重要なポイント

• ざっくり言うと、GPT-5.5 は「少ない指示でもタスクをこなす」方向で打ち出されており、Claude Opus 4.7 は「コーディングとAIエージェント向けの1Mコンテキスト」が強く目立つモデルです。[2][13]
• ただし、今回確認できた公開情報だけでは、どちらが全面的に上かを断定するには不十分です。

研究の答え

サポートビジュアル

研究に関する会話

人々も尋ねます

研究を続けてください

情報源

• [1] OpenAI Unveils GPT-5.5 to Field Tasks With Limited Instructionsbloomberg.com

  Chatbot Delusions Back Forward Technology AI # OpenAI Unveils GPT-5.5 to Field Tasks With Limited Instructions Image 1: OpenAI co-founder Greg Brockman said the company’s latest model is “extremely” good at coding, among other things.  OpenAI co-founder Greg Brockman said the company’s latest model is “extremely” good at coding, among other things. Photographer: SeongJoon Cho/Bloomberg Gift this article Add us on Google Contact us: Provide news feedback or report an error Confidential tip? Send a tip to our reporters Site feedback: Take our Survey By Rachel Metz April 23, 2026 at 6:00 PM…

• [2] OpenAI Unveils Its New, More Powerful GPT-5.5 Modelnytimes.com

  OpenAI Unveils Its New, More Powerful GPT-5.5 Model - The New York Times Skip to contentSkip to site indexSearch & Section Navigation Section Navigation Search Technology []( Subscribe for $1/weekLog in[]( Friday, April 24, 2026 Today’s Paper Subscribe for $1/week []( Artificial Intelligence OpenAI’s New A.I. Model Anthropic’s Model A.I. Arms Race Anthropic-White House Talks Job Cuts on Wall Street Advertisement SKIP ADVERTISEMENT Supported by SKIP ADVERTISEMENT # OpenAI Unveils Its New, More Powerful Model The maker of ChatGPT is taking a more open approach to cybersecurity than its chief…

• [3] GPT-5.5 System Card - OpenAIopenai.com

  GPT-5.5 System Card | OpenAI Skip to main content Log inTry ChatGPT(opens in a new window) Research Products Business Developers Company Foundation(opens in a new window) GPT-5.5 System Card | OpenAI April 23, 2026 SafetyPublication # GPT‑5.5 System Card Read the System Card(opens in a new window) Share ## 1. Introduction GPT‑5.5 is a new model designed for complex, real-world work, including writing code, researching online, analyzing information, creating documents and spreadsheets, and moving across tools to get things done. Relative to earlier models, GPT‑5.5 understands the task earlie…

• [4] OpenAI announces GPT-5.5, its latest artificial intelligence modelcnbc.com

  Image 3: Join Pro Livestream Menu Make It select USA INTL Livestream Search quotes, news & videos Livestream Watchlist SIGN IN Create free account OpenAI announces GPT-5.5, its latest artificial intelligence model Livestream CREATE FREE ACCOUNT Markets Business Investing Tech Politics Video Watchlist Investing Club Image 4: Join IC PRO Image 5: Join Pro Livestream Menu Tech # OpenAI announces GPT-5.5, its latest artificial intelligence model Published Thu, Apr 23 2026 2:06 PM EDT Updated 3 Hours Ago Image 6: thumbnail Ashley Capoot@/in/ashley-capoot/ WATCH LIVE Share Share Article via Faceboo…

• [5] OpenAI releases GPT-5.5 amid a shift to rapid-fire AI updates - Fortunefortune.com

  Fortune 500 AIOpenAI # OpenAI releases GPT-5.5 amid a shift to rapid-fire AI updates By Sharon Goldman Sharon Goldman AI Reporter By Sharon Goldman Sharon Goldman AI Reporter April 23, 2026, 2:13 PM ET OpenAI CEO Sam AltmanAnna Moneymaker/Getty Images [...] By Fortune Editors October 20, 2025 Latest in AI --- Big TechIntel Intel CEO Lip Bu Tan crushed Wall Street targets on his 1-year anniversary: We are embracing our ‘paranoid’ roots By Alexei OreskovicApril 23, 2026 17 minutes ago Big TechBillionaires ‘Don’t leave’: Jensen Huang challenges billionaire class as he insists ‘highest taxes in t…

