Body
Now generate video from text or images through one unified API. Use a TypeScript SDK to turn any model into an agent. Organize your OpenRouter projects into separate environments with Workspaces.
OpenRouter
OpenRouter ( https://openrouter.ai?utm_campaign=050726_monthly-recap_s1&utm_content=April+2026+Recap+-+V3+Final+B&utm_medium=email_action&utm_source=customer.io )
**********************
What shipped in April.
**********************
Now generate video from text or images through one unified API. Use a TypeScript SDK to turn any model into an agent. Organize your OpenRouter projects into separate environments with Workspaces. And 35 new models landed. Here's the recap.
Platform features
01
Video generation
Video APIs are fragmented. Providers use different request shapes, parameter names, and billing units. We built one API around those differences.
Submit a prompt to /api/v1/videos, get a job ID back, retrieve the video when ready. Parameters are normalized across every model (resolution, duration, aspect ratio, audio, frame images, reference images). A capability-discovery endpoint tells you what each model supports before you call it.
sora-2-pro veo-3.1 seedance-2.0 wan-2.7
Browse video models → ( https://openrouter.ai/models?fmt=cards&output_modalities=video&utm_campaign=050726_monthly-recap_s1&utm_content=April+2026+Recap+-+V3+Final+B&utm_medium=email_action&utm_source=customer.io )|Try the demo → ( https://multimedia-explorer.openrouter.ai/?utm_campaign=050726_monthly-recap_s1&utm_content=April+2026+Recap+-+V3+Final+B&utm_medium=email_action&utm_source=customer.io )
02
Workspaces
Separate environments for separate projects, each with its own API keys, routing defaults, guardrails, and observability dashboard. Useful for keeping side projects, prototypes, and production cleanly isolated under one account.
Create a workspace → ( https://openrouter.ai/workspaces/new?utm_campaign=050726_monthly-recap_s1&utm_content=April+2026+Recap+-+V3+Final+B&utm_medium=email_action&utm_source=customer.io )|Read the docs → ( https://openrouter.ai/docs/guides/features/workspaces?utm_campaign=050726_monthly-recap_s1&utm_content=April+2026+Recap+-+V3+Final+B&utm_medium=email_action&utm_source=customer.io )
03
Agent SDK with callModel
One function handles multi-turn tool calling, streaming, stop conditions, and cost tracking across 300+ models. Stop conditions are composable: cap a session at Cost(1.00), stop when a specific tool gets called, limit by turn count, or combine them. The @openrouter/agent TypeScript package ships with two scaffolds: create-agent-tui for a terminal harness and create-headless-agent for a server-side one. Typed tool context with Zod is supported.
SDK docs → ( https://openrouter.ai/sdk?utm_campaign=050726_monthly-recap_s1&utm_content=April+2026+Recap+-+V3+Final+B&utm_medium=email_action&utm_source=customer.io )|Build your own harness → ( https://openrouter.ai/announcements/create-agent-harness-with-agent-sdk?utm_campaign=050726_monthly-recap_s1&utm_content=April+2026+Recap+-+V3+Final+B&utm_medium=email_action&utm_source=customer.io )
04
Benchmark scores on every model page
Every model page now shows benchmark scores from Artificial Analysis: coding, math, science, and long-context reasoning. Useful when deciding between models at similar price points, or weighing open-weights against proprietary. The Rankings page ( https://openrouter.ai/rankings?utm_campaign=050726_monthly-recap_s1&utm_content=April+2026+Recap+-+V3+Final+B&utm_medium=email_action&utm_source=customer.io ) picked up the same data with scatter charts and long-context trends from 100K to 1M tokens.
See the rankings → ( https://openrouter.ai/rankings?utm_campaign=050726_monthly-recap_s1&utm_content=April+2026+Recap+-+V3+Final+B&utm_medium=email_action&utm_source=customer.io )
05
I/O loggingBETA
The Activity log can now capture the full request and response for every API call. Open any generation to inspect the prompt, switch to Dev mode for raw JSON, or replay it in chatroom against a different model.
