---
title: "Cache-Eingabe: der veröffentlichte Wiederholungssatz · Undominated.ai"
canonical: https://undominated.ai/de/cache/
description: "214 von 358 Standard-Modellen veröffentlichen einen Cache-Eingabesatz. Der Median ist 12% der frischen Eingabe."
---

# Cache-Eingabe: der veröffentlichte Wiederholungssatz · Undominated.ai

> 214 von 358 Standard-Modellen veröffentlichen einen Cache-Eingabesatz. Der Median ist 12% der frischen Eingabe.

# Cache

Ein Cache-Eingabesatz ist das, was der Anbieter für schon gesehene Token veröffentlicht. Gleich dem Frischsatz ist das kein Rabatt. Ohne veröffentlichten Cachesatz erfindet dieser Katalog keinen.

Stand 6. Okt. 2026: 214 von 358 Standard-Modellen veröffentlichen einen Cache-Eingabesatz. Der Median liegt bei 12% des Frischsatzes. 5 veröffentlichen Cache gleich Eingabe. 144 veröffentlichen keinen Cachesatz.

Die Trefferquote ist Ihre, nicht unsere. Die Tabelle sind die veröffentlichten Sätze, sortiert nach dem günstigsten Cache relativ zur frischen Eingabe. Workload-Mischungen stehen auf der Rangliste.

| Modell | Frisch ein | Cache ein | Cache / frisch |
| --- | --- | --- | --- |
| [MiMo-V2.5-Pro](/models/xiaomi__mimo-v2.5-pro/) | $0,435 | $0,0036 | 0,8% |
| [MiMo-V2.6-Pro-UltraSpeed](/models/xiaomi__mimo-v2.6-pro-ultraspeed/) | $4,35 | $0,036 | 0,8% |
| [MiMo-V2.6-Pro](/models/xiaomi__mimo-v2.6-pro/) | $0,430 | $0,0036 | 0,8% |
| [MiMo-V2.5](/models/xiaomi__mimo-v2.5/) | $0,140 | $0,0028 | 2% |
| [MiMo-V2.6-Flash](/models/xiaomi__mimo-v2.6-flash/) | $0,140 | $0,0028 | 2% |
| [LongCat 2.0](/models/meituan__longcat-2.0/) | $0,750 | $0,015 | 2% |
| [Muse Spark 1.2 Contributor](/models/meta__muse-spark-1.2-contributor/) | $0,100 | $0,0020 | 2% |
| [Muse Spark 1.3 Contributor](/models/meta__muse-spark-1.3-contributor/) | $0,100 | $0,0020 | 2% |
| [Claude Fable 5.1](/models/anthropic__claude-fable-5.1/) | $10,00 | $0,250 | 2,5% |
| [DeepSeek V4 Flash Vision Exp](/models/deepseek__deepseek-v4-flash-vision-exp/) | $0,440 | $0,014 | 3,2% |
| [Pareto 26.10 Preview](/models/unbiased__pareto-26.10-preview/) | $0,800 | $0,030 | 3,8% |
| [Claude Opus 5.5](/models/anthropic__claude-opus-5.5/) | $4,00 | $0,200 | 5% |
| [GPT-6.1 Sol](/models/openai__gpt-6.1-sol/) | $2,00 | $0,100 | 5% |
| [GPT-6.1 Sol Pro](/models/openai__gpt-6.1-sol-pro/) | $2,00 | $0,100 | 5% |
| [Hy4 preview](/models/tencent__hy4-preview/) | $0,834 | $0,042 | 5% |
| [DeepSeek V4 Pro 0813](/models/deepseek__deepseek-v4-pro-0813/) | $1,30 | $0,100 | 7,7% |
| [Claude Sonnet 4](/models/anthropic__claude-sonnet-4/) | $3,00 | $0,300 | 10% |