• [6] OpenAI releases GPT-5.5, bringing company one step closer to an AI ‘super app’tech.yahoo.com

  Puzzle hints Science Streaming VPN Wearables Deals Advertise About our ads Licensing Careers Help Feedback Sitemap Follow us on © 2026 Yahoo. All rights reserved. [...] AI Audio Computing Gaming Home entertainment Phones Puzzle hints Science Streaming Tech news VPN Deals More ... ## Trending: TechCrunch TechCrunch # OpenAI releases GPT-5.5, bringing company one step closer to an AI ‘super app’ Greg Brockman, president and co-founder of OpenAI Inc., during the SK AI Summit in Seoul, South Korea. OpenAI on Thursday released GPT-5.5, its newest AI model, which the company calls its “smartest and…

• [7] OpenAI releases GPT-5.5, bringing company one step closer to an AI ‘superapp’ - TechCrunchtechcrunch.com

  San Francisco, CA|October 13-15, 2026 REGISTER NOW Mark Chen, chief research officer at OpenAI, said that GPT-5.5 was better at navigating computer work than its predecessors, and also said that the model “shows meaningful gains on scientific and technical research workflows,” noting that the company feels it could really “help expert scientists make progress.” Chen also said it could assist with drug discovery, an area that has shown increased industry interest over the last few years. GPT 5.5 is widely available starting Thursday, according to OpenAI. The company says that the model is depl…

• [8] OpenAI says its new GPT-5.5 model is more efficient and better at ...theverge.com

  OpenAI says its new GPT-5.5 model is more efficient and better at coding | The Verge Skip to main content The homepage SubscribeSign In Image 4: STK155_OPEN_AI_CVirginia__C Image 5: STK155_OPEN_AI_CVirginia__C Image: The Verge OpenAI just announced its new GPT-5.5 model, which the company calls its “smartest and most intuitive to use model yet, and the next step toward a new way of getting work done on a computer.” OpenAI just released GPT-5.4 last month, but says that the new GPT-5.5 “excels” at tasks like writing and debugging code, doing research online, making spreadsheets and documents…

• [9] Introducing GPT-5.5 - OpenAIopenai.com

  Introducing GPT-5.5 | OpenAI Skip to main content Log inTry ChatGPT(opens in a new window) Research Products Business Developers Company Foundation(opens in a new window) Introducing GPT-5.5 | OpenAI Table of contents Model capabilities Next-generation inference efficiency Advancing cybersecurity for everyone’s safety Availability and pricing Evaluations April 23, 2026 ProductRelease # Introducing GPT‑5.5 A new class of intelligence for real work 00:00 01:28 Listen to article Share We’re releasing GPT‑5.5, our smartest and most intuitive to use model yet, and the next step toward a new way…

• [10] OpenAI launched GPT-5.5 on April 23, 2026, giving ChatGPT and ...threads.com

  OpenAI launched GPT-5.5 on April 23, 2026, giving ChatGPT and Codex users access to a new AI model built for coding, research, data analysis, document production and software operation. GPT-5.5 is rolling out to Plus, Pro, Business and Enterprise users in ChatGPT and Codex. GPT-5.5 Pro is available to Pro, Business and Enterprise users in ChatGPT. and the existing $200 Pro plan, aimed at heavy users and developers. Both Pro tiers differ only by usage limits: $100 Pro gives 5x Plus usage, $200 Pro gives 20x. Pro benefits include advanced GPT‑5.4 Pro reasoning, higher Codex limits, unlimited…

• [11] OpenAI's New GPT-5.5 Powers Codex on NVIDIA Infrastructureblogs.nvidia.com

  And OpenAI and NVIDIA are early silicon and codesign partners: OpenAI provides feedback that informs NVIDIA’s hardware roadmap, and in turn gains early access to new architectures. That relationship produced a concrete milestone — the joint bring-up of the first GB200 NVL72 100,000-GPU cluster. The cluster completed multiple large-scale training runs and set a new benchmark for system-level reliability at frontier scale. GPT-5.5 is the product of that infrastructure running at full strength. Learn more in__OpenAI’s announcement_._ Image 24: Explore the Best of GTC 2026 Sessions ### Explore…

