Tuesday, October 13, 2026 · No. 443Prices synced 2 hours ago
All·AI·Model

The AI Model Price Index

Prime Inference

Gateways & marketplaces · 60 listings · documentation ↗ · @ai-sdk/openai-compatible

Prime Inference model prices, USD per one million tokens
CompareModelInput $/1MOutput $/1MCached $/1MContextCapsAcceptsCutoffListed
GPT-6.1 SolnewPrime Inference$2.00$10.00—1.1MRTVApr 2026Sep 2026
Claude Opus 5.5Prime Inference$4.00$20.00—1MRTVJun 2026Sep 2026
GPT-6 LunaPrime Inference$0.10$0.50—1.1MRTVMay 2026Sep 2026
GPT-6 SolPrime Inference$2.00$10.00—1.1MRTVApr 2026Sep 2026
Grok 4.7Prime Inference$1.60$4.80—500KRTVMay 2026Sep 2026
DeepSeek V4.1 FlashPrime Inference$0.30$1.20$0.031.0MRTWMay 2025Sep 2026
GPT-6 AstraPrime Inference$10.00$50.00—1.1MRTVApr 2026Sep 2026
Gemini 3.8 FlashPrime Inference$0.75$3.75—1.0MRTV—Sep 2026
Claude Fable 5.1Prime Inference$10.00$50.00—1MRTVJun 2026Sep 2026
GLM-5.3-FlashPrime Inference$0.15$0.50—1.0MRTVW—Aug 2026
GLM-5.3Prime Inference$1.40$4.40$0.261.0MRTW—Aug 2026
Gemini 3.7 FlashPrime Inference$1.35$6.75—1.0MRTVMar 2026Aug 2026
Grok 4.6Prime Inference$2.00$6.00—500KRTVFeb 2026Aug 2026
DeepSeek V4 Flash 0731Prime Inference$0.44$1.32—1.0MRTWMay 2025Jul 2026
Claude Opus 5Prime Inference$5.00$25.00—1MRTVMay 2026Jul 2026
Gemini 3.6 FlashPrime Inference$1.50$7.50—1.0MRTVMar 2026Jul 2026
Kimi K3Prime Inference$3.45$17.25—1.0MRTVW—Jul 2026
GPT-5.6 LunaPrime Inference$0.20$1.20—1.1MRTVFeb 2026Jul 2026
GPT-5.6 SolPrime Inference$5.00$30.00—1.1MRTVFeb 2026Jul 2026
GPT-5.6 TerraPrime Inference$2.50$15.00—1.1MRTVFeb 2026Jul 2026
Claude Sonnet 5Prime Inference$2.00$10.00—1MRTVJan 2026Jun 2026
GLM-5.2Prime Inference$1.54$4.84—1.0MRTW—Jun 2026
Claude Fable 5Prime Inference$10.00$50.00—1MRTVJan 2026Jun 2026
Claude Opus 4.8Prime Inference$5.00$25.00—1MRTVJan 2026May 2026
Gemini 3.5 FlashPrime Inference$1.50$9.00—1.0MRTVJan 2025May 2026
DeepSeek V4 FlashPrime Inference$0.44$1.32—1.0MRTWMay 2025Apr 2026
DeepSeek V4 ProPrime Inference$1.91$3.83—1.0MRTWMay 2025Apr 2026
GPT-5.5Prime Inference$5.00$30.00—1.1MRTVDec 2025Apr 2026
Claude Opus 4.7Prime Inference$5.00$25.00—1MRTVJan 2026Apr 2026
GPT-5.4 miniPrime Inference$0.75$4.50—400KRTVAug 2025Mar 2026
GPT-5.4 nanoPrime Inference$0.20$1.25—400KRTVAug 2025Mar 2026
Mistral Small 4Prime Inference$0.165$0.66—262KRTVWJun 2025Mar 2026
GPT-5.4Prime Inference$2.50$15.00—1.1MRTVAug 2025Mar 2026
GPT-5.4 ProPrime Inference$30.00$180—1.1MRTVAug 2025Mar 2026
Gemini 3.1 Pro PreviewPrime Inference$2.00$12.00—1.0MRTVJan 2025Feb 2026
Claude Sonnet 4.6Prime Inference$3.00$15.00—1MRTVAug 2025Feb 2026
Claude Opus 4.6Prime Inference$5.00$25.00—1MRTVMay 2025Feb 2026
GPT-5.3 CodexPrime Inference$1.75$14.00—400KRTVAug 2025Feb 2026
Qwen3 Coder NextPrime Inference$0.30$1.50—262KTWSep 2025Feb 2026
Gemini 3 Flash PreviewPrime Inference$0.50$3.00—1.0MRTVJan 2025Dec 2025
GPT-5.2Prime Inference$1.75$14.00—400KRTVAug 2025Dec 2025
GPT-5.2 ProPrime Inference$21.00$168—400KRTVAug 2025Dec 2025
Mistral Large 3Prime Inference$0.50$1.50—262KTVWNov 2024Dec 2025
GPT-5.1Prime Inference$1.25$10.00—400KRTVSep 2024Nov 2025
Qwen3 VL 30B A3B InstructPrime Inference$0.20$0.70—262KTVW—Oct 2025
Qwen3 VL 235B A22B InstructPrime Inference$0.30$1.50—262KTVWMar 2025Sep 2025
Kimi K2 Instruct 0905Prime Inference$0.60$2.50—262KTW—Sep 2025
GPT-5Prime Inference$1.25$10.00—400KRTVSep 2024Aug 2025
GPT-5 MiniPrime Inference$0.25$2.00—400KRTVMay 2024Aug 2025
GPT-5 NanoPrime Inference$0.05$0.40—400KRTVMay 2024Aug 2025
GPT OSS 120BPrime Inference$0.35$0.75—131KRTW—Aug 2025
GPT OSS 20BPrime Inference$0.07$0.30—131KRTW—Aug 2025
GPT-4.1Prime Inference$2.00$8.00—1.0MTVApr 2024Apr 2025
GPT-4.1 miniPrime Inference$0.40$1.60—1.0MTVApr 2024Apr 2025
GPT-4.1 nanoPrime Inference$0.10$0.40—1.0MTVApr 2024Apr 2025
Gemma 3 27B ITPrime Inference$0.119$0.30—131KTVWAug 2024Mar 2025
Llama-3.3-70B-InstructPrime Inference$1.04$2.25—131KTWDec 2023Dec 2024
GPT-4o miniPrime Inference$0.15$0.60—128KTVSep 2023Jul 2024
Mistral NemoPrime Inference$0.165$0.17—131KTWJul 2024Jul 2024
GPT-4oPrime Inference$2.50$10.00—128KTVSep 2023May 2024