| [Claude Sonnet 4.5](/models/anthropic__claude-sonnet-4.5/) | $3,00 | $0,300 | 10% |
| [Claude Sonnet 4.6](/models/anthropic__claude-sonnet-4.6/) | $3,00 | $0,300 | 10% |
| [Ember-1](/models/fireworks__ember-1/) | $3,00 | $0,300 | 10% |
| [Gemini 2.5 Flash Lite](/models/google__gemini-2.5-flash-lite/) | $0,100 | $0,010 | 10% |
| [Gemini 3.5 Flash](/models/google__gemini-3.5-flash/) | $1,50 | $0,150 | 10% |
| [Gemini 3.6 Flash](/models/google__gemini-3.6-flash/) | $0,750 | $0,075 | 10% |
| [Gemini 3.7 Flash](/models/google__gemini-3.7-flash/) | $1,50 | $0,150 | 10% |
| [Gemini 3.8 Flash](/models/google__gemini-3.8-flash/) | $1,50 | $0,150 | 10% |
| [GPT-5 Nano](/models/openai__gpt-5-nano/) | $0,050 | $0,0050 | 10% |
| [GPT-5.2](/models/openai__gpt-5.2/) | $1,75 | $0,175 | 10% |
| [GPT-5.2 Chat](/models/openai__gpt-5.2-chat/) | $1,75 | $0,175 | 10% |
| [GPT-5.2-Codex](/models/openai__gpt-5.2-codex/) | $1,75 | $0,175 | 10% |
| [GPT-5.3-Codex](/models/openai__gpt-5.3-codex/) | $1,75 | $0,175 | 10% |
| [GPT-5.4 Mini](/models/openai__gpt-5.4-mini/) | $0,750 | $0,075 | 10% |
| [GPT-5.4 Nano](/models/openai__gpt-5.4-nano/) | $0,200 | $0,020 | 10% |
| [GPT-5.6 Luna](/models/openai__gpt-5.6-luna/) | $0,200 | $0,020 | 10% |
| [GPT-5.6 Luna Pro](/models/openai__gpt-5.6-luna-pro/) | $0,200 | $0,020 | 10% |
| [GPT-6 Luna](/models/openai__gpt-6-luna/) | $0,100 | $0,010 | 10% |
| [GPT-6 Luna Pro](/models/openai__gpt-6-luna-pro/) | $0,100 | $0,010 | 10% |
| [Laguna S 2.1](/models/poolside__laguna-s-2.1/) | $0,100 | $0,010 | 10% |
| [Mercury 2.5](/models/inception__mercury-2.5/) | $0,200 | $0,020 | 10% |
| [Ministral 3 14B 2512](/models/mistralai__ministral-14b-2512/) | $0,200 | $0,020 | 10% |
| [Ministral 3 3B 2512](/models/mistralai__ministral-3b-2512/) | $0,100 | $0,010 | 10% |
| [Mistral Medium 3](/models/mistralai__mistral-medium-3/) | $0,400 | $0,040 | 10% |
| [Mistral Medium 3.1](/models/mistralai__mistral-medium-3.1/) | $0,400 | $0,040 | 10% |
| [Nex-N2.5-Mini](/models/nex-agi__nex-n2.5-mini/) | $0,025 | $0,0025 | 10% |
| [Saba](/models/mistralai__mistral-saba/) | $0,200 | $0,020 | 10% |
| [Solar Mini 4](/models/upstage__solar-mini4/) | $0,100 | $0,010 | 10% |
| [Voxtral Small 24B 2507](/models/mistralai__voxtral-small-24b-2507/) | $0,100 | $0,010 | 10% |
| [Claude Fable 5](/models/anthropic__claude-fable-5/) | $10,00 | $1,00 | 10% |
| [Claude Haiku 4.5](/models/anthropic__claude-haiku-4.5/) | $1,00 | $0,100 | 10% |
| [Claude Opus 4.1](/models/anthropic__claude-opus-4.1/) | $15,00 | $1,50 | 10% |
| [Claude Opus 4.5](/models/anthropic__claude-opus-4.5/) | $5,00 | $0,500 | 10% |