• [12] OpenAI rolls out GPT-5.5 upgrade that's better at getting context9to5google.com

  Go to the 9to5Google home page ChatGPT OpenAI # OpenAI rolls out GPT-5.5 with improved contextual understanding, Plus and up Andrew Romero | Apr 23 2026 - 12:22 pm PT 0 Comments OpenAI just announced that ChatGPT is getting a model upgrade to GPT-5.5. The company says the model will bring better results because of changes to how it understands context. OpenAI released another lengthy press release detailing GPT-5.5. The update comes with a few changes over the previous model. It should perform significantly better across various familiar tasks, such as coding, computer use, and scientific res…

• [13] What's new in Claude Opus 4.7platform.claude.com

  Task budgets (beta) Claude Opus 4.7 introduces task budgets. A task budget gives Claude a rough estimate of how many tokens to target for a full agentic loop, including thinking, tool calls, tool results, and final output. The model sees a running countdown and uses it to prioritize work and finish the task gracefully as the budget is consumed. To use, set the beta header task-budgets-2026-03-13 and add the following to your output config: Python [...] Python ``` response = client.beta.messages.create( model="claude-opus-4-7", max_tokens=128000, output_config={ "effort": "high", "task_b…

• [14] Anthropic Announces Claude Opus 4.7 - Thurrott.comthurrott.com

  Thurrott Thurrott Thurrott Premium Thurrott Youtube Channel Thurrott Newsletters Thurrott Swag Store Thurrott Eternal Spring CDMX # Anthropic Announces Claude Opus 4.7 Anthropic Announces Claude Opus 4.7 Anthropic Announces Claude Opus 4.7 Anthropic’s latest AI model, Claude Opus 4.7, is a “notable” improvement over its predecessor for advanced software engineering, with its biggest gains coming from the most difficult tasks. “Users report being able to hand off their hardest coding work, the kind that previously needed close supervision, to Opus 4.7 with confidence,” the Anthropic announceme…

• [15] Anthropic Launches Claude Opus 4.7 With Major Upgrades - Grand Pinnacle Tribuneevrimagaci.org

  Anthropic Launches Claude Opus 4.7 With Major Upgrades The new AI model promises sharper coding skills, faster performance, and expanded enterprise use as it rolls out to developers and businesses worldwide. ## Key Points On April 16, 2026, Anthropic unveiled its latest artificial intelligence advancement: Claude Opus 4.7. This release marks another milestone in Anthropic’s steady, two-month upgrade cadence, and it’s already generating buzz across the tech industry, especially among developers and enterprise users who rely on state-of-the-art AI tools for complex software engineering tasks.…

• [16] Anthropic releases Claude Opus 4.7, a less risky model than Mythoscnbc.com

  Business News and Finance MarketsBusinessInvestingTechPoliticsSelectMake It AI Age # Anthropic rolls out Claude Opus 4.7, an AI model that is less risky than Mythos Ashley Capoot@/in/ashley-capoot/ WATCH LIVE KEY POINTS Anthropic on Thursday announced a new artificial intelligence model, Claude Opus 4.7. The company said it is an improvement over past models but is "less broadly capable" than its most powerful offering, Claude Mythos Preview. Anthropic rolled out Mythos to a select of companies as part of a new cybersecurity initiative called Project Glasswing earlier this month. Dario Amodei…

• [17] Anthropic rolls out Claude Opus 4.7, an AI model that is less risky than Mythoscnbc.com

  Ashley Capoot@/in/ashley-capoot/ WATCH LIVE Key Points Anthropic on Thursday announced a new artificial intelligence model, Claude Opus 4.7. The company said it is an improvement over past models but is "less broadly capable" than its most powerful offering, Claude Mythos Preview. Anthropic rolled out Mythos to a select of companies as part of a new cybersecurity initiative called Project Glasswing earlier this month. Dario Amodei, chief executive officer of Anthropic, at the AI Impact Summit in New Delhi, India, on Thursday, Feb. 19, 2026. Ruhani Kaur | Bloomberg | Getty Images [...] Watchli…

