OpenAI Batch API Now Supports GPT Image Models at Half Cost

OpenAI

Feb 21, 2026 · Updated Apr 25, 2026

OpenAI's Batch API now supports GPT Image models for async image generation and editing at 50% lower cost with dedicated rate limits. Large-scale pipelines can queue up to 50,000 jobs overnight without throttling real-time API traffic.

OpenAI's Batch API now accepts image generation and editing requests, supporting gpt-image-1.5, chatgpt-image-latest, gpt-image-1, and gpt-image-1-mini. You submit up to 50,000 jobs in a JSONL file, and results come back within 24 hours through a separate rate limit pool - no competing with your sync traffic.

Until now, generating images at scale meant hitting rate limits or paying full price per call. Batch processing at half the cost changes the economics for teams building visual pipelines - product catalogs, dataset augmentation, automated marketing. The dedicated rate pool is equally important: bulk work no longer degrades your production API.

Switch your bulk image pipelines to the Batch API via the /v1/images/generations or /v1/images/edits endpoints - the same models and parameters work as in sync mode.

View the full update on developers.openai.com

OpenAI Developers

@OpenAIDevsFeb 21

🎨 Generating or editing images at scale? Batch API now supports GPT Image models: gpt-image-1.5, chatgpt-image-latest, gpt-image-1, gpt-image-1-mini. Submit up to 50,000 generations or edits as async jobs at 50% lower cost with separate rate limits. https://t.co/9W6TCeBGw3 https://t.co/KMcBIf8UxR

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 OpenAI →

Keep reading

OpenAI Expands Video API with Five New Sora 2 Capabilities

OpenAI's Video API now supports custom characters and objects, 16:9 and 9:16 exports, clips up to 20 seconds, video continuation, and batch jobs. Powered by Sora 2, all five capabilities are available to all developers now.

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.

GoogleApr 1

Google releases Veo 3.1 Lite for high volume video at half cost

Google launched Veo 3.1 Lite, a new video generation model available through the Gemini API and Google AI Studio that supports text-to-video and image-to-video workflows. By offering the same speed as the Fast model at less than half the price, this update makes high-volume video applications economically viable for developers.

Xiaomi MiMo Slashes V2.5 API Pricing by 99 Percent

MiMoMay 27

Xiaomi MiMo Slashes V2.5 API Pricing by 99 Percent

Xiaomi permanently reduced MiMo-V2.5 Series API costs by up to 99% and eliminated tiered pricing for long-context inputs. The update uses inference optimizations to provide 5–8x more tokens in subscription plans, making high-volume agentic workflows significantly more affordable.