| [Claude Opus 4.6](/models/anthropic__claude-opus-4.6/) | $5,00 | $0,500 | 10% |
| [Claude Opus 4.7](/models/anthropic__claude-opus-4.7/) | $5,00 | $0,500 | 10% |
| [Claude Opus 4.8](/models/anthropic__claude-opus-4.8/) | $5,00 | $0,500 | 10% |
| [Claude Opus 5](/models/anthropic__claude-opus-5/) | $5,00 | $0,500 | 10% |
| [Claude Sonnet 5](/models/anthropic__claude-sonnet-5/) | $2,00 | $0,200 | 10% |
| [Claude Sonnet 5.5](/models/anthropic__claude-sonnet-5.5/) | $2,00 | $0,200 | 10% |
| [Codestral 2508](/models/mistralai__codestral-2508/) | $0,300 | $0,030 | 10% |
| [Fugu Ultra](/models/sakana__fugu-ultra/) | $5,00 | $0,500 | 10% |
| [Fugu Ultra v2](/models/sakana__fugu-ultra-v2/) | $5,00 | $0,500 | 10% |
| [Gemini 2.5 Flash](/models/google__gemini-2.5-flash/) | $0,300 | $0,030 | 10% |
| [Gemini 2.5 Pro](/models/google__gemini-2.5-pro/) | $1,25 | $0,125 | 10% |
| [Gemini 2.5 Pro Preview 06-05](/models/google__gemini-2.5-pro-preview/) | $1,25 | $0,125 | 10% |
| [Gemini 3 Flash Preview](/models/google__gemini-3-flash-preview/) | $0,500 | $0,050 | 10% |
| [Gemini 3.1 Flash Lite](/models/google__gemini-3.1-flash-lite/) | $0,250 | $0,025 | 10% |
| [Gemini 3.1 Flash Lite Preview](/models/google__gemini-3.1-flash-lite-preview/) | $0,250 | $0,025 | 10% |
| [Gemini 3.1 Pro Preview](/models/google__gemini-3.1-pro-preview/) | $2,00 | $0,200 | 10% |
| [Gemini 3.1 Pro Preview Custom Tools](/models/google__gemini-3.1-pro-preview-customtools/) | $2,00 | $0,200 | 10% |
| [Gemini 3.5 Flash Lite](/models/google__gemini-3.5-flash-lite/) | $0,300 | $0,030 | 10% |
| [GPT Chat Latest](/models/openai__gpt-chat-latest/) | $5,00 | $0,500 | 10% |
| [GPT-5](/models/openai__gpt-5/) | $1,25 | $0,125 | 10% |
| [GPT-5 Image Mini](/models/openai__gpt-5-image-mini/) | $2,50 | $0,250 | 10% |
| [GPT-5 Mini](/models/openai__gpt-5-mini/) | $0,250 | $0,025 | 10% |
| [GPT-5.1](/models/openai__gpt-5.1/) | $1,25 | $0,125 | 10% |
| [GPT-5.1-Codex-Max](/models/openai__gpt-5.1-codex-max/) | $1,25 | $0,125 | 10% |
| [GPT-5.4](/models/openai__gpt-5.4/) | $2,50 | $0,250 | 10% |
| [GPT-5.5](/models/openai__gpt-5.5/) | $5,00 | $0,500 | 10% |
| [GPT-5.6 Sol](/models/openai__gpt-5.6-sol/) | $4,00 | $0,400 | 10% |
| [GPT-5.6 Sol Pro](/models/openai__gpt-5.6-sol-pro/) | $4,00 | $0,400 | 10% |
| [GPT-5.6 Terra](/models/openai__gpt-5.6-terra/) | $2,00 | $0,200 | 10% |
| [GPT-5.6 Terra Pro](/models/openai__gpt-5.6-terra-pro/) | $2,00 | $0,200 | 10% |
| [GPT-6 Astra](/models/openai__gpt-6-astra/) | $10,00 | $1,00 | 10% |
| [GPT-6 Astra Pro](/models/openai__gpt-6-astra-pro/) | $10,00 | $1,00 | 10% |
| [GPT-6 Sol](/models/openai__gpt-6-sol/) | $2,00 | $0,200 | 10% |