• [18] Claude Opus 4.7: 7 Biggest Changes + Benchmarksdecodethefuture.org

  The headline claim from Anthropic’s April 16, 2026 announcement is that Opus 4.7 delivers “notable improvement on Opus 4.6 in advanced software engineering” — with some benchmarks showing 3× the task resolution rate of its predecessor. That framing matters because 4.6 was already strong enough to ship inside production agent pipelines. If the 3× figure holds up outside Anthropic’s curated evaluations, we’re looking at one of the largest single-release coding jumps since the Claude 3 → Claude 3.5 Sonnet transition in mid-2024. [...] ## What is Claude Opus 4.7? Claude Opus 4.7 is Anthropic’s fl…

• [19] Anthropic releases Claude Opus 4.7, concedes it trails ... - Axiosaxios.com

  Axios Homepage Axios Media Inc., 2026 Image 9Image 10 Image 11,Opus,Claude%20Opus%204.7,Artificial%20intelligence,Software%20engineering,Gemini%20(chatbot),Advanced%20Micro%20Devices,ChatGPT,GitHub,Claude%20Code&p=https%3A%2F%2Fwww.axios.com%2F2026%2F04%2F16%2Fanthropic-claude-opus-model-mythos&r=&lt=3082&evt=pageLoad&sv=2&cdb=ARoB&rn=845988) [...] Save Privacy Center Powered by Skip to main content sms (opens in new window) facebook (opens in new window) twitter (opens in new window) linkedin (opens in new window) bluesky (opens in new window) Add Axios on Google Add Axios as your preferred…

• [20] Claude Opus 4.7 Is Here: Release Confirmed April 16, 2026 | FindSkill.ai — Learn AI for Your Jobfindskill.ai

  Three pieces of evidence, nothing more: 1. The Information published on April 14 evening that Anthropic is preparing Opus 4.7 + an AI design tool. The piece was sourced from unnamed Anthropic contacts. No public statement from Anthropic confirming or denying. 2. March 2026 npm package leak: over 500,000 lines of Claude Code source code briefly exposed via a misconfigured npm package. The leak included internal references to Opus 4.7 + Sonnet 4.8 in the “Undercover Mode” forbidden-version-strings list (strings Claude is instructed never to mention in output). Also referenced: models codenamed…

• [21] Anthropic releases Claude Opus 4.7: How to try it, benchmarks, safetymashable.com

  Anthropic releases Claude Opus 4.7: How to try it, benchmarks, safety headshot of timothy beck werth, a handsome journalist with great hair The Claude AI logo is displayed on a smartphone screen with a multitude of Anthropic logos in the background Anthropic has been shipping products and making news at a blistering pace in 2026, and on Thursday, the AI company announced the launch of Claude Opus 4.7. Claude Opus 4.7 is Anthropic's most intelligent model available to the general public. Notably, Anthropic said in a press release") that Opus 4.7 is not as powerful as Claude Mythos, which Ant…

• [22] Anthropic releases Claude Opus 4.7: How to try it, benchmarks, safety - Techsea.mashable.com

  Anthropic releases Claude Opus 4.7: How to try it, benchmarks, safety Anthropic has been on a tear lately. Timothy Beck Werth By Timothy Beck Werth Anthropic releases Claude Opus 4.7: How to try it, benchmarks, safety Credit: Samuel Boivin/NurPhoto via Getty Images > Tech Anthropic has been shipping products and making news at a blistering pace in 2026, and on Thursday, the AI company announced the launch of Claude Opus 4.7. Claude Opus 4.7 is Anthropic's most intelligent model available to the general public. Notably, Anthropic said in a press release that Opus 4.7 is not as powerful as Cl…

• [23] Artificial Intelligencefacebook.com

  Anthropic released Claude Opus... - Artificial Intelligence | Facebook Log In Log In Forgot Account? ## Artificial Intelligence's Post []( ### Artificial Intelligence 2d · Inevitable Waves · Paul Fowler · Anthropic released Claude Opus 4.7 on April 17, 2026. The new AI model codes better, handles bigger images, and works longer with less help. People already used it to build games, websites, animations, and CAD designs in minutes. Image 1 0:00 / 0:00 0:00 / 0:00 0:00 / 0:00 0:00 / 0:00 +5 Image 2 Image 3 All reactions: 359 15 comments 139 shares Like Comment Most relevant Keith Clark can yo…

• [24] Claude Opus 4.7 is Out — Weekly AI Newsletter (April 20th 2026) | by Fabio Chiusano | Generative AI | Apr, 2026 | Mediummedium.com

