Catalogue
Models
376 models, cross-linked to hardware verdicts and live provider pricing.
51 models
GPT-5.6 Terra2 sizes here
GPT-5.6 TerraOpenAIGPT-5.6 Terra is OpenAI's flagship hosted model that can handle up to 1.05 million tokens in a single request, accepting text, images and files.Jul 2026—1.1M$1.00 / $6.00per 1Mvia OpenRouter—GPT-5.6 Terra ProOpenAIGPT-5.6 Terra Pro is OpenAI's proprietary flagship that can handle up to 1.05 million tokens in a single request, accepting text, images and files.Jul 2026—1.1M$1.00 / $6.00per 1Mvia OpenRouter—
GPT-5.6 Luna2 sizes here
GPT-5.6 Luna ProOpenAIGPT-5.6 Luna Pro is a proprietary multimodal model from OpenAI that handles text, images and files across a one-million-token request limit.Jul 2026—1.1M$0.50 / $3.00per 1Mvia OpenRouter—GPT-5.6 LunaOpenAIGPT-5.6 Luna is OpenAI's flagship text model that can handle over one million tokens in a single request, released in July 2026.Jul 2026—1.1M$0.22 / $1.32per 1Mvia Amazon Bedrock74 tok/sGPT-5.6 Sol2 sizes here
GPT-5.6 SolOpenAIOpenAI's top-tier reasoning and coding model can handle a 1,050,000-token request.Jul 2026—1.1M$5.00 / $30.00per 1Mvia OpenRouter—GPT-5.6 Sol ProOpenAIGPT-5.6 Sol Pro is OpenAI's hosted-only flagship that can handle over one million tokens in a single request, accepting text, images and files.Jul 2026—1.1M$5.00 / $30.00per 1Mvia OpenRouter—GPT-5.52 sizes here
GPT-5.5 ProOpenAIGPT-5.5 Pro is OpenAI's flagship hosted-only model built for enormous single requests — it can take in over one million tokens at once, including text, images and files.Apr 2026—1.1M$30.00 / $180.00per 1Mvia OpenRouter—GPT-5.5OpenAIGPT-5.5 is OpenAI's flagship multimodal model that can handle up to 1.05 million tokens in a single request, making it one of the longest-context frontier offerings available.Apr 2026—1.1M$5.00 / $30.00per 1Mvia OpenRouter—GPT-5.44 sizes here
GPT-5.4 MiniOpenAIGPT-5.4 Mini is a compact hosted model from OpenAI that handles text, images and files with a 400,000-token working memory.Mar 2026—400K$0.75 / $4.50per 1Mvia OpenRouter—GPT-5.4 NanoOpenAIGPT-5.4 Nano is a small hosted model from OpenAI that can handle up to 400,000 tokens in a single request and accepts text, images and files.Mar 2026—400K$0.20 / $1.25per 1Mvia OpenRouter—GPT-5.4OpenAIGPT-5.4 is OpenAI's flagship reasoning model that can handle over one million tokens in a single request, accepting text, images and files.Mar 2026—1.1M$2.50 / $15.00per 1Mvia OpenRouter—GPT-5.4 ProOpenAIGPT-5.4 Pro is OpenAI's premium multimodal model that can handle up to 1.05 million tokens in a single request, accepting text, images and files.Mar 2026—1.1M$30.00 / $180.00per 1Mvia OpenRouter—GPT-5.3 ChatOpenAIGPT-5.3 Chat is OpenAI's flagship reasoning model, available only through hosted APIs with a 128,000-token request limit and broad multimodal input.Mar 2026—128K$1.75 / $14.00per 1Mvia OpenRouter—GPT-5.3-CodexOpenAIGPT-5.3-Codex is a proprietary coding model from OpenAI that can handle up to 400,000 tokens in a single request and accepts text, images and files.Feb 2026—400K$1.75 / $14.00per 1Mvia OpenRouter—GPT-5.2-CodexOpenAIGPT-5.2-Codex is a hosted-only coding specialist from OpenAI that can handle up to 400,000 tokens in a single request.Jan 2026—400K$1.75 / $14.00per 1Mvia OpenRouter—GPT-5.22 sizes here
