Alex Atallah says OpenRouter added 39 models in the last week
Alex Atallah says OpenRouter added 39 models over the past week.
#openrouter
View all AI newsOpenRouter says six decision models are now on the market, two of them free
OpenRouter says that two weeks after TypeSafe started the category, six decision models are now available, including two free models.
Opus 5.5 leads Anthropic models on OpenRouter by spend and tokens
About one week after launch, OpenRouter says Opus 5.5 ranks first among Anthropic models on its platform by share of spend and share of tokens, with a particularly rapid shift away from Opus 5.
Claude Sonnet 5.5 on OpenRouter keeps 1M context at $2 and $10 per million tokens
OpenRouter prices Claude Sonnet 5.5 at $2 per million input tokens and $10 per million output tokens, with a 1 million-token context window. Those rates are unchanged from Sonnet 5.
Claude Sonnet 5.5 is live on OpenRouter
OpenRouter now offers Anthropic’s Claude Sonnet 5.5. OpenRouter says it is significantly smarter than Sonnet 5, writes more clearly, and is 30% faster and about 30% cheaper for most work.
OpenRouter says solar-decide beats Jev 1.13 on JevBench accuracy and latency
On JevBench, OpenRouter says solar-decide scored 87.0% accuracy versus 86.1% for Jev 1.13, with a median latency of 0.14 seconds versus 0.30 seconds.
Solar Decide returns structured decisions on OpenRouter at $0.10 per million input tokens
Solar Decide is a decision model built on Solar Mini 4. On OpenRouter’s Decisions API it returns a structured decision instead of free text, priced at $0.10 per million input tokens and $0 for output.
Solar Mini 4 is a 35B MoE model priced at $0.05 per million input tokens on OpenRouter
Upstage’s Solar Mini 4 on OpenRouter is a 35B mixture-of-experts model with 3B active parameters, a 524K context window, tool calling, structured outputs, and optional reasoning. OpenRouter prices it at $0.05 per million input tokens and $0.20 per million output tokens.
Solar Mini 4 and Solar Decide are live on OpenRouter at 50% off
OpenRouter now offers upstageai’s Solar Mini 4 and Solar Decide. Both models are 50% off for a limited time.
OpenRouter prices Span-01 at $0.02 per million input tokens
OpenRouter charges $0.02 per million input tokens for Span-01 and nothing for its output. Span-01 Lite is free.
OpenRouter sets no size cap on Span-01 spans
OpenRouter says Span-01 and Span-01 Lite accept plain text or a full span of system, user, assistant, and tool messages, with no cap on span size. It describes them as checks for risky tool calls, support chats that need a person, and bulk eval-trace labels.
Respan’s Span-01 and Span-01 Lite are live on OpenRouter
OpenRouter now offers Respan’s Span-01 and Span-01 Lite, decision models that return the probability that specified behaviors appear in an agent span.
OpenRouter says Jev took 27% of weekly classification requests
OpenRouter says Jev accounted for 27% of weekly classification request volume, nearly twice the share of DeepSeek V4 Flash, which previously led that category.
Elvis’s small Pi SDK test finds Jev Router cheaper and faster than fixed GPT-6 Sol
On a small support agent, elvis says Jev Router and a fixed GPT-6 Sol baseline both solved all 8 cases across 32 calls. The router cost $0.008 versus $0.018, with a 1.5-second median response time versus 1.9 seconds.
OpenRouter Chat shows Jev Router’s per-turn model choices and scores
OpenRouter Chat’s routing insights panel shows the model Jev Router selects for each turn and the scores behind that choice, including task, difficulty, precision, and larger model benefit. The router is available there as typesafe/jev-router.
OpenRouter introduces typesafe/jev-router, a cache-aware model router
OpenRouter has introduced typesafe/jev-router, a cache-aware model router powered by Jev and typesafeai. OpenRouter says it selects the best model and reasoning effort for each request while balancing quality, speed, and cost.
Qwen Image 3 Pro leads the first Memebench bracket with 35%
In the first Memebench bracket, Qwen Image 3 Pro took 35% of the vote, ahead of Nano Banana Pro at 33%, Riverflow V2 Pro at 23%, and GPT Image 2 at 9%.
Qwen Image 3 Pro wins the first Memebench bracket with 35% of the vote
OpenRouter said Qwen Image 3 Pro won the first Memebench bracket for the “Why would I deceive you?” meme with 35% of the vote. Nano Banana Pro finished one vote behind at 33%.
Kev uses the same OpenRouter API as Jev
OpenRouter says developers already calling Jev can switch to Kev by changing only the model field to jaredpalmer/kev-4b.
Kev 4B is now available on OpenRouter
jaredpalmer’s small open-weight System One model accepts state and typed questions and returns typed answers. OpenRouter prices it at $0.042 per million input tokens and $0 for output, with an 8K context window.