  Claude Opus 4.7 is Out — Weekly AI Newsletter (April 20th 2026) | by Fabio Chiusano | Generative AI | Apr, 2026 | Medium Sitemap Open in app Sign up Sign in ## Also: Anthropic launches Claude Design Image 3: Fabio Chiusano Fabio Chiusano 5 min read · 4 days ago [...] TRACER: Trace-Based Adaptive Cost-Efficient Routing for LLM Classification. TRACER uses lightweight execution traces to route classification requests across model tiers, cutting cost while preserving accuracy. The method adapts routing decisions to observed difficulty patterns rather than static rules, outperforming fixed-thres…

• [25] Anthropic.Claude Opus 4 7 Pricing & Specs | AI Models | CloudPricecloudprice.net

  | Model Key | Provider | Mode | Input Price, $ | Output Price, $ | Context | Max Output | Vision | Functions | --- --- --- --- | claude-opus-4-7 | Anthropic logoAnthropic | Text | 5.00 | 25.00 | 1.0M | 128K | yes | yes | | claude-opus-4-7-20260416 | Anthropic logoAnthropic | Text | 5.00 | 25.00 | 1.0M | 128K | yes | yes | | vertex_ai/claude-opus-4-7 | Anthropic (Vertex AI) logoAnthropic (Vertex AI) | Text | 5.00 | 25.00 | 1.0M | 128K | yes | yes | | vertex_ai/claude-opus-4-7@default | Anthropic (Vertex AI) logoAnthropic (Vertex AI) | Text | 5.00 | 25.00 | 1.0M | 128K | yes | yes | | anthrop…

• [26] Claude Opus 4.7 \ Anthropicanthropic.com

  Skip to main contentSkip to footer []( Research Economic Futures Commitments Learn News Try Claude # Claude Opus 4.7 Image 1: Claude Opus 4.7 Image 2: Claude Opus 4.7 Hybrid reasoning model that pushes the frontier for coding and AI agents, featuring a 1M context window Try ClaudeGet API access ## Announcements NEW Claude Opus 4.7 Apr 16, 2026 Claude Opus 4.7 brings stronger performance across coding, vision, and complex multi-step tasks. It's more thorough and consistent on difficult work, with better results across professional knowledge work. Read more Claude Opus 4.6 [...] Pricing for Opu…

• [27] Claude Opus 4.7 by Anthropic — Pricing, Specs & API Access | Inworldinworld.ai

  Get started Get started Anthropic Anthropic # Claude Opus 4.7 Claude Opus 4.7 is a reasoning model by Anthropic with vision, function calling, prompt caching, structured output — designed for complex, multi-step problem solving where accuracy matters more than speed. It supports a 1M token context window with up to 128K tokens of output. Priced at $5 per million input tokens and $25 per million output tokens. Access Claude Opus 4.7 through Inworld Router with OpenAI SDK compatibility, built-in failover, and intelligent routing across providers. →Function CallingReasoningPrompt CachingResponse…

• [28] Claude Opus 4.7 Price: 2026 API Rates & Subscription - GlobalGPTglbgpt.com

  Claude Opus 4.7 marks a significant shift in Anthropic's model architecture, moving from incremental updates to a fully autonomous agentic framework. While the sticker price for API usage remains at $5/MTok (Input) and $25/MTok (Output), the underlying mechanics of how tokens are counted and how the model "thinks" have been completely overhauled for the 2026 market. benchmark of claude 4.7 ### High-Resolution Vision: The 3.75MP Breakthrough [...] The official API rate for Claude Opus 4.7 is $5.00 per million (MTok) input tokens and $25.00 per million output tokens. While these rates match the…

• [29] Claude Opus 4.7 Pricing In 2026: What It Actually Costs - CloudZerocloudzero.com

  How Much Does Claude Opus 4.7 Cost Per Million Tokens? Here’s the complete Anthropic pricing table for every current-generation model as of April 2026: | | | | | | --- --- | Model | Input (per 1M tokens) | Output (per 1M tokens) | Context window | Max output | | Claude Opus 4.7 | $5.00 | $25.00 | 1M tokens | 128K tokens | | Claude Opus 4.6 | $5.00 | $25.00 | 1M tokens | 128K tokens | | Claude Sonnet 4.6 | $3.00 | $15.00 | 1M tokens | 128K tokens | | Claude Haiku 4.5 | $1.00 | $5.00 | 200K tokens | 64K tokens | [...] | | | | | --- --- | | Model | Input ($ / 1M tokens) | Output ($ / 1M token…