| [GPT-6 Sol Pro](/models/openai__gpt-6-sol-pro/) | $2,00 | $0,200 | 10% |
| [Mercury 2](/models/inception__mercury-2/) | $0,250 | $0,025 | 10% |
| [MiniMax M2](/models/minimax__minimax-m2/) | $0,300 | $0,030 | 10% |
| [MiniMax M2-her](/models/minimax__minimax-m2-her/) | $0,300 | $0,030 | 10% |
| [MiniMax M2.1](/models/minimax__minimax-m2.1/) | $0,300 | $0,030 | 10% |
| [Ministral 3 8B 2512](/models/mistralai__ministral-8b-2512/) | $0,150 | $0,015 | 10% |
| [Mistral Large](/models/mistralai__mistral-large/) | $2,00 | $0,200 | 10% |
| [Mistral Large 2407](/models/mistralai__mistral-large-2407/) | $2,00 | $0,200 | 10% |
| [Mistral Large 3 2512](/models/mistralai__mistral-large-2512/) | $0,500 | $0,050 | 10% |
| [Mistral Small 4](/models/mistralai__mistral-small-2603/) | $0,150 | $0,015 | 10% |
| [Mixtral 8x22B Instruct](/models/mistralai__mixtral-8x22b-instruct/) | $2,00 | $0,200 | 10% |
| [Nano Banana (Gemini 2.5 Flash Image)](/models/google__gemini-2.5-flash-image/) | $0,300 | $0,030 | 10% |
| [Nano Banana Pro (Gemini 3 Pro Image Preview)](/models/google__gemini-3-pro-image-preview/) | $2,00 | $0,200 | 10% |
| [Nano Banana Pro (Gemini 3 Pro Image)](/models/google__gemini-3-pro-image/) | $2,00 | $0,200 | 10% |
| [Pareto](/models/unbiased__pareto/) | $2,50 | $0,250 | 10% |
| [Solar Pro 3](/models/upstage__solar-pro-3/) | $0,150 | $0,015 | 10% |
| [Mistral Large 4](/models/mistralai__mistral-large-4-0/) | $1,36 | $0,140 | 10,3% |
| [GPT-5.1-Codex](/models/openai__gpt-5.1-codex/) | $1,25 | $0,130 | 10,4% |
| [Qwen3.8 Flash](/models/qwen__qwen3.8-flash/) | $0,150 | $0,016 | 10,7% |
| [Qwen3.8 Omni Flash](/models/qwen__qwen3.8-omni-flash/) | $0,150 | $0,016 | 10,7% |
| [Qwen3 Coder 480B A35B](/models/qwen__qwen3-coder/) | $0,350 | $0,040 | 11,4% |
| [GPT-5.1-Codex-Mini](/models/openai__gpt-5.1-codex-mini/) | $0,250 | $0,030 | 12% |
| [Muse Spark 1.1](/models/meta__muse-spark-1.1/) | $1,25 | $0,150 | 12% |
| [Muse Spark 1.2](/models/meta__muse-spark-1.2/) | $1,25 | $0,150 | 12% |
| [Muse Spark 1.3](/models/meta__muse-spark-1.3/) | $1,25 | $0,150 | 12% |
| [Fugu Max](/models/sakana__fugu-max/) | $2,00 | $0,250 | 12,5% |
| [GPT-5 Image](/models/openai__gpt-5-image/) | $10,00 | $1,25 | 12,5% |
| [Qwen3.8 2.4T A95B](/models/qwen__qwen3.8-2.4t-a95b/) | $2,00 | $0,250 | 12,5% |
| [Qwen3.8 Max (0902)](/models/qwen__qwen3.8-max-0902/) | $2,00 | $0,250 | 12,5% |
| [Qwen3.8 Max Prime](/models/qwen__qwen3.8-max-prime/) | $4,00 | $0,500 | 12,5% |
| [Muse Glimmer 30B](/models/meta__muse-glimmer-30b/) | $0,300 | $0,040 | 13,3% |
