Estimator part of the price index

Price your workload across every model.

Describe it in a sentence or fill in the fields. You'll see the bill for every model, the cheapest equivalent that fits, and where the money goes. Prices pull from the live index.

Support bot over our docs, 5k chats/day, 3 turns each Summarize 2,000 news articles a day into 3 bullets Coding agent: plan, edit, review — ~40k runs/month Classify 1M tickets per month by topic
Workload profile Tweak anything — the board updates live.
share of system tokens served from cache
Estimated spend · recommended model
$186 /mo
450K req/mo · 2.4K tok/req
$0.0004per request
Cheapest equivalent that fits your needs
DeepSeek R1DeepSeek · Frontier · 128K ctx
$186 $0.0004 / call
92% Switch GPT-5 → DeepSeek R1, save $2,034/mo ($24,404/yr)

Every model, priced for this workload

$/mo $/call

Ranked cheapest first · green = cheapest equivalent, your baseline marked

I Ling-2.6-flashMid · 262K ctx · below min tier $9.77 <$0.0001/call cheaper −100% Llama 3.1 8B InstructMid · 131K ctx · below min tier $23.49 <$0.0001/call cheaper −99% Mistral NemoMid · 131K ctx · below min tier $23.49 <$0.0001/call cheaper −99% I Granite 4.0 MicroMid · 131K ctx · below min tier $34.76 <$0.0001/call cheaper −98% S Llama 3 8B LunarisMid · 8K ctx · below min tier $45.27 $0.0001/call cheaper −98% L LFM2-24B-A2BMid · 32K ctx · below min tier $48.06 $0.0001/call cheaper −98% gpt-oss-20bMid · 131K ctx · below min tier $50.56 $0.0001/call cheaper −98% Qwen2.5 7B InstructMid · 32K ctx · below min tier $53.82 $0.0001/call cheaper −98% A Nova Micro 1.0Mid · 128K ctx · below min tier $56.07 $0.0001/call cheaper −97% Ministral 3 3B 2512Mid · 131K ctx · below min tier $57.87 $0.0001/call cheaper −97% Llama 3.2 1B InstructMid · 60K ctx · below min tier $59.16 $0.0001/call cheaper −97% Mistral Small 3Mid · 32K ctx · below min tier $59.58 $0.0001/call cheaper −97% C Command R7B (12-2024)Mid · 128K ctx · below min tier $60.08 $0.0001/call cheaper −97% Gemma 3 4BMid · 131K ctx · below min tier $63.00 $0.0001/call cheaper −97% I Granite 4.1 8BMid · 131K ctx · below min tier $63.00 $0.0001/call cheaper −97% G MythoMax 13BMid · 4K ctx · below min tier $65.34 $0.0001/call cheaper −97% gpt-oss-120bMid · 131K ctx · below min tier $66.58 $0.0001/call cheaper −97% A Trinity MiniMid · 131K ctx · below min tier $66.96 $0.0001/call cheaper −97% T Hy3 previewMid · 262K ctx · below min tier $69.93 $0.0002/call cheaper −97% Gemma 3 12BMid · 131K ctx · below min tier $71.55 $0.0002/call cheaper −97% Gemma 3n 4BMid · 32K ctx · below min tier $75.60 $0.0002/call cheaper −97% Qwen3 30B A3B Instruct 2507Mid · 128K ctx · below min tier $77.21 $0.0002/call cheaper −97% N Nemotron 3 Nano 30B A3BMid · 262K ctx · below min tier $80.10 $0.0002/call cheaper −96% M Phi 4Mid · 16K ctx · below min tier $83.61 $0.0002/call cheaper −96% Ministral 3 8B 2512Mid · 262K ctx · below min tier $86.80 $0.0002/call cheaper −96% GPT-5 NanoMid · 400K ctx · below min tier $91.62 $0.0002/call cheaper −96% X MiMo-V2-FlashMid · 262K ctx · below min tier $92.07 $0.0002/call cheaper −96% Voxtral Small 24B 2507Mid · 32K ctx · below min tier $92.07 $0.0002/call cheaper −96% S Step 3.5 FlashMid · 262K ctx · below min tier $94.23 $0.0002/call cheaper −96% Z GLM 4.7 FlashMid · 202K ctx · below min tier $95.13 $0.0002/call cheaper −96% A Nova Lite 1.0Mid · 300K ctx · below min tier $96.12 $0.0002/call cheaper −96% P