https://agent.sasid.ai/llm-api-pricing Changes between dated OpenRouter public API observations. Third-party-reported, not measured by Crewshal. 53 known changes across 255 compared endpoint keys. 11 ambiguous or changed-lineage keys omitted. Partial known-change history; not complete. Added/removed mean endpoint-listing observations, not retirement or account access. Noon UTC dates are ordering placeholders for snapshot days, not observed publication or vendor-change times. en-us Fri, 09 Oct 2026 12:00:00 GMT https://agent.sasid.ai/llm-api-pricing#price-changes https://agent.sasid.ai/llm-api-pricing#changes-2026-10-09 Fri, 09 Oct 2026 12:00:00 GMT Claude Sonnet 5.5 at Amazon Bedrock: cache read $0.20 to $0.10. Claude Sonnet 5.5 at Anthropic: cache read $0.20 to $0.10. Claude Sonnet 5.5 at Azure: cache read $0.20 to $0.10. Claude Sonnet 5.5 at Azure (regional): cache read $0.22 to $0.11. Claude Sonnet 5.5 at Claude Platform on AWS: cache read $0.20 to $0.10. Claude Sonnet 5.5 at Google Vertex (regional): cache read $0.22 to $0.11. Claude Sonnet 5.5 at Google Vertex: cache read $0.20 to $0.10. Claude Sonnet 5.5 at Google Vertex (regional): cache read $0.22 to $0.11. DeepSeek V4 Flash 0423 at OpenInference: input $0.0132 to $0.0046. DeepSeek V4 Flash 0423 at OpenInference: output $1.41 to $0.2803. DeepSeek V4 Flash 0423 at OpenInference: cache read $0.0132 to $0.0046. DeepSeek V4 Flash 0423 at Relace: input $0.012 to $0.03. DeepSeek V4 Flash 0423 at Relace: cache read $0.012 to $0.03. DeepSeek V4 Flash 0423 at Wafer: added. DeepSeek V4 Pro 0423 at NextBit: removed. DeepSeek V4 Pro 0423 at Relace: input $0.2067 to $0.30. DeepSeek V4 Pro 0423 at Relace: cache read $0.21 to $0.23. Llama 4 Maverick at DigitalOcean: cache read — to $0.05. Kimi K3 at AkashML: input $1.30 to $1.20. Kimi K3 at AkashML: cache read $1.30 to $1.20. Kimi K3 at InferenceNet (fast): input $3.50 to $2.99. Kimi K3 at InferenceNet: input $0.95 to $0.58. Kimi K3 at InferenceNet: output $14.00 to $12.00. Kimi K3 at InferenceNet: cache read $0.31 to $0.30. Kimi K3 at Makora: removed. Kimi K3 at Makora: added. Kimi K3 at Morph: input $1.27 to $2.50. Kimi K3 at Morph: output $13.30 to $14.00. Kimi K3 at Morph: cache read $0.278 to $0.29. Kimi K3 at Parasail (fast): added. Kimi K3 at Parasail: input $3.00 to $2.60. Kimi K3 at Parasail: output $15.00 to $13.00. Kimi K3 at Parasail: cache read $0.30 to $0.26. Kimi K3 at Relace: input $0.83 to $0.57. Kimi K3 at Relace: cache read $0.45 to $0.30. Kimi K3 at Wafer: input $0.95 to $0.79. Kimi K3 at Wafer: output $14.00 to $15.00. Kimi K3 at Wafer: cache read $0.40 to $0.45. gpt-oss-120b at Mancer 2: input $0.045 to $0.05. GLM 5.3 at InferenceNet: removed. GLM 5.3 at InferenceNet: added. GLM 5.3 at Io Net: added. GLM 5.3 at Morph: input $0.179 to $0.145. GLM 5.3 at Morph: output $3.55 to $3.74. GLM 5.3 at Morph: cache read $0.137 to $0.108. GLM 5.3 at Relace: input $0.03 to $0.0312. GLM 5.3 at Relace: cache read $0.03 to $0.029. GLM 5.3 at Wafer: input $0.15 to $0.17. GLM 5.3 at Wafer: output $7.00 to $3.39. GLM 5.3 at Wafer: cache read $0.14 to $0.16. GLM 5.3 at Wafer (regional): input $0.07 to $0.039. GLM 5.3 at Wafer (regional): output $7.00 to $3.39. GLM 5.3 at Wafer (regional): cache read $0.065 to $0.038. 255 of 266 endpoint keys compared. 11 ambiguous or changed-lineage keys omitted: deepseek/deepseek-v4-flash / streamlake/fp8, deepseek/deepseek-v4-pro / reka, deepseek/deepseek-v4-pro / streamlake/fp8, moonshotai/kimi-k3 / decart/mxfp4, moonshotai/kimi-k3 / phala, z-ai/glm-5.3 / decart/fp4, z-ai/glm-5.3 / makora/fp4, z-ai/glm-5.3 / mistral/nvfp4, z-ai/glm-5.3 / novita/fp8, z-ai/glm-5.3 / reka, z-ai/glm-5.3 / siliconflow/fp8.