| [Grok 4.5](/models/x-ai__grok-4.5/) | $2,00 | $0,300 | 15% |
| [Sakana Namazu](/models/sakana__sakana-namazu/) | $0,950 | $0,150 | 15,8% |
| [Grok 4.20](/models/x-ai__grok-4.20/) | $1,25 | $0,200 | 16% |
| [Grok 4.20 Multi-Agent](/models/x-ai__grok-4.20-multi-agent/) | $1,25 | $0,200 | 16% |
| [Grok 4.3](/models/x-ai__grok-4.3/) | $1,25 | $0,200 | 16% |
| [GLM 4.6V](/models/z-ai__glm-4.6v/) | $0,300 | $0,050 | 16,7% |
| [GLM 4.7 Flash](/models/z-ai__glm-4.7-flash/) | $0,060 | $0,010 | 16,7% |
| [Kimi K2.5](/models/moonshotai__kimi-k2.5/) | $0,600 | $0,100 | 16,7% |
| [Inkling](/models/thinkingmachines__inkling/) | $0,950 | $0,160 | 16,8% |
| [GLM 4.5](/models/z-ai__glm-4.5/) | $0,600 | $0,110 | 18,3% |
| [GLM 4.5V](/models/z-ai__glm-4.5v/) | $0,600 | $0,110 | 18,3% |
| [GLM 4.6](/models/z-ai__glm-4.6/) | $0,430 | $0,080 | 18,6% |
| [DeepSeek V4.1 Flash](/models/deepseek__deepseek-v4.1-flash/) | $0,053 | $0,010 | 18,9% |
| [GLM 4.5 Air](/models/z-ai__glm-4.5-air/) | $0,130 | $0,025 | 19,2% |
| [DeepSeek V4 Flash 0423](/models/deepseek__deepseek-v4-flash/) | $0,090 | $0,018 | 20% |
| [GLM 4.7](/models/z-ai__glm-4.7/) | $0,400 | $0,080 | 20% |
| [MiniMax M3](/models/minimax__minimax-m3/) | $0,280 | $0,056 | 20% |
| [Qwen-Plus](/models/qwen__qwen-plus/) | $0,260 | $0,052 | 20% |
| [Qwen3 Coder Flash](/models/qwen__qwen3-coder-flash/) | $0,195 | $0,039 | 20% |
| [Qwen3 Max](/models/qwen__qwen3-max/) | $0,780 | $0,156 | 20% |
| [Qwen3.7 Max](/models/qwen__qwen3.7-max/) | $1,48 | $0,295 | 20% |
| [Step 3.7 Flash](/models/stepfun__step-3.7-flash/) | $0,200 | $0,040 | 20% |
| [GLM 5 Turbo](/models/z-ai__glm-5-turbo/) | $1,20 | $0,240 | 20% |
| [GLM 5.3 Flash](/models/z-ai__glm-5.3-flash/) | $0,150 | $0,030 | 20% |
| [GLM 5V Turbo](/models/z-ai__glm-5v-turbo/) | $1,20 | $0,240 | 20% |
| [Grok Build 0.1](/models/x-ai__grok-build-0.1/) | $1,00 | $0,200 | 20% |
| [Ling 3.0 Flash](/models/inclusionai__ling-3.0-flash/) | $0,060 | $0,012 | 20% |
| [Ling 3.0 Flash Fin](/models/inclusionai__ling-3.0-flash-fin/) | $0,075 | $0,015 | 20% |
| [Ling 3.0 Flash VL](/models/inclusionai__ling-3.0-flash-vl/) | $0,060 | $0,012 | 20% |
| [MiniMax M2.7](/models/minimax__minimax-m2.7/) | $0,300 | $0,060 | 20% |
| [Nex-N2.5-Pro](/models/nex-agi__nex-n2.5-pro/) | $0,075 | $0,015 | 20% |
| [Qwen3 Coder Plus](/models/qwen__qwen3-coder-plus/) | $0,650 | $0,130 | 20% |
| [Qwen3.7 Flash](/models/qwen__qwen3.7-flash/) | $0,030 | $0,0060 | 20% |
| [Qwen3.7 Plus](/models/qwen__qwen3.7-plus/) | $0,320 | $0,064 | 20% |
| [Solar Pro 4](/models/upstage__solar-pro4/) | $0,300 | $0,060 | 20% |
| [GLM 5](/models/z-ai__glm-5/) | $0,700 | $0,140 | 20% |