Laguna XS.2Mid · 262K ctx · below min tier $97.65 $0.0002/call cheaper −96% DeepSeek V4 FlashMid · 1M ctx · below min tier $98.61 $0.0002/call cheaper −96% X MiMo-V2.5Mid · 1.05M ctx · below min tier $98.61 $0.0002/call cheaper −96% gpt-oss-safeguard-20bMid · 131K ctx · below min tier $98.89 $0.0002/call cheaper −96% Qwen3 235B A22B Instruct 2507Mid · 262K ctx · below min tier $99.72 $0.0002/call cheaper −96% Gemma 3 27BMid · 131K ctx · below min tier $101 $0.0002/call cheaper −95% Mistral Small 3.2 24BMid · 128K ctx · below min tier $103 $0.0002/call cheaper −95% Llama 3.2 3B InstructMid · 80K ctx · below min tier $104 $0.0002/call cheaper −95% Qwen3.5-FlashMid · 1M ctx · below min tier $104 $0.0002/call cheaper −95% R Reka EdgeMid · 16K ctx · below min tier $109 $0.0002/call cheaper −95% Qwen3 235B A22B Thinking 2507Mid · 262K ctx · below min tier $109 $0.0002/call cheaper −95% Gemini 2.5 Flash Lite Preview 09-2025Mid · 1.05M ctx · below min tier $109 $0.0002/call cheaper −95% Gemini 2.5 Flash LiteMid · 1.05M ctx · below min tier $109 $0.0002/call cheaper −95% Qwen3 Coder 30B A3B InstructMid · 160K ctx · below min tier $110 $0.0002/call cheaper −95% Gemma 4 26B A4BMid · 262K ctx · below min tier $112 $0.0002/call cheaper −95% Qwen3 8BMid · 40K ctx · below min tier $114 $0.0003/call cheaper −95% Ministral 3 14B 2512Mid · 262K ctx · below min tier $116 $0.0003/call cheaper −95% Qwen3.5-9BMid · 262K ctx · below min tier $117 $0.0003/call cheaper −95% GPT-4.1 NanoSmall · 1M ctx · below min tier $118 $0.0003/call cheaper −95% B Seed 1.6 FlashMid · 262K ctx · below min tier $120 $0.0003/call cheaper −95% Qwen3 32BMid · 40K ctx · below min tier $121 $0.0003/call cheaper −95% Llama 4 ScoutMid · 1M ctx · below min tier $125 $0.0003/call cheaper −94% B UI-TARS 7BMid · 128K ctx · below min tier $126 $0.0003/call cheaper −94% R Reka Flash 3Mid · 65K ctx · below min tier $126 $0.0003/call cheaper −94% Qwen3 14BMid · 40K ctx · below min tier $133 $0.0003/call cheaper −94% M Phi 4 Mini InstructMid · 128K ctx · below min tier $133 $0.0003/call cheaper −94% I Ring-2.6-1TMid · 262K ctx · below min tier $142 $0.0003/call cheaper −94% I Ling-2.6-1TMid · 262K ctx · below min tier $142 $0.0003/call cheaper −94% Qwen3 30B A3B Thinking 2507Mid · 131K ctx · below min tier $142 $0.0003/call cheaper −94% Mistral Small 4Small · 262K ctx · below min tier $143 $0.0003/call cheaper −94% Llama 3.3 70B InstructMid · 131K ctx · below min tier $147 $0.0003/call cheaper −93% Llama 3 8B InstructMid · 8K ctx · below min tier $152 $0.0003/call cheaper −93% Gemma 4 31BMid · 262K ctx · below min tier $153 $0.0003/call cheaper −93% Qwen3 VL 8B InstructMid · 131K ctx · below min tier $159 $0.0004/call cheaper −93% N Nemotron 3 SuperMid · 262K ctx · below min tier $160 $0.0004/call cheaper −93% B Seed-2.0-MiniMid · 262K ctx · below min tier $160 $0.0004/call cheaper −93% E Rnj 1 InstructMid · 32K ctx · below min tier $163 $0.0004/call cheaper −93% U Solar Pro 3Mid · 128K ctx · below min tier $164 $0.0004/call cheaper −93% Qwen3 VL 32B InstructMid · 131K ctx · below min tier $167 $0.0004/call cheaper −92% SabaMid · 32K ctx · below min tier $184 $0.0004/call cheaper −92% DeepSeek R1 Frontier · 128K ctx $186 $0.0004/call cheaper −92% DeepSeek V3Mid · 128K ctx · below min tier $186 $0.0004/call cheaper −92% N Hermes 4 70BMid · 131K ctx · below min tier $188 $0.0004/call cheaper −92% P Laguna M.1Mid · 262K ctx · below min tier $195 $0.0004/call cheaper −91% Qwen3 30B A3BMid · 40K ctx · below min tier $196 $0.0004/call cheaper −91% Llama Guard 4 12BMid · 163K ctx · below min tier $196 $0.0004/call cheaper −91% GPT-4o-mini (2024-07-18)Mid · 128K ctx · below min tier $198 $0.0004/call cheaper −91% Z GLM 4.5 AirMid · 131K ctx · below min tier $205 $0.0005/call cheaper −91% Qwen3 VL 30B A3B InstructMid · 131K ctx · below min tier $208 $0.0005/call cheaper −91% Qwen3 Coder NextMid · 262K ctx · below min tier $215 $0.0005/call cheaper −90% Qwen3 Next 80B A3B ThinkingMid · 131K ctx · below min tier $223 $0.0005/call cheaper −90% A Olmo 3 32B ThinkMid · 65K ctx · below min tier $223 $0.0005/call cheaper −90% T Hunyuan A13B InstructMid · 131K ctx · below min tier $226 $0.0005/call cheaper −90% T Rocinante 12BMid · 32K ctx · below min tier $230 $0.0005/call cheaper −90% I Mercury 2Mid · 128K ctx · below min tier $230 $0.0005/call cheaper −90% M MiniMax M2.5Mid · 196K ctx · below min tier $235 $0.0005/call cheaper −89% Llama 4 MaverickFrontier · 1M ctx $240 $0.0005/call cheaper −89% C Command R (08-2024)Mid · 128K ctx · below min tier $240 $0.0005/call cheaper −89% GPT-4o-mini Search PreviewMid · 128K ctx · below min tier $240 $0.0005/call cheaper −89% C Command RMid · 128K ctx · below min tier $240 $0.0005/call cheaper −89% Qwen-PlusMid · 1M ctx · below min tier $254 $0.0006/call cheaper −89% Qwen3 Coder FlashMid · 1M ctx · below min tier $257 $0.0006/call cheaper −88% A Trinity Large ThinkingMid · 262K ctx · below min tier $259 $0.0006/call cheaper −88% DeepSeek V3.2Mid · 128K ctx · below min tier $269 $0.0006/call cheaper −88% Qwen3 Next 80B A3B InstructMid · 262K ctx · below min tier $271 $0.0006/call cheaper −88% T Cydonia 24B V4.1Mid · 131K ctx · below min tier $276 $0.0006/call cheaper −88% Codestral 2508Mid · 256K ctx · below min tier $276 $0.0006/call cheaper −88% M MiniMax M2Mid · 196K ctx · below min tier $278 $0.0006/call cheaper −87% DeepSeek V3 0324Mid · 163K ctx · below min tier $278 $0.0006/call cheaper −87% M MiniMax M2.1Mid · 196K ctx · below min tier $281 $0.0006/call cheaper −87% DeepSeek V3.1Mid · 163K ctx · below min tier $283 $0.0006/call cheaper −87% Qwen3 VL 235B A22B InstructMid · 262K ctx · below min tier $283 $0.0006/call cheaper −87% M MiniMax M2.7Mid · 196K ctx · below min tier $287 $0.0006/call cheaper −87% S Step 3.7 FlashMid · 256K ctx · below min tier $290 $0.0006/call cheaper −87% Z GLM 4.6VMid · 131K ctx · below min tier $290 $0.0006/call cheaper −87% GPT-5.4 NanoMid · 400K ctx · below min tier $295 $0.0007/call cheaper −87% Qwen3.6 35B A3BMid · 262K ctx · below min tier $300 $0.0007/call cheaper −87% Qwen3.5-35B-A3BMid · 262K ctx · below min tier $300 $0.0007/call cheaper −87% X MiMo-V2.5-ProMid · 1.05M ctx · below min tier $303 $0.0007/call cheaper −86% DeepSeek V4 ProFrontier · 1M ctx $304 $0.0007/call cheaper −86% R1 Distill Qwen 32BMid · 32K ctx · below min tier $316 $0.0007/call cheaper −86% DeepSeek V3.2 ExpMid · 163K ctx · below min tier $318 $0.0007/call cheaper −86% M MiniMax M2-herMid · 65K ctx · below min tier $328 $0.0007/call cheaper −85% DeepSeek V3.1 TerminusMid · 163K ctx · below min tier $331 $0.0007/call cheaper −85% Qwen3 VL 8B ThinkingMid · 131K ctx · below min tier $341 $0.0008/call cheaper −85% M MiniMax M3Mid · 524K ctx · below min tier $345 $0.0008/call cheaper −84% K KAT-Coder-Pro V2Mid · 256K ctx · below min tier $345 $0.0008/call cheaper −84% Gemini 3.1 