LLMDB.APP COST MATRIX

AI Model API Pricing & Token Cost Reference

Compare token-level API input/output pricing, context window boundaries, and estimated query costs across OpenAI, Anthropic, Google, DeepSeek, and Meta models.

Agent Cost Projection Calculator

Estimate monthly costs accounting for loop intensity, reasoning overhead, and prompt caching discounts.

Input: 30%Output: 70%
Estimated Monthly Costs (Top 3 Most Economical)
1. Auto Router (Beta)
$0.00/mo
2. Fusion
$0.00/mo
3. Pareto Code Router
$0.00/mo
Context Window Alerts
warningFree Models Router — input exceeds 10× context window (200k). Consider a model with larger context or lower per-request volume.
warningBody Builder (beta) — input exceeds 10× context window (128k). Consider a model with larger context or lower per-request volume.
warningMistral Nemo — input exceeds 10× context window (131.072k). Consider a model with larger context or lower per-request volume.
warningLlama 3.1 8B — input exceeds 10× context window (131.072k). Consider a model with larger context or lower per-request volume.
warningLing 3.0 Flash — input exceeds 10× context window (262.144k). Consider a model with larger context or lower per-request volume.

Full Pricing Reference

Click headers to sort. All prices in USD per million tokens.

Model Provider DeployTierContext Input $/MTok Output $/MTok Agent Score Calc CostConfig
Auto Router (Beta)OpenRouterAPIReasoning2,000k$0.00$0.00$0.00
FusionOpenRouterAPIReasoning1,000k$0.00$0.00$0.00
Pareto Code RouterOpenRouterAPIReasoning2,000k$0.00$0.00$0.00
Lyria 3 Clip PreviewGoogleAPIReasoning1,048.576k$0.00$0.00$0.00
Lyria 3 Pro PreviewGoogleAPIReasoning1,048.576k$0.00$0.00$0.00
Free Models RouterOpenRouterAPIReasoning200k$0.00$0.00$0.00
Body Builder (beta)OpenRouterAPIReasoning128k$0.00$0.00$0.00
Auto RouterOpenRouterAPIReasoning2,000k$0.00$0.00$0.00
Granite 4.0 MicroIBMAPIReasoning131k$0.02$0.11$0.84
Mistral NemoMistralOpenReasoning131.072k$0.02$0.03$0.27
Ling 3.0 FlashInclusion AIAPIReasoning262.144k$0.02$0.06$0.50
Nex-N2-MiniNex AGIAPIReasoning262.144k$0.03$0.10$0.78
Llama 3.2 1B InstructMetaOpenReasoning60k$0.03$0.20$1.49
Qwen3.7 FlashAlibabaOpenReasoning1,000k$0.03$0.13$1.00
gpt-oss-20bOpenAIAPIReasoning131.072k$0.03$0.13$1.00
Nova Micro 1.0AmazonAPIReasoning128k$0.04$0.14$1.09
Command R7B (12-2024)CohereAPIReasoning128k$0.04$0.15$1.16
Mercury 2.5Inception AIAPIReasoning260k$0.04$0.15$1.17
Mercury 2.5 PreviewInception AIAPIReasoning260k$0.04$0.15$1.17
DeepSeek V4 Flash 0731DeepSeekOpenReasoning1,310.72k$0.04$0.32$2.36
Llama 3.1 8BMetaOpenReasoning131.072k$0.04$0.0474/100$0.40
Hy-MT2-1.8BTencentAPIReasoning8.192k$0.04$0.18$1.37
Qwen3 30B A3B Instruct 2507AlibabaOpenReasoning262.144k$0.05$0.19$1.50
Granite 4.1 8BIBMAPIReasoning131.072k$0.05$0.10$0.85
Nemotron 3 Nano 30B A3BNvidiaAPIReasoning262.144k$0.05$0.20$1.55
GPT-5 NanoOpenAIAPIReasoning400k$0.05$0.40$2.95
Gemma 3 12BGoogleAPIReasoning131.072k$0.05$0.15$1.20
Gemma 3 4BGoogleAPIReasoning131.072k$0.05$0.10$0.85