| [GLM 5.3 Prime](/models/z-ai__glm-5.3-prime/) | $2,80 | $0,560 | 20% |
| [KAT-Coder-Pro V2.5](/models/kwaipilot__kat-coder-pro-v2.5/) | $0,740 | $0,150 | 20,3% |
| [MiniMax M2.5](/models/minimax__minimax-m2.5/) | $0,295 | $0,060 | 20,3% |
| [Kimi K2.6](/models/moonshotai__kimi-k2.6/) | $0,465 | $0,098 | 21% |
| [DeepSeek V4 Pro 0423](/models/deepseek__deepseek-v4-pro/) | $0,450 | $0,100 | 22,2% |
| [Inkling Small](/models/thinkingmachines__inkling-small/) | $0,450 | $0,100 | 22,2% |
| [Trinity Large Thinking](/models/arcee-ai__trinity-large-thinking/) | $0,250 | $0,060 | 24% |
| [GLM 5.3 FlashX](/models/z-ai__glm-5.3-flashx/) | $0,370 | $0,090 | 24,3% |
| [Aion 3.5](/models/aion-labs__aion-3.5/) | $3,00 | $0,750 | 25% |
| [Aion-2.0](/models/aion-labs__aion-2.0/) | $0,800 | $0,200 | 25% |
| [Aion-3.0](/models/aion-labs__aion-3.0/) | $3,00 | $0,750 | 25% |
| [DeepSeek V4 Flash 0731](/models/deepseek__deepseek-v4-flash-0731/) | $0,060 | $0,015 | 25% |
| [GPT-4.1](/models/openai__gpt-4.1/) | $2,00 | $0,500 | 25% |
| [GPT-4.1 Mini](/models/openai__gpt-4.1-mini/) | $0,400 | $0,100 | 25% |
| [GPT-4.1 Nano](/models/openai__gpt-4.1-nano/) | $0,100 | $0,025 | 25% |
| [GPT-5.4 Image 2](/models/openai__gpt-5.4-image-2/) | $8,00 | $2,00 | 25% |
| [Granite 4.2 8B](/models/ibm-granite__granite-4.2-8b/) | $0,060 | $0,015 | 25% |
| [Grok 4.6](/models/x-ai__grok-4.6/) | $2,00 | $0,500 | 25% |
| [Grok 4.7](/models/x-ai__grok-4.7/) | $2,00 | $0,500 | 25% |
| [Hy3](/models/tencent__hy3/) | $0,132 | $0,033 | 25% |
| [Kimi K2 Thinking](/models/moonshotai__kimi-k2-thinking/) | $0,600 | $0,150 | 25% |
| [Nova Premier 1.0](/models/amazon__nova-premier-v1/) | $2,50 | $0,625 | 25% |
| [o3](/models/openai__o3/) | $2,00 | $0,500 | 25% |
| [o4 Mini](/models/openai__o4-mini/) | $1,10 | $0,275 | 25% |
| [o4 Mini High](/models/openai__o4-mini-high/) | $1,10 | $0,275 | 25% |
| [Aion 3.5 Mini](/models/aion-labs__aion-3.5-mini/) | $0,700 | $0,180 | 25,7% |
| [Aion-3.0-Mini](/models/aion-labs__aion-3.0-mini/) | $0,700 | $0,180 | 25,7% |
| [Kimi K2.7 Code](/models/moonshotai__kimi-k2.7-code/) | $0,671 | $0,180 | 26,8% |
| [Nemotron 3 Ultra](/models/nvidia__nemotron-3-ultra-550b-a55b/) | $0,625 | $0,188 | 30% |
| [Hy3 preview](/models/tencent__hy3-preview/) | $0,180 | $0,060 | 33,3% |
| [Qwen3.5-35B-A3B](/models/qwen__qwen3.5-35b-a3b/) | $0,140 | $0,050 | 35,7% |
| [Gemma 4 26B A4B](/models/google__gemma-4-26b-a4b-it/) | $0,069 | $0,029 | 42% |
| [GLM 5.2](/models/z-ai__glm-5.2/) | $0,309 | $0,137 | 44,3% |
| [Skyfall 36B V2](/models/thedrummer__skyfall-36b-v2/) | $0,550 | $0,250 | 45,5% |