Flash LiteMid · 1.05M ctx · below min tier $358 $0.0008/call cheaper −84% Gemini 3.1 Flash Lite PreviewMid · 1.05M ctx · below min tier $358 $0.0008/call cheaper −84% Qwen3.6 FlashMid · 1M ctx · below min tier $364 $0.0008/call cheaper −84% Qwen3.7 PlusMid · 1M ctx · below min tier $367 $0.0008/call cheaper −83% M MiniMax-01Mid · 1M ctx · below min tier $372 $0.0008/call cheaper −83% P INTELLECT-3Mid · 131K ctx · below min tier $372 $0.0008/call cheaper −83% Qwen Plus 0728Mid · 1M ctx · below min tier $372 $0.0008/call cheaper −83% Qwen Plus 0728 (thinking)Mid · 1M ctx · below min tier $372 $0.0008/call cheaper −83% Llama 3.2 11B Vision InstructMid · 131K ctx · below min tier $376 $0.0008/call cheaper −83% Qwen3 VL 30B A3B ThinkingMid · 131K ctx · below min tier $386 $0.0009/call cheaper −83% P Perceptron Mk1Mid · 32K ctx · below min tier $394 $0.0009/call cheaper −82% Qwen2.5 72B InstructMid · 32K ctx · below min tier $399 $0.0009/call cheaper −82% Mistral Small 3.1 24BMid · 128K ctx · below min tier $417 $0.0009/call cheaper −81% N Llama 3.3 Nemotron Super 49B V1.5Mid · 131K ctx · below min tier $436 $0.0010/call cheaper −80% Llama 3.1 70B InstructMid · 131K ctx · below min tier $436 $0.0010/call cheaper −80% T UnslopNemo 12BMid · 32K ctx · below min tier $436 $0.0010/call cheaper −80% GPT-5.1-Codex-MiniMid · 400K ctx · below min tier $444 $0.0010/call cheaper −80% GPT-5 MiniMid · 400K ctx · below min tier $444 $0.0010/call cheaper −80% Qwen3.5-27BMid · 262K ctx · below min tier $446 $0.0010/call cheaper −80% Llama Guard 3 8BMid · 131K ctx · below min tier $449 $0.0010/call cheaper −80% Mistral Large 3 2512Mid · 262K ctx · below min tier $460 $0.0010/call cheaper −79% GPT-4.1 MiniSmall · 1M ctx · below min tier $471 $0.0010/call cheaper −79% T Skyfall 36B V2Mid · 32K ctx · below min tier $472 $0.0010/call cheaper −79% Z GLM 4.7Mid · 202K ctx · below min tier $485 $0.0011/call cheaper −78% Z GLM 4.6Mid · 202K ctx · below min tier $494 $0.0011/call cheaper −78% Mistral Medium 3.1Mid · 131K ctx · below min tier $505 $0.0011/call cheaper −77% Devstral 2 2512Mid · 262K ctx · below min tier $505 $0.0011/call cheaper −77% Mistral Medium 3Mid · 131K ctx · below min tier $505 $0.0011/call cheaper −77% Qwen3.5 Plus 2026-02-15Mid · 1M ctx · below min tier $505 $0.0011/call cheaper −77% Qwen3 Coder 480B A35BMid · 262K ctx · below min tier $510 $0.0011/call cheaper −77% U ReMM SLERP 13BMid · 6K ctx · below min tier $524 $0.0012/call cheaper −76% Nano Banana (Gemini 2.5 Flash Image)Mid · 32K ctx · below min tier $550 $0.0012/call cheaper −75% Gemini 2.5 FlashMid · 1M ctx · below min tier $550 $0.0012/call cheaper −75% B Seed-2.0-LiteMid · 262K ctx · below min tier $572 $0.0013/call cheaper −74% B Seed 1.6Mid · 262K ctx · below min tier $572 $0.0013/call cheaper −74% Qwen3 MaxFrontier · 256K ctx $575 $0.0013/call cheaper −74% Z GLM 4.5VMid · 65K ctx · below min tier $581 $0.0013/call cheaper −74% Qwen3.5 Plus 2026-04-20Mid · 1M ctx · below min tier $583 $0.0013/call cheaper −74% Qwen3.5-122B-A10BMid · 262K ctx · below min tier $594 $0.0013/call cheaper −73% Llama 3 70B InstructMid · 8K ctx · below min tier $595 $0.0013/call cheaper −73% A Coder LargeMid · 32K ctx · below min tier $596 $0.0013/call cheaper −73% B ERNIE 4.5 VL 424B A47BMid · 123K ctx · below min tier $599 $0.0013/call cheaper −73% Z GLM 5Mid · 202K ctx · below min tier $607 $0.0013/call cheaper −73% N Nemotron 3 UltraMid · 262K ctx · below min tier $608 $0.0014/call cheaper −73% Qwen3.6 PlusMid · 1M ctx · below min tier $632 $0.0014/call cheaper −72% Z GLM 4.5Mid · 131K ctx · below min tier $649 $0.0014/call cheaper −71% A Aion-2.0Mid · 131K ctx · below min tier $668 $0.0015/call cheaper −70% M WizardLM-2 8x22BMid · 65K ctx · below min tier $675 $0.0015/call cheaper −70% Qwen2.5 VL 72B InstructMid · 128K ctx · below min tier $679 $0.0015/call cheaper −69% Qwen3 VL 235B A22B ThinkingMid · 131K ctx · below min tier $683 $0.0015/call cheaper −69% A Nova 2 LiteMid · 1M ctx · below min tier $703 $0.0016/call cheaper −68% Gemma 2 27BMid · 8K ctx · below min tier $708 $0.0016/call cheaper −68% GPT-3.5 TurboMid · 16K ctx · below min tier $716 $0.0016/call cheaper −68% Mistral Large 3Frontier · 262K ctx $716 $0.0016/call cheaper −68% Gemini 3 Flash PreviewMid · 1.05M ctx · below min tier $717 $0.0016/call cheaper −68% Gemini 3 FlashMid · 1M ctx · below min tier $717 $0.0016/call cheaper −68% S Llama 3.3 Euryale 70BMid · 131K ctx · below min tier $725 $0.0016/call cheaper −67% Qwen3 235B A22BMid · 131K ctx · below min tier $729 $0.0016/call cheaper −67% R1 0528Mid · 163K ctx · below min tier $742 $0.0016/call cheaper −67% M MiniMax M1Mid · 1M ctx · below min tier $743 $0.0017/call cheaper −67% N Hermes 3 70B InstructMid · 131K ctx · below min tier $762 $0.0017/call cheaper −66% Qwen3.5 397B A17BMid · 131K ctx · below min tier $772 $0.0017/call cheaper −65% Qwen2.5 Coder 32B InstructMid · 32K ctx · below min tier $777 $0.0017/call cheaper −65% Kimi K2.5Frontier · 256K ctx $780 $0.0017/call cheaper −65% Grok Build 0.1Mid · 256K ctx · below min tier $806 $0.0018/call cheaper −64% Qwen3.6 27BMid · 262K ctx · below min tier $807 $0.0018/call cheaper −64% Kimi K2.7 CodeMid · 262K ctx · below min tier $813 $0.0018/call cheaper −63% Qwen3 Coder PlusMid · 1M ctx · below min tier $858 $0.0019/call cheaper −61% M Weaver (alpha)Mid · 8K ctx · below min tier $860 $0.0019/call cheaper −61% R1 Distill Llama 70BMid · 8K ctx · below min tier $871 $0.0019/call cheaper −61% A Aion-1.0-MiniMid · 131K ctx · below min tier $882 $0.0020/call cheaper −60% A Virtuoso LargeMid · 131K ctx · below min tier $894 $0.0020/call cheaper −60% Kimi K2 0711Mid · 131K ctx · below min tier $917 $0.0020/call cheaper −59% S Llama 3.1 Euryale 70B v2.2Mid · 131K ctx · below min tier $926 $0.0021/call cheaper −58% M Morph V3 FastMid · 81K ctx · below min tier $940 $0.0021/call cheaper −58% GPT Audio MiniMid · 128K ctx · below min tier $961 $0.0021/call cheaper −57% Nano Banana 2 (Gemini 3.1 Flash Image Preview)Mid · 131K ctx · below min tier $972 $0.0022/call cheaper −56% Nano Banana 2 (Gemini 3.1 Flash Image)Mid · 65K ctx · below min tier $972 $0.0022/call cheaper −56% Kimi K2 ThinkingMid · 262K ctx · below min tier $978 $0.0022/call cheaper −56% Kimi K2 0905Mid · 262K ctx · below min tier $978 $0.0022/call cheaper −56% Grok 4.20 Multi-AgentMid · 2M ctx · below min tier $980 $0.0022/call cheaper −56% Grok 4.3Frontier · 1M ctx $980 $0.0022/call cheaper −56% Grok 4.20Frontier · 2M ctx $980 $0.0022/call cheaper −56% R Relace Apply 3Mid · 256K ctx · below min tier $994 $0.0022/call cheaper −55% A Aion-RP 1.0 (8B)Mid · 32K ctx · below min tier $1,008 $0.0022/call cheaper −55% R1Mid · 64K ctx · below min tier $1,070 $0.0024/call cheaper −52% GPT-5.4 MiniMid · 400K ctx · below min tier $1,075 $0.0024/call cheaper −52% N Hermes 3 405B InstructMid · 131K ctx · below