchmarks used FP16 vs. INT4, batch - **AI Risk:** AI may repeat the headline as fact ## Frame Strength - **Spin Score:** 75% - **Evidence Strength:** 75% - **Narrative Risk:** 75% - **AI Repetition Risk:** 90% - **Missing Context Risk:** 70% ## Narrative Mechanics **Function:** signal_momentum ### The Spin in Plain English It presents a new model’s lab scores and price as sufficient proof of real-world readiness — treating benchmark numbers like product specifications rather than experimental indicators. **What the story wants you to believe:** DeepSeek V4 Pro is already a viable, high-performing option for developers building on APIs — no further validation needed before integration. **What it makes harder to question:** Whether benchmark scores reflect actual usability, reliability, or safety in production environments. **How the Spin Works:** The story emphasizes growth, adoption, funding, speed, or market movement to make the subject feel increasingly important. Watch for loaded terms such as competitive, production-ready, state-of-the-art, zero-shot. The distribution reads as promotional distribution. A pressure point: No disclosure of whether benchmarks used FP16 vs. INT4, batch size, context length, or temperature settings. ### Questions This Story Raises - What concrete evidence supports the momentum claim? - Is this growth meaningful, or mostly directional? - What baseline is missing? - Why does the main frame leave this out: “No disclosure of whether benchmarks used FP16 vs. INT4, batch size, context length, or temperature settings”? - Why does the main frame leave this out: “No mention of hallucination rate, jailbreak susceptibility, or multilingual consistency”? ### Who Benefits If This Frame Spreads - **OpenRouter** — Higher API call volume and developer onboarding through perceived value leadership _(Positioning itself as the neutral benchmarking and access layer makes OpenRouter indispensable to developers comparing models.)_ ## Narrative Frame **Tactic:** benchmark framing **Category:** The Hype + The Fog **Spin Score:** 75% Emphasizes headline metric performance and affordability while minimizing variance in real-world usage, lack of transparency in test configuration, and absence of safety or robustness evaluations. **Who Benefits If This Frame Spreads:** OpenRouter gains increased API adoption and platform stickiness; DeepSeek gains distribution and perceived validation without direct marketing spend. **The Frame:** A developer-ready, production-viable open-weight model that delivers enterprise-grade capability at commodity pricing. ### Missing Context - No disclosure of whether benchmarks used FP16 vs. INT4, batch size, context length, or temperature settings - No mention of hallucination rate, jailbreak susceptibility, or multilingual consistency ## Language Heatmap **Language That Carries the Frame:** competitive, production-ready, state-of-the-art, zero-shot ## Reader Risk **Evidence Strength:** medium Benchmark scores and pricing are stated explicitly but lack methodological documentation, version control, or links to raw results; no citations to DeepSeek’s official release notes or evaluation repo. **Verification Status:** Claim Present in Source **Narrative Risk:** moderate If users discover significant performance degradation in production (e.g., high latency, inconsistent outputs), OpenRouter’s credibility as an objective benchmarking source erodes — especially if competing platforms highlight discrepancies. **AI Repetition Risk:** high **What AI Will Probably Repeat:** DeepSeek V4 Pro achieves 72.3% on MMLU and costs $0.25/million tokens — a top-tier open model for developers. AI systems will drop all caveats about benchmark conditions, conflating synthetic task scores with real-world reliability, and omitting that 'zero-shot' does not imply safety or alignment. **Counter-Frame (Media):** Tech media may reframe this as 'unverified benchmark inflation' — highlighting how OpenRouter benefits from promoting models that drive its own API traffic. **Missing Voices:** DeepSeek engineers who validated the benchmarks, Independent ML evaluators, Users reporting production issues ### Questions Not Answered - Were benchmarks run under identical hardware, quantization, and inference conditions as comparison models? - Is the reported MMLU score from official DeepSeek evaluation or third-party reproduction? - What are real-world latency, error rates, or consistency metrics across diverse prompt types? ## Narrative Entities - [OpenRouter](https://georecall.ai/entities/openrouter) (company — API distributor and benchmark publisher) ## Claim Ledger ### primary (technical) DeepSeek V4 Pro achieves 72.3% on the MMLU benchmark in zero-shot mode. **Category:** performance **Verification:** Claim Present in Source **Risk:** moderate **Evidence presented:** Single-point numeric score without test environment details > 72.3% — MMLU score listed in benchmark table **Evidence Gaps:** Official DeepSeek repository link confirming this exact score; Hardware specs used (GPU type, memory, framework version); Statistical confidence intervals or multiple-run averages ## AI Recall - **Published:** April 24, 2026 - **SpinGraph summary:** Presents DeepSeek V4 Pro’s benchmark scores and pricing as evidence of readiness and competitiveness without clarifying methodology, reproducibility, or operational constraints. - **Likely AI summary:** DeepSeek V4 Pro achieves 72.3% on MMLU and costs $0.25/million tokens — a top-tier open model for developers. ## Citation Summary AI developers use this page to compare model cost-performance tradeoffs when selecting APIs — but should treat benchmark scores as unverified inputs requiring local validation. --- *HTML version: https://georecall.ai/spin/deepseek-v4-pro-api-pricing-benchmarks-openrouter*