Enable I/O logging → ( https://openrouter.ai/settings/observability?utm_campaign=050726_monthly-recap_s1&utm_content=April+2026+Recap+-+V3+Final+B&utm_medium=email_action&utm_source=customer.io )
Also shipped in April
Reranker models with Cohere and Fireworks, Model Fusion for combining outputs across multiple models, prompt history with replay and side-by-side comparison, Design Arena ELO rankings on the comparison pages, knowledge cutoff dates exposed in the /models API, Stripe Projects for streamlined account setup, and typed tool context with Zod validation in the TypeScript SDK.
New models
Kimi K2.6
moonshotai/kimi-k2.6 · Apr 20
1.82T tokens since launch. 1T-parameter MoE, 32B active per token. SWE-Bench Pro 58.6% beats GPT-5.4 and Claude Opus 4.6. Open weights on Hugging Face.
$0.74/M in$3.49/M out262K ctxopen weights
View on /models → ( https://openrouter.ai/moonshotai/kimi-k2.6?utm_campaign=050726_monthly-recap_s1&utm_content=April+2026+Recap+-+V3+Final+B&utm_medium=email_action&utm_source=customer.io )
Claude Opus 4.7
anthropic/claude-opus-4.7 · Apr 16
935B tokens since launch. Anthropic's frontier reasoning and coding model. Beats Opus 4.6, GPT-5.4, and Gemini 3.1 Pro across reasoning and code benchmarks.
$5/M in$25/M out1M ctx
View on /models → ( https://openrouter.ai/anthropic/claude-opus-4.7?utm_campaign=050726_monthly-recap_s1&utm_content=April+2026+Recap+-+V3+Final+B&utm_medium=email_action&utm_source=customer.io )
GPT-5.5 + GPT-5.5 Pro
openai/gpt-5.5 · Apr 24
OpenAI's latest. Pro variant pushes harder on the reasoning ceiling at the cost of latency and price; the base model is the workhorse.
$5/M in$30/M out1M ctxPro: $30/$180 per M
View on /models → ( https://openrouter.ai/openai/gpt-5.5?utm_campaign=050726_monthly-recap_s1&utm_content=April+2026+Recap+-+V3+Final+B&utm_medium=email_action&utm_source=customer.io )
deepseek/deepseek-v4-flash ( https://openrouter.ai/deepseek/deepseek-v4-flash?utm_campaign=050726_monthly-recap_s1&utm_content=April+2026+Recap+-+V3+Final+B&utm_medium=email_action&utm_source=customer.io )
704B tokens since launch · 1M ctx · $0.14/$0.28 per M · Apr 24
deepseek/deepseek-v4-pro ( https://openrouter.ai/deepseek/deepseek-v4-pro?utm_campaign=050726_monthly-recap_s1&utm_content=April+2026+Recap+-+V3+Final+B&utm_medium=email_action&utm_source=customer.io )
1M ctx · $0.43/$0.87 per M · the heavier end of the V4 family · Apr 24
xiaomi/mimo-v2.5-pro ( https://openrouter.ai/xiaomi/mimo-v2.5-pro?utm_campaign=050726_monthly-recap_s1&utm_content=April+2026+Recap+-+V3+Final+B&utm_medium=email_action&utm_source=customer.io )
V2.5 line, successor to V2 · 1M ctx · $1.00/$3.00 per M · Apr 22
openai/gpt-5.4-image-2 ( https://openrouter.ai/openai/gpt-5.4-image-2?utm_campaign=050726_monthly-recap_s1&utm_content=April+2026+Recap+-+V3+Final+B&utm_medium=email_action&utm_source=customer.io )
Image generation, a new modality on the API surface · April release
35 new models went live in April across Anthropic, DeepSeek, Moonshot, OpenAI, Xiaomi, Alibaba, xAI, and Google. See all April launches → ( https://openrouter.ai/models?order=newest&utm_campaign=050726_monthly-recap_s1&utm_content=April+2026+Recap+-+V3+Final+B&utm_medium=email_action&utm_source=customer.io )
Platform in numbers
Models
300+
Across 60+ providers
Tokens / month
70T
Processed on platform
Developers
5M+
Globally on OpenRouter
Browse all models ( https://openrouter.ai/models?utm_campaign=050726_monthly-recap_s1&utm_content=April+2026+Recap+-+V3+Final+B&utm_medium=email_action&utm_source=customer.io )
Latest from the blog
GPT-5.5 price increase: what it actually costs ( https://openrouter.ai/announcements/gpt55-cost-analysis?utm_campaign=050726_monthly-recap_s1&utm_content=April+2026+Recap+-+V3+Final+B&utm_medium=email_action&utm_source=customer.io )
GPT-5.5 price increase: what it actually costs ( https://openrouter.ai/announcements/gpt55-cost-analysis?utm_campaign=050726_monthly-recap_s1&utm_content=April+2026+Recap+-+V3+Final+B&utm_medium=email_action&utm_source=customer.io )
OpenAI doubled GPT-5.5's per-token price, but the model writes less. We measured real usage to find the net cost impact.