Llama 3.2 3B InstructMetaOpenReasoning131.072k$0.05$0.33$2.46
Llama 3.1 8B InstructMetaOpenReasoning131.072k$0.05$0.08$0.71
DeepSeek V4 Flash 0423DeepSeekOpenReasoning1,048.576k$0.06$0.11$0.94
DeepSeek V4 FlashDeepSeekAPIReasoning1,048.576k$0.06$0.1186/100$0.94
Ling 3.0 Flash VLInclusion AIAPIReasoning131.072k$0.06$0.18$1.44
Granite 4.2 8BIBMAPIReasoning131.072k$0.06$0.25$1.93
Ling 3.0 Flash FinInclusion AIAPIReasoning262.144k$0.06$0.18$1.44
Laguna XS 2.1PoolsideAPIReasoning262.144k$0.06$0.12$1.02
Gemma 3n 4BGoogleAPIReasoning32.768k$0.06$0.12$1.02
Nova Lite 1.0AmazonAPIReasoning300k$0.06$0.24$1.86
GLM 4.7 FlashZhipu AIAPIReasoning200k$0.06$0.40$2.98
Qwen3.5-FlashAlibabaOpenReasoning1,000k$0.07$0.26$2.02
Nemotron 3.5 LightningNvidiaAPIReasoning262.144k$0.07$0.20$1.61
Qwen3 Coder 30B A3B InstructAlibabaOpenReasoning262.144k$0.07$0.28$2.17
Phi 4MicrosoftAPIReasoning16.384k$0.07$0.14$1.19
Hy-MT2-30B-A3BTencentAPIReasoning8.192k$0.07$0.29$2.29
Hy-MT2-7BTencentAPIReasoning8.192k$0.07$0.29$2.29
GLM Flash LatestZhipu AIAPIReasoning1,310.72k$0.07$0.25$1.98
GLM 5.3 FlashZhipu AIAPIReasoning1,310.72k$0.07$0.25$1.98
Seed 1.6 FlashByteDanceAPIReasoning262.144k$0.07$0.30$2.33
gpt-oss-safeguard-20bOpenAIAPIReasoning131.072k$0.07$0.30$2.33
Nemotron 3 SuperNvidiaAPIReasoning262.144k$0.08$0.45$3.39
Qwen3 32BAlibabaOpenReasoning131.072k$0.08$0.28$2.20
Gemma 3 27BGoogleAPIReasoning131.072k$0.08$0.45$3.39
Hy3TencentAPIReasoning262.144k$0.08$0.33$2.56
Qwen3 235B A22B Instruct 2507AlibabaOpenReasoning262.144k$0.09$0.35$2.71
Solar Pro 4UpstageAPIReasoning524.288k$0.09$0.36$2.79
Laguna S 2.1PoolsideAPIReasoning1,048.576k$0.09$0.18$1.53
Gemma 4 26B A4BGoogleAPIReasoning262.144k$0.09$0.30$2.37
Gemma 4 31BGoogleAPIReasoning262.144k$0.09$0.34$2.65
Qwen3 Next 80B A3B InstructAlibabaOpenReasoning262.144k$0.09$1.10$7.97
Mistral Small 3.2 24BMistralOpenReasoning256k$0.09$0.25$2.03
Mistral Small 3MistralAPIReasoning32.768k$0.09$0.2584/100$2.03
Muse Spark 1.3 ContributorMetaAPIReasoning1,048.576k$0.10$0.20$1.70
Muse Spark 1.2 ContributorMetaAPIReasoning1,048.576k$0.10$0.20$1.70
Reka EdgeReka AIAPIReasoning16.384k$0.10$0.10$1.00
Qwen3.5-9BAlibabaOpenReasoning262.144k$0.10$0.15$1.35
Seed-2.0-MiniByteDanceAPIReasoning262.144k$0.10$0.40$3.10
Step 3.5 FlashStepFunAPIReasoning262.144k$0.10$0.30$2.40
Ministral 3 3B 2512MistralOpenReasoning131.072k$0.10$0.10$1.00
Voxtral Small 24B 2507MistralOpenReasoning32.768k$0.10$0.30$2.40
Gemini 2.5 Flash Lite Preview 09-2025GoogleAPIReasoning1,048.576k$0.10$0.40$3.10
UI-TARS 7BByteDanceAPIReasoning128k$0.10$0.20$1.70
Gemini 2.5 Flash LiteGoogleAPIReasoning1,048.576k$0.10$0.40$3.10
GPT-4.1 NanoOpenAIAPIReasoning1,047.576k$0.10$0.40$3.10
Llama 4 ScoutMetaOpenReasoning1,310.72k$0.10$0.3082/100$2.40
Reka Flash 3Reka AIAPIReasoning65.536k$0.10$0.20$1.70
Gemini 2.0 FlashGoogleAPIReasoning1,048.576k$0.10$0.4080/100$3.10
Llama 3.3 70B InstructMetaOpenReasoning131.072k$0.10$0.32$2.54
