Cache

A cached-input rate is what the seller publishes for tokens already seen. Equal to the fresh rate is not a discount. No published cache rate means this catalogue will not invent one.

Hit rate is yours, not ours. The table is the published rates, sorted cheapest cache relative to fresh input. Workload blends live on the leaderboard.

ModelFresh inCached inCached / fresh
MiMo-V2.5-Pro$0.435Price under confirmation since Oct 16, 2026$0.00360.8%
MiMo-V2.6-Pro-UltraSpeed$4.35$0.0360.8%
MiMo-V2.6-Pro$0.430$0.00360.8%
MiMo-V2.6-Flash$0.130$0.00201.5%
MiMo-V2.5$0.140$0.00282%
LongCat 2.0$0.750$0.0152%
Muse Spark 1.2 Contributor$0.100$0.00202%
Muse Spark 1.3 Contributor$0.100$0.00202%
Claude Fable 5.1$10.00$0.2502.5%
DeepSeek V4 Flash Vision Exp$0.440$0.0143.2%
Claude Opus 5.5$4.00$0.2005%
Claude Sonnet 5.5$2.00$0.1005%
Gemini 4 Argon$4.00$0.2005%
GPT-6.1 Sol$2.00$0.1005%
GPT-6.1 Sol Pro$2.00$0.1005%
Muse Wonder$4.00$0.2005%
Step 5 Preview$1.00$0.0505%
Hy4 preview$0.834$0.0425%
DeepSeek V4 Pro 0813$1.30$0.1007.7%
Claude Haiku 5.5$0.100$0.01010%
Claude Sonnet 4.5$3.00$0.30010%
Claude Sonnet 4.6$3.00$0.30010%
Ember-1$3.00$0.30010%
Gemini 2.5 Flash Lite$0.100$0.01010%
Gemini 3.5 Flash$1.50$0.15010%
Gemini 3.6 Flash$0.750$0.07510%
Gemini 3.7 Flash$1.50$0.15010%
Gemini 3.8 Flash$1.50$0.15010%
GPT-5 Nano$0.050$0.005010%
GPT-5.2$1.75$0.17510%
GPT-5.2 Chat$1.75$0.17510%
GPT-5.2-Codex$1.75$0.17510%
GPT-5.3-Codex$1.75$0.17510%
GPT-5.4 Mini$0.750$0.07510%
GPT-5.4 Nano$0.200$0.02010%
GPT-5.6 Luna$0.200$0.02010%
GPT-5.6 Luna Pro$0.200$0.02010%
GPT-6 Luna$0.100$0.01010%
GPT-6 Luna Pro$0.100$0.01010%
Kimi K2.6$0.450$0.04510%
Laguna S 2.1$0.100$0.01010%
Mercury 2.5$0.200$0.02010%
Ministral 3 14B 2512$0.200$0.02010%
Ministral 3 3B 2512$0.100$0.01010%
Mistral Medium 3$0.400$0.04010%
Mistral Medium 3.1$0.400$0.04010%
Nex-N2.5-Mini$0.025$0.002510%
Saba$0.200$0.02010%
Solar Mini 4$0.100$0.01010%
Voxtral Small 24B 2507$0.100$0.01010%
Claude Fable 5$10.00$1.0010%
Claude Haiku 4.5$1.00$0.10010%
Claude Opus 4.1$15.00$1.5010%
Claude Opus 4.5$5.00$0.50010%
Claude Opus 4.6$5.00$0.50010%
Claude Opus 4.7$5.00$0.50010%
Claude Opus 4.8$5.00$0.50010%
Claude Opus 5$5.00$0.50010%
Claude Sonnet 5$2.00$0.20010%
Codestral 2508$0.300$0.03010%
Fugu Ultra$5.00$0.50010%
Fugu Ultra v2$5.00$0.50010%
Gemini 2.5 Flash$0.300$0.03010%
Gemini 2.5 Pro$1.25$0.12510%
Gemini 2.5 Pro Preview 06-05$1.25$0.12510%
Gemini 3 Flash Preview$0.500$0.05010%
Gemini 3.1 Flash Lite$0.250$0.02510%
