OpenRouter Batch API limits files, media input, and its web plugin

OOpenRouter9/22/2026, 09:19:46

Images and files submitted to the OpenRouter Batch API must be public URLs; base64 is not accepted. Audio and video input are not accepted, and OpenRouter’s own web plugin is not available in batch. The complete limitations are listed in the Batch API limitations documentation.

#openrouter #batch-api #api-limits

View original post ↗

Previous articleOpenRouter logs each batch and retains inputs and results for 30 days Next articleOpenRouter Batch API is live, halving per-token pricing on most models

Related AI news

OpenRouter logs each batch and retains inputs and results for 30 days

Each batch appears in the Batches tab of OpenRouter logs with its model, provider, status, and cost. Inputs and results are kept for 30 days or until the batch is deleted.

OOpenRouter•9/22/2026, 09:27:07•

#openrouter #batch-api #logs #data-retention

OpenRouter Batch API is live, halving per-token pricing on most models

OpenRouter’s Batch API is available for work that does not need an immediate answer. It cuts per-token pricing in half on most models and returns results within 24 hours.

OOpenRouter•9/22/2026, 09:19:13•

#openrouter #batch-api #pricing #api

OpenRouter adds Perplexity Decider v1.1 with free output

OpenRouter has integrated Perplexity AI's open-weights multimodal decision model, Perplexity Decider v1.1 (pplx-decider-v1.1-27b). The model is priced at $0.02 per million input tokens with free output.

OOpenRouter•10/7/2026, 14:03:20•

#openrouter #perplexity #multimodal-models #model-integration

OpenRouter adds OpenAI's GPT-6 Luna Decisions with 1M context and free output

OpenRouter has made OpenAI's GPT-6 Luna Decisions available on its platform, featuring a 1M context window, pricing of $0.10 per million input tokens, and free output.

OOpenRouter•10/7/2026, 13:33:04•

#openrouter #openai #decisions-api #gpt-6-luna

Claude Haiku 5.5 is live on OpenRouter with reasoning support

OpenRouter has added Anthropic's Claude Haiku 5.5 to its platform, noting it is the first Haiku model to support reasoning efforts, runs at roughly 75% lower cost than its predecessor, and achieves over 100 tokens per second.

OOpenRouter•10/7/2026, 12:04:01•

#openrouter #claude-haiku #anthropic

Reset history AI News FAQ Usage limits RSS feeds API MCP Skill

News is compiled from public information. The data is for reference only, and this site has no affiliation with OpenAI.

Data & original project: Did Codex Reset · Licoy