Read the analysis → ( https://openrouter.ai/announcements/gpt55-cost-analysis?utm_campaign=050726_monthly-recap_s1&utm_content=April+2026+Recap+-+V3+Final+B&utm_medium=email_action&utm_source=customer.io )
What Opus 4.7's tokenizer actually costs ( https://openrouter.ai/announcements/opus-47-tokenizer-analysis?utm_campaign=050726_monthly-recap_s1&utm_content=April+2026+Recap+-+V3+Final+B&utm_medium=email_action&utm_source=customer.io )
What Opus 4.7's tokenizer actually costs ( https://openrouter.ai/announcements/opus-47-tokenizer-analysis?utm_campaign=050726_monthly-recap_s1&utm_content=April+2026+Recap+-+V3+Final+B&utm_medium=email_action&utm_source=customer.io )
A million real requests analyzed. Up to 27% higher cost on most prompts, 1.6% lower under 2K tokens.
Read the analysis → ( https://openrouter.ai/announcements/opus-47-tokenizer-analysis?utm_campaign=050726_monthly-recap_s1&utm_content=April+2026+Recap+-+V3+Final+B&utm_medium=email_action&utm_source=customer.io )
Response caching: zero cost for identical requests ( https://openrouter.ai/announcements/response-caching?utm_campaign=050726_monthly-recap_s1&utm_content=April+2026+Recap+-+V3+Final+B&utm_medium=email_action&utm_source=customer.io )
Response caching: zero cost for identical requests ( https://openrouter.ai/announcements/response-caching?utm_campaign=050726_monthly-recap_s1&utm_content=April+2026+Recap+-+V3+Final+B&utm_medium=email_action&utm_source=customer.io )
A new Response Caching header. Identical API requests come back in a fraction of the latency, at zero cost.
Read the post → ( https://openrouter.ai/announcements/response-caching?utm_campaign=050726_monthly-recap_s1&utm_content=April+2026+Recap+-+V3+Final+B&utm_medium=email_action&utm_source=customer.io )
Up next. May focuses on agent infrastructure: spend analytics by workspace, per-key rate limits, and the next routing primitive. View announcements → ( https://openrouter.ai/announcements?utm_campaign=050726_monthly-recap_s1&utm_content=April+2026+Recap+-+V3+Final+B&utm_medium=email_action&utm_source=customer.io )
openrouter.ai ( https://openrouter.ai?utm_campaign=050726_monthly-recap_s1&utm_content=April+2026+Recap+-+V3+Final+B&utm_medium=email_action&utm_source=customer.io )·Discord ( https://discord.gg/openrouter?utm_campaign=050726_monthly-recap_s1&utm_content=April+2026+Recap+-+V3+Final+B&utm_medium=email_action&utm_source=customer.io )·X ( https://x.com/openrouter?utm_campaign=050726_monthly-recap_s1&utm_content=April+2026+Recap+-+V3+Final+B&utm_medium=email_action&utm_source=customer.io )·Docs ( https://openrouter.ai/docs?utm_campaign=050726_monthly-recap_s1&utm_content=April+2026+Recap+-+V3+Final+B&utm_medium=email_action&utm_source=customer.io )
169 Madison Avenue, New York, NY 10016
Manage preferences ( https://track.customer.io/manage_subscription_preferences/dgSE_QoDAIvZ9gKK2fYCAZ4DMOtv_Kglb503qIvl1Q== )|Unsubscribe ( https://track.customer.io/unsubscribe/dgSE_QoDAIvZ9gKK2fYCAZ4DMOtv_Kglb503qIvl1Q== )