Choose a category in More filters to see relevant price sorts.
Model / what’s differentBenchmark resultsAPI priceExplore
openaiReleased 20 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 · USDAmazon Bedrock · via OpenRouteramazon-bedrock/us-east-1 · prompt ≤ 272000 tokens anthropicReleased 21 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
anthropicReleased 27 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 · USDAmazon Bedrock · via OpenRouter · 3 endpointsamazon-bedrock openaiReleased 27 days ago
Can turn reasoning off for high-volume requests; Chat Completions tool calls require reasoning_effort=none.
1.1M contextImage inputTool calling
$0.11in$0.55out/ 1M tokens · USDAmazon Bedrock · via OpenRouteramazon-bedrock/us-east-1 · 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
$11.00in$55.00out/ 1M tokens · USDAmazon Bedrock · via OpenRouteramazon-bedrock/us-west-2 · 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
moonshotaiReleased Jul 16
2.8T total and 104B active parameters; combines Kimi Delta Attention with native image/video input under the Kimi K3 license.
1M contextImage inputVideo input
$3.00in$15.00out/ 1M tokens · USDAmazon Bedrock · via OpenRouteramazon-bedrock/us-east-2