Choose a category in More filters to see relevant price sorts.
Model / what’s differentBenchmark resultsAPI priceExplore
openaiReleased 21 days ago
Requires Responses API for tools; offers Ultrafast inference with US or EU data residency.
1.1M contextImage inputTool calling
$2.20in$11.00out/ 1M tokens · USDAzure · via OpenRouter · 3 endpointsazure/eu · prompt ≤ 272000 tokens anthropicReleased 22 days ago
Tuned for quick iteration on scoped fixes and documents; Anthropic favors Opus 5.5 for open-ended work needing sustained judgment.
1M contextImage inputTool calling
$2.00in$10.00out/ 1M tokens · USDAzure · via OpenRouter · 2 endpointsazure/global anthropicReleased 28 days ago
Always-on adaptive thinking defaults to medium effort; built for sustained work across large codebases and professional documents.
1M contextImage inputTool calling
$4.00in$20.00out/ 1M tokens · USDAzure · via OpenRouter · 2 endpointsazure/global openaiReleased 28 days ago
Can turn reasoning off for high-volume requests; Chat Completions tool calls require reasoning_effort=none.
1.1M contextImage inputTool calling
$0.10in$0.50out/ 1M tokens · USDAzure · via OpenRouter · 3 endpointsazure · prompt ≤ 272000 tokens openaiReleased Sep 3
Accepts mid-turn steering and async tool calls, so agents can take new instructions while other tools are still running.
1.1M contextImage inputTool calling
$10.00in$50.00out/ 1M tokens · USDAzure · via OpenRouter · 2 endpointsazure · prompt ≤ 272000 tokens anthropicReleased Sep 1
Beta controls change effort per message without invalidating the prompt cache and report progress between tool calls.
1M contextImage inputTool calling