min tier $1,089 $0.0024/call cheaper −51% P SonarMid · 127K ctx · below min tier $1,089 $0.0024/call cheaper −51% Kimi K2.6Frontier · 256K ctx $1,108 $0.0025/call cheaper −50% Z GLM 5.1Mid · 202K ctx · below min tier $1,148 $0.0026/call cheaper −48% M Morph V3 LargeMid · 262K ctx · below min tier $1,151 $0.0026/call cheaper −48% Z GLM 5.2Mid · 1.05M ctx · below min tier $1,236 $0.0027/call cheaper −44% Z GLM 5 TurboMid · 262K ctx · below min tier $1,241 $0.0028/call cheaper −44% GPT-3.5 Turbo (older v0613)Mid · 4K ctx · below min tier $1,260 $0.0028/call cheaper −43% Claude Haiku 4.5Small · 200K ctx · below min tier $1,263 $0.0028/call cheaper −43% A Nova Pro 1.0Mid · 300K ctx · below min tier $1,282 $0.0028/call cheaper −42% o4 Mini HighMid · 200K ctx · below min tier $1,294 $0.0029/call cheaper −42% o4-miniSmall · 200K ctx · below min tier $1,294 $0.0029/call cheaper −42% D Cogito v2.1 671BMid · 128K ctx · below min tier $1,361 $0.0030/call cheaper −39% GPT-5 Image MiniMid · 400K ctx · below min tier $1,361 $0.0030/call cheaper −39% S Switchpoint RouterMid · 131K ctx · below min tier $1,362 $0.0030/call cheaper −39% Qwen3 Max ThinkingMid · 262K ctx · below min tier $1,383 $0.0031/call cheaper −38% N Hermes 4 405BMid · 131K ctx · below min tier $1,431 $0.0032/call cheaper −36% R Relace SearchMid · 256K ctx · below min tier $1,431 $0.0032/call cheaper −36% o3 Mini HighMid · 200K ctx · below min tier $1,450 $0.0032/call cheaper −35% W Palmyra X5Mid · 1.04M ctx · below min tier $1,577 $0.0035/call cheaper −29% GPT-3.5 Turbo InstructMid · 4K ctx · below min tier $1,719 $0.0038/call cheaper −23% Mistral Large 2407Mid · 131K ctx · below min tier $1,841 $0.0041/call cheaper −17% Mixtral 8x22B InstructMid · 65K ctx · below min tier $1,841 $0.0041/call cheaper −17% Qwen3.6 Max PreviewMid · 262K ctx · below min tier $2,022 $0.0045/call cheaper −9% Gemini 3.5 FlashMid · 1M ctx · below min tier $2,151 $0.0048/call cheaper −3% Gemini 2.5 Pro Preview 06-05Mid · 1.05M ctx · below min tier $2,220 $0.0049/call Gemini 2.5 Pro Preview 05-06Mid · 1.05M ctx · below min tier $2,220 $0.0049/call GPT-5 CodexMid · 400K ctx · below min tier $2,220 $0.0049/call GPT-5.1-Codex-MaxMid · 400K ctx · below min tier $2,220 $0.0049/call GPT-5 ChatMid · 128K ctx · below min tier $2,220 $0.0049/call Gemini 2.5 ProFrontier · 1M ctx $2,220 $0.0049/call GPT-5Frontier · 1M ctx · baseline $2,220 $0.0049/call GPT-5.1-CodexMid · 400K ctx · below min tier $2,222 $0.0049/call GPT-5.1Mid · 400K ctx · below min tier $2,222 $0.0049/call GPT-5.1 ChatMid · 128K ctx · below min tier $2,222 $0.0049/call o3Frontier · 200K ctx $2,354 $0.0052/call dearer +6% o4 Mini Deep ResearchMid · 200K ctx · below min tier $2,354 $0.0052/call dearer +6% GPT-4.1Mid · 1M ctx · below min tier $2,354 $0.0052/call dearer +6% Mistral Medium 3.5Mid · 128K ctx · below min tier $2,660 $0.0059/call dearer +20% Gemini 3 ProFrontier · 1M ctx $2,867 $0.0064/call dearer +29% Nano Banana Pro (Gemini 3 Pro Image Preview)Mid · 65K ctx · below min tier $2,867 $0.0064/call dearer +29% Gemini 3.1 Pro PreviewMid · 1.05M ctx · below min tier $2,867 $0.0064/call dearer +29% Gemini 3.1 Pro Preview Custom ToolsMid · 1.05M ctx · below min tier $2,867 $0.0064/call dearer +29% Gemini 3.1 ProFrontier · 1M ctx $2,867 $0.0064/call dearer +29% Nano Banana Pro (Gemini 3 Pro Image)Mid · 65K ctx · below min tier $2,867 $0.0064/call dearer +29% GPT-5.3-CodexMid · 400K ctx · below min