Llama 3.3 70B InstructMetaOpenReasoning131.072k$0.10$0.3283/100$2.54
Qwen2.5 7B InstructAlibabaOpenReasoning32.768k$0.10$0.20$1.70
Qwen3 VL 32B InstructAlibabaOpenReasoning131.072k$0.10$0.42$3.22
Ministral 8BMistralOpenReasoning128k$0.11$0.11$1.10
Qwen3 VL 8B InstructAlibabaOpenReasoning262.144k$0.12$0.46$3.54
Qwen3 8BAlibabaOpenReasoning131.072k$0.12$0.46$3.54
Qwen3 Coder NextAlibabaOpenReasoning262.144k$0.12$0.80$5.96
Qwen3 14BAlibabaOpenReasoning131.072k$0.12$0.24$2.04
Qwen3 30B A3BAlibabaOpenReasoning131.072k$0.12$0.50$3.86
Qwen3 VL 30B A3B InstructAlibabaOpenReasoning262.144k$0.13$0.52$4.03
Hermes 4 70BNous ResearchAPIReasoning131.072k$0.13$0.40$3.19
GLM 4.5 AirZhipu AIAPIReasoning131.072k$0.13$0.85$6.34
MiMo-V2.5XiaomiAPIReasoning1,050k$0.14$0.28$2.38
Hunyuan A13B InstructTencentAPIReasoning131.072k$0.14$0.57$4.41
Llama 3 8B InstructMetaOpenReasoning8.192k$0.14$0.14$1.40
DeepSeek V4.1 FlashDeepSeekOpenReasoning1,048.576k$0.15$0.60$4.65
Qwen3.8 FlashAlibabaOpenReasoning1,000k$0.15$0.47$3.74
KAT-Coder-Air V2.5KuaishouAPIReasoning256k$0.15$0.60$4.65
Qwen3.6 35B A3BAlibabaOpenReasoning262.144k$0.15$1.00$7.45
Mistral Small 4MistralOpenReasoning262.144k$0.15$0.60$4.65
Solar Pro 3UpstageAPIReasoning131.072k$0.15$0.60$4.65
Ministral 3 8B 2512MistralOpenReasoning262.144k$0.15$0.15$1.50
Yi-Lightning01.AIAPIReasoning131.072k$0.15$0.3082/100$2.55
Qwen3 Next 80B A3B ThinkingAlibabaOpenReasoning262.144k$0.15$1.20$8.85
gpt-oss-120bOpenAIAPIReasoning131.072k$0.15$0.60$4.65
GPT-4o-mini Search PreviewOpenAIAPIReasoning128k$0.15$0.60$4.65
Command R (08-2024)CohereAPIReasoning128k$0.15$0.60$4.65
GPT-4o-mini (2024-07-18)OpenAIAPIReasoning128k$0.15$0.60$4.65
GPT-4o-miniOpenAIAPIReasoning128k$0.15$0.6082/100$4.65
Command RCohereAPIReasoning128k$0.15$0.6078/100$4.65
Hy3 previewTencentAPIReasoning262.144k$0.18$0.60$4.74
Qwen3 VL 8B ThinkingAlibabaOpenReasoning131.072k$0.18$2.10$15.24
Llama Guard 4 12BMetaOpenReasoning163.84k$0.18$0.18$1.80
Qwen3.6 FlashAlibabaOpenReasoning1,000k$0.19$1.13$8.44
Qwen3.5-27BAlibabaOpenReasoning262.144k$0.20$1.56$11.50
Qwen3 Coder FlashAlibabaOpenReasoning1,000k$0.20$0.97$7.41
GPT-5.6 Luna ProOpenAIAPIReasoning1,050k$0.20$1.20$9.00
GPT-5.6 LunaOpenAIAPIReasoning1,050k$0.20$1.20$9.00
Nemotron 3.5 Content SafetyNvidiaAPIReasoning131.072k$0.20$0.20$2.00
Step 3.7 FlashStepFunAPIReasoning262.144k$0.20$1.15$8.65
Llama 4 MaverickMetaOpenReasoning1,048.576k$0.20$0.8089/100$6.20
Laguna M.1PoolsideAPIReasoning262.144k$0.20$0.40$3.40
GPT-5.4 NanoOpenAIAPIReasoning400k$0.20$1.25$9.35
Ministral 3 14B 2512MistralOpenReasoning262.144k$0.20$0.20$2.00
Qwen3 VL 30B A3B ThinkingAlibabaOpenReasoning262.144k$0.20$2.40$17.40
Qwen3 30B A3B Thinking 2507AlibabaOpenReasoning81.92k$0.20$2.40$17.40
Llama 4 MaverickMetaOpenReasoning1,048.576k$0.20$0.80$6.20
SabaMistralOpenReasoning32.768k$0.20$0.60$4.80
MiniMax-01MiniMaxAPIReasoning1,000.192k$0.20$1.10$8.30
Qwen3 VL 235B A22B InstructAlibabaOpenReasoning262.144k$0.21$1.90$13.93
DeepSeek V4 Flash Vision ExpDeepSeekOpenReasoning1,048.576k$0.22$0.66$5.28