GPT-5.2 ChatOpenAIGPT-5.2 Chat is OpenAI's flagship hosted model that handles text, images and files in a single request.Dec 2025—128K$1.75 / $14.00per 1Mvia OpenRouter—GPT-5.2 ProOpenAIGPT-5.2 Pro is a proprietary reasoning model from OpenAI that can handle up to 400,000 tokens in a single request and accepts text, images and files together.Dec 2025—400K$21.00 / $168.00per 1Mvia OpenRouter—GPT-5.1-Codex-MaxOpenAIGPT-5.1-Codex-Max is a proprietary coding model from OpenAI that can handle up to 400,000 tokens in a single request and accepts both text and images.Dec 2025—400K$1.25 / $10.00per 1Mvia OpenRouter—GPT-5.1-CodexOpenAIGPT-5.1-Codex is a proprietary coding specialist from OpenAI that can handle up to 400,000 tokens in a single request.Nov 2025—400K$1.25 / $10.00per 1Mvia OpenRouter—GPT-5.1-Codex-MiniOpenAIGPT-5.1-Codex-Mini is a compact coding specialist from OpenAI that can handle up to 400,000 tokens in a single request and accepts both text and images.Nov 2025—400K$0.25 / $2.00per 1Mvia OpenRouter—GPT-5.1OpenAIGPT-5.1 is OpenAI's flagship reasoning model that can handle up to 400,000 tokens in a single request and accepts text, images and files.Nov 2025—400K$0.63 / $5.00per 1Mvia OpenAI31 tok/so3 Deep ResearchOpenAIo3 Deep Research is a hosted-only reasoning model from OpenAI that accepts documents, images and files to produce long-form text analysis.Oct 2025—200K$10.00 / $40.00per 1Mvia OpenRouter—o43 sizes here
o4 Mini Deep ResearchOpenAIo4 Mini Deep Research is OpenAI's hosted-only agent for long-document and multimodal analysis, handling up to 200,000 tokens in a single request alongside images and files.Oct 2025—200K$2.00 / $8.00per 1Mvia OpenRouter—o4 MiniOpenAIo4 Mini is a small reasoning-focused model from OpenAI that handles text, images and files in requests of up to 200,000 tokens.Apr 2025—200K$1.10 / $4.40per 1Mvia OpenRouter—o4 Mini HighOpenAIo4 Mini High is a hosted-only reasoning model from OpenAI that handles text, images and files up to 200,000 tokens in a single request.Apr 2025—200K$1.10 / $4.40per 1Mvia OpenRouter—gpt-oss-safeguard-20bOpenAIgpt-oss-safeguard-20b is a compact downloadable text model from OpenAI with a permissive Apache licence and measured scores across six Arena categories.Sept 202521.5B131K$0.040 / $0.15per 1Mvia Novita AI—GPT-52 sizes here
GPT-5 MiniOpenAIGPT-5 Mini is OpenAI's proprietary small model that can handle up to 400,000 tokens in a single request and accepts text, images and files.Aug 2025—400K$0.25 / $2.00per 1Mvia OpenRouter—GPT-5 NanoOpenAIGPT-5 Nano is a small hosted model from OpenAI that handles text, images and files in a single request of up to 400,000 tokens.Aug 2025—400K$0.050 / $0.40per 1Mvia OpenRouter—gpt-oss-120bOpenAIgpt-oss-120b is OpenAI's first downloadable model, released in 2025 with a permissive Apache licence and a 120.4-billion-parameter dense architecture.Aug 2025120B131K$0.037 / $0.17per 1Mvia OpenRouter—o34 sizes here
o3 ProOpenAIo3 Pro is OpenAI's hosted-only reasoning model built for complex documents and images, with a 200,000-token request limit.Jun 2025—200K$20.00 / $80.00per 1Mvia OpenRouter—o3OpenAIo3 is a hosted-only reasoning model from OpenAI that handles text, images and files up to 200,000 tokens in a single request.Apr 2025—200K$2.00 / $8.00per 1Mvia OpenRouter—o3 Mini HighOpenAIo3 Mini High is a hosted-only reasoning model from OpenAI that handles up to 200,000 tokens in a single request.Feb 2025—200K$1.10 / $4.40per 1Mvia OpenRouter—o3 MiniOpenAIo3 Mini is a compact reasoning model from OpenAI that handles text and file inputs up to 200,000 tokens.Jan 2025—200K$1.10 / $4.40per 1Mvia OpenRouter—GPT-4.13 sizes here