| [Command A+](/models/cohere__command-a-plus/) | $0,300 | $0,150 | 50% |
| [Cydonia 24B V4.1](/models/thedrummer__cydonia-24b-v4.1/) | $0,300 | $0,150 | 50% |
| [DeepSeek V3.2](/models/deepseek__deepseek-v3.2/) | $0,260 | $0,130 | 50% |
| [GPT-4o](/models/openai__gpt-4o/) | $2,50 | $1,25 | 50% |
| [GPT-4o (2024-08-06)](/models/openai__gpt-4o-2024-08-06/) | $2,50 | $1,25 | 50% |
| [GPT-4o (2024-11-20)](/models/openai__gpt-4o-2024-11-20/) | $2,50 | $1,25 | 50% |
| [GPT-4o-mini](/models/openai__gpt-4o-mini/) | $0,150 | $0,075 | 50% |
| [GPT-4o-mini (2024-07-18)](/models/openai__gpt-4o-mini-2024-07-18/) | $0,150 | $0,075 | 50% |
| [gpt-oss-20b](/models/openai__gpt-oss-20b/) | $0,018 | $0,0090 | 50% |
| [gpt-oss-safeguard-20b](/models/openai__gpt-oss-safeguard-20b/) | $0,075 | $0,038 | 50% |
| [Laguna XS 2.1](/models/poolside__laguna-xs-2.1/) | $0,100 | $0,050 | 50% |
| [Nemotron 3.5 Lightning](/models/nvidia__nemotron-3.5-lightning/) | $0,060 | $0,030 | 50% |
| [o1](/models/openai__o1/) | $15,00 | $7,50 | 50% |
| [o3 Mini](/models/openai__o3-mini/) | $1,10 | $0,550 | 50% |
| [o3 Mini High](/models/openai__o3-mini-high/) | $1,10 | $0,550 | 50% |
| [Qwen2.5 VL 72B Instruct](/models/qwen__qwen2.5-vl-72b-instruct/) | $0,800 | $0,400 | 50% |
| [Qwen3.6 35B A3B](/models/qwen__qwen3.6-35b-a3b/) | $0,100 | $0,050 | 50% |
| [Ternary Bonsai 2 27B](/models/prism-ml__ternary-bonsai-2-27b/) | $0,075 | $0,038 | 50% |
| [GLM 5.1](/models/z-ai__glm-5.1/) | $1,19 | $0,600 | 50,4% |
| [Qwen3 VL 235B A22B Instruct](/models/qwen__qwen3-vl-235b-a22b-instruct/) | $0,200 | $0,110 | 55% |
| [Qwen3 Coder Next](/models/qwen__qwen3-coder-next/) | $0,120 | $0,070 | 58,3% |
| [Nemotron 3 Nano 30B A3B](/models/nvidia__nemotron-3-nano-30b-a3b/) | $0,050 | $0,030 | 60% |
| [Kimi K3](/models/moonshotai__kimi-k3/) | $0,680 | $0,450 | 66,2% |
| [GLM 5.3](/models/z-ai__glm-5.3/) | $0,200 | $0,150 | 75% |
| [Qwen3.8 27B](/models/qwen__qwen3.8-27b/) | $0,089 | $0,085 | 95,2% |
| [Gemma 4 31B](/models/google__gemma-4-31b-it/) | $0,140 | $0,140 | 100% |
| [gpt-oss-120b](/models/openai__gpt-oss-120b/) | $0,030 | $0,030 | 100% |
| [Schematron V2 Small](/models/inference-net__schematron-v2-small/) | $0,050 | $0,050 | 100% |
| [Schematron V2 Turbo](/models/inference-net__schematron-v2-turbo/) | $0,030 | $0,030 | 100% |
| [UI-TARS 7B](/models/bytedance__ui-tars-1.5-7b/) | $0,100 | $0,100 | 100% |

## Continue your investigation

 - [Check context tiers · English](/cliffs/)
- [Inspect batch variants](/de/batch/)
- [Import usage · English](/audit/)
- [Estimate a scenario · English](/compare/)
