OpenRouter Adds GPT-5.4 Mini and Nano, Optimized for Agent Pipelines

OpenRouter

Mar 19, 2026 · Updated Jun 5, 2026

OpenRouter adds GPT-5.4 mini and nano to its model catalog. Mini brings GPT-5.4-level capabilities at lower latency, while nano targets high-volume, cost-critical pipelines — both with 400K context and image input support.

OpenRouter, a unified API for accessing AI models, has added OpenAI's GPT-5.4 mini and nano to its catalog. GPT-5.4 mini handles text and image inputs with strong reasoning, coding, and tool use — priced at $0.75/M input and $4.50/M output tokens. GPT-5.4 nano is the lightest variant, built for classification, data extraction, ranking, and sub-agent execution at $0.20/M input and $1.25/M output. Both carry a 400,000-token context window.

OpenRouter's early testing found mini's speed gains meaningful for coding agents in tight feedback loops and for chat apps that trigger agent tasks mid-conversation. On benchmarks, mini scores 54.4% on SWE-Bench Pro, 72.1% on OSWorld-Verified, and 88.0% on GPQA Diamond.

Switch your OpenRouter model string to openai/gpt-5.4-mini for agent workflows or openai/gpt-5.4-nano for background classification and sub-agent tasks where cost and latency are the primary constraint.

View the full update on openrouter.ai

OpenRouter

@OpenRouterMar 17

The new @OpenAI GPT-5.4 mini and nano are available now on OpenRouter! In our early testing, mini’s increase in speed was useful for staying in the loop for coding agents, and results in better UX for chat apps that allow the models to perform agent tasks mid conversation. https://t.co/E13omKL6RD

View on X

Every HeadsUpAI update is written based on its original source and reviewed before it's published. Read our editorial standards →

See all AI news & updates from OpenRouter →

Keep reading

OpenAI Launches GPT-5.4 Mini and Nano for Fast, Low-Cost Agentic Workflows

OpenAI released GPT-5.4 mini and nano, its most capable small models yet. Mini runs more than 2x faster than GPT-5 mini with strong coding, tool use, and computer-use scores. Nano is the smallest, cheapest option, built for high-volume simple tasks.

OpenRouter launches GPT-5.4 Image 2 to unify frontier reasoning and visual generation

OpenRouterApr 24

OpenRouter launches GPT-5.4 Image 2 to unify frontier reasoning and visual generation

OpenRouter added OpenAI's gpt-5.4-image-2 to its unified API, combining the latest reasoning model with high-fidelity image generation. This update allows developers to build workflows where the model refines its own visual prompts to produce more accurate, instruction-aligned assets.

Notion Adds GPT-5.4 Mini to Custom Agent Model Picker

NotionMar 19

Notion Adds GPT-5.4 Mini to Custom Agent Model Picker

Notion added GPT-5.4 Mini to its Custom Agent model picker, offering a faster, lower-cost option for agent tasks. For straightforward jobs — routing, classification, or simple data retrieval — it delivers results at lower cost than the flagship GPT-5.4.