Gemini 3.1 Flash Lite Preview$0.250$0.02510%
Gemini 3.1 Pro Preview$2.00$0.20010%
Gemini 3.1 Pro Preview Custom Tools$2.00$0.20010%
Gemini 3.5 Flash Lite$0.300$0.03010%
GPT Chat Latest$5.00$0.50010%
GPT-5$1.25$0.12510%
GPT-5 Image Mini$2.50$0.25010%
GPT-5 Mini$0.250$0.02510%
GPT-5.1$1.25$0.12510%
GPT-5.1-Codex-Max$1.25$0.12510%
GPT-5.4$2.50$0.25010%
GPT-5.5$5.00$0.50010%
GPT-5.6 Sol$4.00$0.40010%
GPT-5.6 Sol Pro$4.00$0.40010%
GPT-5.6 Terra$2.00$0.20010%
GPT-5.6 Terra Pro$2.00$0.20010%
GPT-6 Astra$10.00$1.0010%
GPT-6 Astra Pro$10.00$1.0010%
GPT-6 Sol$2.00$0.20010%
GPT-6 Sol Pro$2.00$0.20010%
Mercury 2$0.250$0.02510%
MiniMax M2-her$0.300$0.03010%
MiniMax M2.1$0.300$0.03010%
Ministral 3 8B 2512$0.150$0.01510%
Mistral Large$2.00$0.20010%
Mistral Large 2407$2.00$0.20010%
Mistral Large 3 2512$0.500$0.05010%
Mistral Small 4$0.150$0.01510%
Mixtral 8x22B Instruct$2.00$0.20010%
Nano Banana (Gemini 2.5 Flash Image)$0.300$0.03010%
Nano Banana Pro (Gemini 3 Pro Image Preview)$2.00$0.20010%
Nano Banana Pro (Gemini 3 Pro Image)$2.00$0.20010%
Pareto 26.9$2.50$0.25010%
Qwen3.6 27B$0.250$0.02510%
Solar Pro 3$0.150$0.01510%
Mistral Large 4$1.36$0.14010.3%
GPT-5.1-Codex$1.25$0.13010.4%
Qwen3.8 Flash$0.150$0.01610.7%
Qwen3.8 Omni Flash$0.150$0.01610.7%
GPT-5.1-Codex-Mini$0.250$0.03012%
Muse Spark 1.1$1.25$0.15012%
Muse Spark 1.2$1.25$0.15012%
Muse Spark 1.3$1.25$0.15012%
Muse Spark Open$1.25$0.15012%
Fugu Max$2.00$0.25012.5%
GPT-5 Image$10.00$1.2512.5%
Qwen3.8 2.4T A95B$2.00$0.25012.5%
Qwen3.8 Max (0902)$2.00$0.25012.5%
Qwen3.8 Max Prime$4.00$0.50012.5%
Muse Glimmer 30B$0.300$0.04013.3%
Nemotron 3.5 Super VL$0.150$0.02013.3%
Grok 4.5$2.00$0.30015%
Sakana Namazu$0.950$0.15015.8%
Grok 4.20$1.25$0.20016%
Grok 4.20 Multi-Agent$1.25$0.20016%
Grok 4.3$1.25$0.20016%
GLM 4.6V$0.300$0.05016.7%
Kimi K2.5$0.600$0.10016.7%
Inkling$0.950$0.16016.8%
GLM 4.5$0.600$0.11018.3%
GLM 4.5V$0.600$0.11018.3%
GLM 4.7$0.600Price under confirmation since Oct 16, 2026$0.11018.3%
GLM 4.6$0.430$0.08018.6%
DeepSeek V4.1 Flash$0.053Price under confirmation since Oct 12, 2026$0.01018.9%
GLM 4.5 Air$0.130$0.02519.2%
DeepSeek V4 Flash 0423$0.090Price under confirmation since Oct 12, 2026$0.01820%
MiniMax M3$0.280$0.05620%
Qwen-Plus$0.260$0.05220%
Qwen3 Coder Flash$0.195$0.03920%
Qwen3.7 Max$1.48$0.29520%
Step 3.7 Flash$0.200$0.04020%
GLM 5 Turbo$1.20$0.24020%
GLM 5.3 Flash$0.150Price under confirmation since Oct 12, 2026$0.03020%
GLM 5V Turbo$1.20$0.24020%