GPT-4.1 MiniOpenAIGPT-4.1 Mini is OpenAI's compact hosted-only model with a one-million-token request limit and measured coding strength.Apr 2025—1M$0.40 / $1.60per 1Mvia OpenRouter—GPT-4.1OpenAIGPT-4.1 is a proprietary multimodal model from OpenAI that can handle up to one million tokens in a single request and accepts text, images and files.Apr 2025—1M$2.00 / $8.00per 1Mvia OpenRouter—GPT-4.1 NanoOpenAIGPT-4.1 Nano is OpenAI's smallest hosted-only model, built for long-context work at entry-level cost.Apr 2025—1M$0.10 / $0.40per 1Mvia OpenRouter—o1-proOpenAIo1-pro is OpenAI's premium reasoning model for extended chain-of-thought work across text, images and files.Mar 2025—200K$150.00 / $600.00per 1Mvia OpenRouter—GPT-4o Search PreviewOpenAIGPT-4o Search Preview is a hosted-only text model from OpenAI that augments its responses with search.Mar 2025—128K$2.50 / $10.00per 1Mvia OpenRouter—GPT-4o-mini Search PreviewOpenAIGPT-4o-mini Search Preview is a lightweight hosted model from OpenAI built for search-augmented tasks.Mar 2025—128K$0.15 / $0.60per 1Mvia OpenRouter—o1OpenAIo1 is a hosted-only reasoning model from OpenAI that accepts text, images and files, and can handle up to 200,000 tokens in a single request.Dec 2024—200K$15.00 / $60.00per 1Mvia OpenRouter—GPT-4o4 sizes here
GPT-4o (2024-11-20)OpenAIGPT-4o is a proprietary multimodal model from OpenAI that handles text, images and files in a single request.Nov 2024—128K$2.50 / $10.00per 1Mvia OpenRouter—GPT-4o (2024-08-06)OpenAIGPT-4o is a multimodal model from OpenAI that accepts text, images and files, released in August 2024 with a 128,000-token request limit.Aug 2024—128K$2.50 / $10.00per 1Mvia OpenRouter—GPT-4oOpenAIGPT-4o is OpenAI's flagship multimodal system from May 2024, handling text, images and files in a single request with a 128,000-token limit.May 2024—128K$2.50 / $10.00per 1Mvia OpenRouter—GPT-4o (2024-05-13)OpenAIGPT-4o is OpenAI's multimodal flagship from May 2024 that accepts text, images and files.May 2024—128K$5.00 / $15.00per 1Mvia OpenRouter—GPT-4o-mini2 sizes here
GPT-4o-miniOpenAIGPT-4o-mini is OpenAI's small multimodal model that handles text, images and files within a 128,000-token request limit.Jul 2024—128K$0.15 / $0.60per 1Mvia OpenRouter—GPT-4o-mini (2024-07-18)OpenAIGPT-4o-mini is OpenAI's low-cost entry point to the GPT-4o family, handling text, images and files with a 128,000-token request limit.Jul 2024—128K$0.15 / $0.60per 1Mvia OpenRouter—GPT-43 sizes here
GPT-4 TurboOpenAIGPT-4 Turbo is OpenAI's flagship-class model from April 2024, handling up to 128,000 tokens in a single request with text and image input.Apr 2024—128K$10.00 / $30.00per 1Mvia OpenRouter—GPT-4 Turbo PreviewOpenAIGPT-4 Turbo Preview is a text-only hosted model from OpenAI released in early 2024 with a 128,000-token request limit.Jan 2024—128K$10.00 / $30.00per 1Mvia OpenRouter—GPT-4OpenAIGPT-4 is OpenAI's hosted-only flagship text model from 2023, still competitive in coding tasks but limited to 8,191 tokens per request and available only through three identically priced providers. Its Arena scores have stayed remarkably stable, though its creative writing lags well behind its coding performance.May 2023—8K$30.00 / $60.00per 1Mvia OpenRouter—GPT-3.51 sizes here
GPT-3.5 Turbo (older v0613)OpenAIGPT-3.5 Turbo is an older text-only model from OpenAI, released in early 2024 and still available through a handful of hosts.Jan 2024—4K$3.00 / $4.00per 1Mvia OpenAI4 tok/s1 / 2