• [30] Claude Opus 4.7: Anthropic’s new flagship, benchmarks, and how it compares to Sonnet & Haiku | explainx.ai Blog | explainx.aiexplainx.ai

  | Feature | Claude Opus 4.7 | Claude Sonnet 4.6 | Claude Haiku 4.5 | --- --- | | Positioning | Most capable GA model for complex reasoning & agentic coding | Best speed + intelligence balance | Fastest; near-frontier intelligence | | Pricing (API) | $5 / input MTok · $25 / output MTok | $3 / input · $15 / output | $1 / input · $5 / output | | Extended thinking | No | Yes | Yes | | Adaptive thinking | Yes | Yes | No | | Priority tier | Yes | Yes | Yes | | Latency (relative) | Moderate | Fast | Fastest | | Context window | 1M tokens | 1M tokens | 200k tokens | | Max output (sync Messages API) |…

• [31] Claude Opus 4.7: Pricing, Benchmarks & Context Windowalmcorp.com

  Claude Opus 4.7 pricing: same list price, different cost conversation The pricing headline is easy to remember: $5 per million input tokens and $25 per million output tokens, the same posted rate as Opus 4.6. That is good news in one narrow sense. Teams do not need to rework every budget model just because Anthropic raised list prices. But treating that as the full pricing story would be a mistake. [...] ### What is Claude Opus 4.7? Claude Opus 4.7 is Anthropic’s latest generally available Opus model. It is positioned as a premium model for advanced coding, long-running agentic tasks, docu…

• [32] Claude Opus 4.7: What Changed, Pricing, and API Name | Remote OpenClawremoteopenclaw.com

  | Field | Claude Opus 4.7 | --- | | Launch date | April 16, 2026 | | API model ID | claude-opus-4-7 | | Input price | $5 / million tokens | | Output price | $25 / million tokens | | Context window | 1M tokens | | Max output | 128k tokens | | Reliable knowledge cutoff | January 2026 | | Training data cutoff | January 2026 | ## What changed from Opus 4.6 The cleanest official summary is simple: Opus 4.7 keeps Opus-level pricing but is supposed to be more useful on the work people actually escalate to Opus. Anthropic's Claude Opus 4.7 launch post says the biggest launch-day gains are in advanc…

• [33] Claude Opus 4.7 Pricing, Context Window, and Features | Simsim.ai

  Back to Anthropic Anthropicmodel # Claude Opus 4.7 Claude Opus 4.7 is a Anthropic model tracked in Sim. It supports a 1M token context window. Pricing starts at $5/1M input tokens and $25/1M output tokens. Key capabilities include Tool choice, Structured outputs, Thinking low, medium, high, xhigh, max.Best for reasoning-heavy tasks that need more deliberate model control. Build with this modelAll Anthropic models Input price$5/1M Cached input$0.5/1M Output price$25/1M Context window1M Max output128k tokens ProviderAnthropic UpdatedApr 16, 2026 Best forBest for reasoning-heavy tasks that need…

• [34] Anthropic: Claude Opus 4.7 – Effective Pricing - OpenRouteropenrouter.ai

  Anthropic: Claude Opus 4.7 ### anthropic/claude-opus-4.7 Released Apr 16, 20261,000,000 context$5/M input tokens$25/M output tokens Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on complex, multi-step tasks and more reliable agentic execution across extended workflows. It is especially effective for asynchronous agent pipelines where tasks unfold over time - large codebases, multi-stage debugging, and end-to-end project orchestration.

