Provider guide
Where to run Claude Opus 4.8
13 live listings tracked.
FASTEST MEASURED
133 tok/s
measured throughput · $10.00 input / $50.00 output per million tokens
OpenRouter$5.00 in/1M$25.00 out/1M—1M—2 hours agoDeepInfra$5.00 in/1M$25.00 out/1M—1M—2 hours agoMicrosoft Azure AI$5.00 in/1M$25.00 out/1M23 tok/s1M—2 hours agoGoogle Vertex AIzero-retention$5.00 in/1M$25.00 out/1M75 tok/s1M—2 hours agoAnthropicCHEAPEST$5.00 in/1M$25.00 out/1M54 tok/s1M—2 hours agoAmazon Bedrockzero-retention$5.00 in/1M$25.00 out/1M58 tok/s1M—2 hours agoClaude Platform on AWS$5.00 in/1M$25.00 out/1M41 tok/s1M—2 hours agoAmazon Bedrockzero-retention$5.50 in/1M$27.50 out/1M65 tok/s1M—2 hours agoMicrosoft Azure AI$5.50 in/1M$27.50 out/1M29 tok/s1M—2 hours agoAmazon Bedrockzero-retention$5.50 in/1M$27.50 out/1M73 tok/s1M—2 hours agoGoogle Vertex AIzero-retention$5.50 in/1M$27.50 out/1M110 tok/s1M—2 hours agoGoogle Vertex AIzero-retention$5.50 in/1M$27.50 out/1M84 tok/s1M—2 hours agoAnthropicfast tier$10.00 in/1M$50.00 out/1M133 tok/s1M—2 hours ago
Full specs, hardware verdicts and benchmarks on the Claude Opus 4.8 model page →