tier $3,107 $0.0069/call dearer +40% GPT-5.3 ChatMid · 128K ctx · below min tier $3,107 $0.0069/call dearer +40% GPT-5.2-CodexMid · 400K ctx · below min tier $3,107 $0.0069/call dearer +40% GPT-5.2 ChatMid · 128K ctx · below min tier $3,107 $0.0069/call dearer +40% GPT-5.2Mid · 400K ctx · below min tier $3,107 $0.0069/call dearer +40% A Jamba Large 1.7Mid · 256K ctx · below min tier $3,204 $0.0071/call dearer +44% P Sonar Reasoning ProMid · 128K ctx · below min tier $3,204 $0.0071/call dearer +44% P Sonar Deep ResearchMid · 128K ctx · below min tier $3,204 $0.0071/call dearer +44% S Llama 3.1 70B Hanami x1Mid · 16K ctx · below min tier $3,267 $0.0073/call dearer +47% GPT-4o (2024-11-20)Mid · 128K ctx · below min tier $3,296 $0.0073/call dearer +49% GPT-4o (2024-08-06)Mid · 128K ctx · below min tier $3,296 $0.0073/call dearer +49% A Nova Premier 1.0Mid · 1M ctx · below min tier $3,369 $0.0075/call dearer +52% GPT-3.5 Turbo 16kMid · 16K ctx · below min tier $3,438 $0.0076/call dearer +55% Qwen 3.7 MaxFrontier · 1M ctx $3,577 $0.0080/call dearer +61% GPT-5.4Mid · 1.05M ctx · below min tier $3,584 $0.0080/call dearer +61% A Magnum v4 72BMid · 16K ctx · below min tier $3,609 $0.0080/call dearer +63% Claude Sonnet 4.6Mid · 1M ctx · below min tier $3,788 $0.0084/call dearer +71% Claude Sonnet 4.5Mid · 1M ctx · below min tier $3,788 $0.0084/call dearer +71% C Command R PlusFrontier · 128K ctx $4,005 $0.0089/call dearer +80% C Command R+ (08-2024)Mid · 128K ctx · below min tier $4,005 $0.0089/call dearer +80% I Inflection 3 PiMid · 8K ctx · below min tier $4,005 $0.0089/call dearer +80% I Inflection 3 ProductivityMid · 8K ctx · below min tier $4,005 $0.0089/call dearer +80% GPT AudioMid · 128K ctx · below min tier $4,005 $0.0089/call dearer +80% GPT-4o Search PreviewMid · 128K ctx · below min tier $4,005 $0.0089/call dearer +80% C Command AMid · 256K ctx · below min tier $4,005 $0.0089/call dearer +80% A Aion-1.0Mid · 131K ctx · below min tier $5,040 $0.011/call dearer +127% P Sonar ProMid · 200K ctx · below min tier $5,319 $0.012/call dearer +140% P Sonar Pro SearchMid · 200K ctx · below min tier $5,319 $0.012/call dearer +140% GPT-5 ImageMid · 400K ctx · below min tier $5,929 $0.013/call dearer +167% Claude Opus 4.8Frontier · 1M ctx $6,314 $0.014/call dearer +184% Claude Opus 4.7Frontier · 1M ctx $6,314 $0.014/call dearer +184% Claude Opus 4.6Frontier · 1M ctx $6,314 $0.014/call dearer +184% Claude Opus 4.5Frontier · 200K ctx $6,314 $0.014/call dearer +184% GPT-5.4 Image 2Mid · 272K ctx · below min tier $6,507 $0.014/call dearer +193% GPT-4o (2024-05-13)Mid · 128K ctx · below min tier $7,155 $0.016/call dearer +222% GPT-5.5Frontier · 1M ctx $7,169 $0.016/call dearer +223% o3 Deep ResearchMid · 200K ctx · below min tier $11,768 $0.026/call dearer +430% Claude Fable 5Frontier · 1M ctx $12,627 $0.028/call dearer +469% GPT-4 Turbo PreviewMid · 128K ctx · below min tier $14,310 $0.032/call dearer +545% o3-proFrontier · 200K ctx $32,040 $0.071/call dearer +1343% o3 ProMid · 200K ctx · below min tier $32,040 $0.071/call dearer +1343% GPT-5 ProMid · 400K ctx · below min tier $34,290 $0.076/call dearer +1445% GPT-5.2 ProMid · 400K ctx · below min tier $48,006 $0.107/call dearer +2063% GPT-5.4 ProMid · 1.05M ctx · below min tier $58,320 $0.130/call dearer +2527% GPT-5.5 ProFrontier · 1M ctx $58,320 $0.130/call dearer +2527% o1-proMid · 200K ctx · below min tier $240,300 $0.534/call dearer +10726%