• [35] Claude Opus 4.7 and Every Anthropic Model Reviewed - Web Wallahwebwallah.in

  One million tokens means Claude could now process several full-length novels, an entire codebase, or years of company emails in a single conversation. Norway’s $2.2 trillion sovereign wealth fund adopted Opus 4.6 to screen its portfolio for ESG risks. Claude Sonnet 4.6 Another historic moment: 70% of developers in evaluations preferred Sonnet 4.6 over Opus 4.5 – the previous generation’s flagship. Computer use accuracy hit 94% on insurance industry benchmarks. Microsoft integrated it into Microsoft 365 Copilot, bringing Claude to hundreds of millions of enterprise users. ## Claude Opus 4.7 –…

• [36] Pricing | OpenAI APIdevelopers.openai.com

  All models ## Tools | Tool | Details | Pricing | --- | Web search | Web search (all models) | $10.00 / 1k calls + Search content tokens billed at model rates. | | Web search preview (reasoning models, including gpt-5, o-series) | $10.00 / 1k calls + Search content tokens billed at model rates. | | Web search preview (non-reasoning models) | $25.00 / 1k calls + Search content tokens are free. | | Containers | Hosted Shell and Code Interpreter | 1 GB $0.03, 4 GB $0.12, 16 GB $0.48, 64 GB $1.92 per 20-minute session per container | | File search | Storage | $0.10 / GB per day (1 GB free) | |…

• [37] API Pricing - OpenAIopenai.com

  OpenAI API Pricing | OpenAI Skip to main content Log inTry ChatGPT(opens in a new window) Research Products Business Developers Company Foundation(opens in a new window) OpenAI API Pricing | OpenAI # API Pricing Contact sales ## Flagship models Our frontier models are designed to spend more time thinking before producing a response, making them ideal for complex, multi-step problems. Choose your processing mode Standard Batch -50%Data residency +10% ## GPT-5.5 (coming soon) A new class of intelligence for coding and professional work. ### Price Input: $5.00 / 1M tokens Cached input: $0.50 /…

• [38] 🚨 AI News | TestingCatalog (@testingcatalog) on Threadsthreads.com

  BREAKING 🚨: GPT-5 API pricing details are now available! - 400,000 context window - pricing - in $1.25 / out $10 []( []( []( # Thread 10.6K views Image 1: A Threads user's profile picture testingcatalog 08/07/25 BREAKING 🚨: GPT-5 API pricing details are now available! - 400,000 context window - pricing - in $1.25 / out $10 Image 2: No photo description available. 95 5 4 2 Image 3: A Threads user's profile picture testingcatalog 08/07/25 ·Author Image 4: A Threads user's profile picture Link platform.openai.com/docs… Image 5: GPT-5 Model | OpenAI API Image 6 developers.openai.com GPT-5 Mod…

• [39] 2026 OpenAI API Pricing Guide & Savings Tips - UniFuncs 深度搜索unifuncs.com

  I've gathered comprehensive information about OpenAI API pricing in 2026. Let me summarize what I have: Official OpenAI Pricing (as of March-April 2026): From the official OpenAI documentation I've read: 1. GPT-5.4 Standard: $2.50 input / $15.00 output per 1M tokens (short context) 2. GPT-5.4 Mini: $0.75 input / $4.50 output per 1M tokens 3. GPT-5.4 Nano: $0.20 input / $1.25 output per 1M tokens 4. GPT-5.4 Pro: $30.00 input / $180.00 output per 1M tokens 5. GPT-5.4 with long context (1M): $5.00 input / $22.50 output (Standard), $60/$270 (Pro) 6. GPT-5.3-Codex: $1.75/$14.00 7. GPT-4.1: $2.00/$…

• [40] Everything You Need to Know About GPT-5.5techflowpost.com

  However, GPT-5.5’s pricing has also risen significantly. Its API is priced at $5 per million input tokens and $30 per million output tokens—double that of GPT-5.4 ($2.50 input / $15 output per million tokens). Yet OpenAI emphasizes that GPT-5.5 requires far fewer tokens to complete the same tasks, so overall cost may not rise substantially. The GPT-5.5 Pro API is priced at $30 per million input tokens and $180 per million output tokens. Bulk processing and flexible pricing receive a 50% discount; priority processing costs 2.5× the standard rate. Within ChatGPT, GPT-5.5 is rolling out as “GPT-…