Grok Build 0.1$1.00$0.20020%
Ling 3.0 Flash$0.060$0.01220%
Ling 3.0 Flash VL$0.060$0.01220%
Ling 3.1 Flash$0.300$0.06020%
MiniMax M2.7$0.300$0.06020%
Nex-N2.5-Pro$0.075$0.01520%
Qwen3.7 Flash$0.030$0.006020%
Qwen3.7 Plus$0.320$0.06420%
Qwen3.8 27B$0.425$0.08520%
Solar Pro 4$0.300$0.06020%
GLM 5$0.700$0.14020%
GLM 5.3 Prime$2.80$0.56020%
MiniMax M2.5$0.295$0.06020.3%
DeepSeek V4 Pro 0423$0.450Price under confirmation since Oct 12, 2026$0.10022.2%
Inkling Small$0.450$0.10022.2%
Trinity Large Thinking$0.250$0.06024%
GLM 5.3 FlashX$0.370$0.09024.3%
Aion 3.5$3.00$0.75025%
Aion-2.0$0.800$0.20025%
Aion-3.0$3.00$0.75025%
DeepSeek V4 Flash 0731$0.060Price under confirmation since Oct 15, 2026$0.01525%
GPT-4.1$2.00$0.50025%
GPT-4.1 Mini$0.400$0.10025%
GPT-4.1 Nano$0.100$0.02525%
GPT-5.4 Image 2$8.00$2.0025%
Granite 4.2 8B$0.060$0.01525%
Grok 4.6$2.00$0.50025%
Grok 4.7$2.00$0.50025%
Hy3$0.132$0.03325%
Kimi K2 Thinking$0.600$0.15025%
Nova Premier 1.0$2.50$0.62525%
o3$2.00$0.50025%
o4 Mini$1.10$0.27525%
o4 Mini High$1.10$0.27525%
Aion 3.5 Mini$0.700$0.18025.7%
Aion-3.0-Mini$0.700$0.18025.7%
Kimi K2.7 Code$0.671$0.18026.8%
Nemotron 3 Ultra$0.625$0.18830%
Hy3 preview$0.180$0.06033.3%
Qwen3.5-35B-A3B$0.140$0.05035.7%
GLM 5.2$0.309Price under confirmation since Oct 12, 2026$0.13744.3%
Skyfall 36B V2$0.550$0.25045.5%
Qwen3 VL 8B Instruct$0.250$0.12048%
Command A+$0.300$0.15050%
Cydonia 24B V4.1$0.300$0.15050%
DeepSeek V3.2$0.260$0.13050%
Gemma 3 4B$0.040$0.02050%
GPT-4o$2.50$1.2550%
GPT-4o (2024-08-06)$2.50$1.2550%
GPT-4o (2024-11-20)$2.50$1.2550%
GPT-4o-mini$0.150$0.07550%
GPT-4o-mini (2024-07-18)$0.150$0.07550%
gpt-oss-20b$0.018$0.009050%
gpt-oss-safeguard-20b$0.075$0.03850%
Laguna XS 2.1$0.100$0.05050%
LFM2.5-24B-A2B$0.050$0.02550%
Llama 3.3 70B Instruct$0.200$0.10050%
Nemotron 3.5 Lightning$0.060$0.03050%
o1$15.00$7.5050%
o3 Mini$1.10$0.55050%
o3 Mini High$1.10$0.55050%
Qwen2.5 VL 72B Instruct$0.800$0.40050%
Qwen3.6 35B A3B$0.100$0.05050%
Ternary Bonsai 2 27B$0.075$0.03850%
GLM 5.1$1.19$0.60050.4%
Qwen3 VL 235B A22B Instruct$0.200$0.11055%
Qwen3 Coder Next$0.120$0.07058.3%
Gemma 4 26B A4B $0.060$0.04066.7%
GLM 5.3$0.200Price under confirmation since Oct 12, 2026$0.15075%
Kimi K3$0.730Price under confirmation since Oct 13, 2026$0.55075.3%
Gemma 4 31B$0.140$0.140100%
gpt-oss-120b$0.030Price under confirmation since Oct 16, 2026$0.030100%
Schematron V2 Small$0.050$0.050100%
Schematron V2 Turbo$0.030$0.030100%
UI-TARS 7B $0.100$0.100100%
Evidence & Ask