Where the money goes

DeepSeek R1 · $186/mo
Input 61% $114/mo Output 39% $71.82/mo
Prompt caching at 70% saves $143/mo on input.

This workload, priced through history

cheapest model that fit, on each date
Apr 2024$5,319
97%
today$186
See what drove the drops

Cut it further

contextual levers for this workload
Cache the context

You reuse 1.8K context tokens each call. Cached input bills up to 90% cheaper.

≈ $51.03/mo at 95% hit
Route by difficulty

Send easy calls to a small model and reserve a frontier model for the hard ones. A 70/30 split often halves spend.

Use the Batch API

Non-urgent jobs (eval, backfill, summarization) run ~50% cheaper on async batch endpoints.

≈ −50% on batchable volume
Read the cost-cutting playbook

Assumptions

  • Prices are USD per 1M tokens, at current list rates.
  • Dimensions priced: input, output, and cached input where offered.
  • Cache hit rate applies to your system / reused tokens only.
  • Excludes batch discounts, free tiers, image/audio, and rate-limit effects.
  • “Cheapest equivalent” respects your context-window and minimum-capability constraints.
A cost comparison, not a quality verdict. A cheaper model can change output quality; validate any switch with your own eval before moving production traffic.
Always-current, history-backed list prices — nothing you enter leaves your browser.
Permalink encodes this exact workload
Coming soon · the measure product

Measure your real usage

Paste a production trace or connect your provider data and get your exact cost per call — then the same cheapest-equivalent recommendation, on the calls you actually ship.

Paste a trace Connect your data Exact cost & savings

No spam — one note when it ships. This is the separate measure product, not part of the estimator.

Alert me when this estimate changes

Get an email when a price change shifts this bill — we'll name the model and the new number.