• [41] GPT-5.3 and GPT-5.5 in ChatGPT | OpenAI Help Centerhelp.openai.com

  GPT-5.3 and GPT-5.5 in ChatGPT | OpenAI Help Center Image 1: OpenAI Language English United States Login 1. All Collections 2. ChatGPT 3. GPT-5.3 and GPT-5.5 in ChatGPT # GPT-5.3 and GPT-5.5 in ChatGPT Updated: 16 minutes ago As of February 13, 2026, models GPT-4o, GPT-4.1, GPT-4.1 mini, OpenAI o4-mini, and GPT-5 (Instant and Thinking) have been retired from ChatGPT and are no longer available. API access remains unchanged. _ChatGPT Business, Enterprise, and Edu customers will retain access to GPT-4o within Custom GPTs until April 3, 2026. After April 3, GPT-4o will be fully retired acros…

• [42] GPT-5.5 released by...? Trading Odds & Predictions 2026 | Polymarketpolymarket.com

  Final outcome: No OpenAI's official release of GPT-5.5 on April 23, 2026, drives overwhelming trader consensus toward the company as the model originator, with immediate availability in ChatGPT for Plus, Pro, Business, and Enterprise users, plus Codex integration. This large language model excels in agentic tasks like coding (82.7% on Terminal-Bench 2.0), knowledge work (84.9% GDPval), and multi-tool workflows, outperforming Anthropic's Claude Opus 4.7 and Google's Gemini 3.1 Pro on key benchmarks while matching GPT-5.4 speed and efficiency. Following rapid iterations like GPT-5.4 in March, i…

• [43] OpenAI API Pricing (March 2026): GPT-5, GPT-4.1, GPT-4o, o3 Per ...devtk.ai

  Bottom Line OpenAI’s 2026 pricing strategy gives developers more options than ever. GPT-5 at $1.25/$10.00 is competitively priced against Gemini 2.5 Pro and significantly cheaper than Claude Sonnet 4.5. The budget tier — GPT-5 Mini at $0.25/$2.00 and GPT-4.1 Nano at $0.10/$0.40 — makes OpenAI accessible for high-volume production use cases that were previously cost-prohibitive. For most developers, the optimal strategy is: 1. Start with GPT-5 Mini for development and testing 2. Upgrade to GPT-5 only for tasks where Mini’s quality falls short 3. Use GPT-4.1 when you need the 1M context wind…

• [44] OpenAI Pricing in 2026 for Individuals, Orgs & Developers - Finoutfinout.io

  | | | | | --- --- | | Model | Quality | 1024x1024 | 1024x1536 / 1536x1024 | | GPT Image 1 | Low | $0.011 | $0.016 | | | Medium | $0.042 | $0.063 | | | High | $0.167 | $0.25 | | GPT Image 1 Mini | Low | $0.005 | $0.006 | | | Medium | $0.011 | $0.015 | | | High | $0.036 | $0.052 | | DALL·E 3 | Std | $0.04 | $0.08 / $0.12 (HD) | | DALL·E 2 | Std | $0.02 | — | ### Embeddings Embeddings convert text into vector representations for tasks like search, classification, or clustering. Prices vary based on the model's capacity and batch usage. | | | | --- | Model | Standard Cost | Batch Cost | | text-em…

• [45] What ChatGPT 5.5 really means in April 2026webiano.digital

  OpenAI’s general models page adds the economic picture. It lists gpt-5.4, gpt-5.4-mini, and gpt-5.4-nano, with a 1M context window for gpt-5.4, 400K for mini and nano, 128K max output, and tool support that includes functions, web search, file search, and computer use. That lineup says a lot about where OpenAI thinks demand is headed. The future is not a single “best” chatbot. It is a family of models distributed by cost, latency, context, and automation needs. [...] The pricing and capability tables deepen the separation. Developers choose models partly by cost, latency, context wind…

• [46] OpenAI launches GPT-5.5, calling it "a new class of intelligence"thenewstack.io

  For those who need more speed in Codex, where GPT-5.5 will have a 400,000-token context window, OpenAI is also making a Fast mode available. This mode will be 1.5x faster, but also cost 2.5x more. In the API, GPT-5.5 will cost $5 per 1 million input tokens and $30 per 1 million output tokens and will feature a 1 million token context window. That’s twice the price of what OpenAI charged for GPT-5.4. GPT-5.4 also had a tiered pricing structure, where shorter prompts under 272,000 tokens were charged at the standard rate while larger prompts cost $5/$22.5 per million input/output tokens. [...]…