Qwen3 235B A22B Thinking 2507AlibabaOpenReasoning131.072k$0.23$2.30$16.79
Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)GoogleAPIReasoning65.536k$0.25$1.50$11.25
Nex-N2-ProNex AGIAPIReasoning262.144k$0.25$1.00$7.75
Gemini 3.1 Flash LiteGoogleAPIReasoning1,048.576k$0.25$1.50$11.25
Gemini 3.1 FlashGoogleAPIReasoning1,000k$0.25$1.5086/100$11.25
Seed-2.0-LiteByteDanceAPIReasoning262.144k$0.25$2.00$14.75
Mercury 2Inception AIAPIReasoning128k$0.25$0.75$6.00
Gemini 3.1 Flash Lite PreviewGoogleAPIReasoning1,048.576k$0.25$1.50$11.25
Seed 1.6ByteDanceAPIReasoning262.144k$0.25$2.00$14.75
GPT-5.1-Codex-MiniOpenAIAPIReasoning400k$0.25$2.00$14.75
DeepSeek V3.1DeepSeekOpenReasoning163.84k$0.25$0.95$7.40
GPT-5 MiniOpenAIAPIReasoning400k$0.25$2.0085/100$14.75
DeepSeek V3 0324DeepSeekOpenReasoning163.84k$0.25$1.00$7.75
Claude 3 HaikuAnthropicAPIReasoning200k$0.25$1.25$9.50
MiniMax M2MiniMaxAPIReasoning204.8k$0.26$1.02$7.91
Qwen3.5-122B-A10BAlibabaOpenReasoning262.144k$0.26$2.08$15.34
Qwen3.5 Plus 2026-02-15AlibabaOpenReasoning1,000k$0.26$1.56$11.70
Qwen Plus 0728 (thinking)AlibabaOpenReasoning1,000k$0.26$0.78$6.24
Qwen Plus 0728AlibabaOpenReasoning1,000k$0.26$0.78$6.24
Qwen-PlusAlibabaOpenReasoning1,000k$0.26$0.78$6.24
DeepSeek V3.2DeepSeekOpenReasoning163.84k$0.27$0.40$3.61
MiniMax M2.5MiniMaxAPIReasoning204.8k$0.27$1.08$8.37
DeepSeek V3.2 ExpDeepSeekOpenReasoning163.84k$0.27$0.41$3.68
DeepSeek V3.1 TerminusDeepSeekOpenReasoning163.84k$0.27$1.00$7.81
Muse Glimmer 30BMetaAPIReasoning131.072k$0.30$1.20$9.30
Gemini 3.5 Flash LiteGoogleAPIReasoning1,048.576k$0.30$2.50$18.40
MiniMax M3MiniMaxAPIReasoning1,048.576k$0.30$1.20$9.30
Qwen3.6 27BAlibabaOpenReasoning262.144k$0.30$2.00$14.90
Qwen3.5 Plus 2026-04-20AlibabaOpenReasoning1,000k$0.30$1.80$13.50
KAT-Coder-Pro V2KuaishouAPIReasoning262.144k$0.30$1.20$9.30
MiniMax M2.7MiniMaxAPIReasoning204.8k$0.30$1.20$9.30
MiniMax M2-herMiniMaxAPIReasoning65.536k$0.30$1.20$9.30
MiniMax M2.1MiniMaxAPIReasoning204.8k$0.30$1.20$9.30
GLM 4.6VZhipu AIAPIReasoning131.072k$0.30$0.90$7.20
Nova 2 LiteAmazonAPIReasoning1,000k$0.30$2.50$18.40
Nano Banana (Gemini 2.5 Flash Image)GoogleAPIReasoning32.768k$0.30$2.50$18.40
Cydonia 24B V4.1The DrummerAPIReasoning131.072k$0.30$0.50$4.40
Codestral 2508MistralOpenReasoning256k$0.30$0.90$7.20
Qwen3 Coder 480B A35BAlibabaOpenReasoning262.144k$0.30$1.00$7.90
Gemini 2.5 FlashGoogleAPIReasoning1,048.576k$0.30$2.50$18.40
Qwen3.5-35B-A3BAlibabaOpenReasoning262.144k$0.31$1.25$9.69
Qwen3.7 PlusAlibabaOpenReasoning1,000k$0.32$1.28$9.92
DeepSeek V3DeepSeekOpenReasoning163.84k$0.32$0.89$7.19
Qwen3.6 PlusAlibabaOpenReasoning1,000k$0.33$1.95$14.63
Llama 3.2 11B Vision InstructMetaOpenReasoning131.072k$0.34$0.34$3.45
Llama 3.2 11B VisionMetaOpenReasoning131.072k$0.34$0.3472/100$3.45
Qwen 2.5-Coder 32BAlibabaOpenReasoning131.072k$0.35$0.7089/100$5.95
Mistral Small 3.1 24BMistralOpenReasoning128k$0.35$0.56$4.94
Qwen2.5 72B InstructAlibabaOpenReasoning32.768k$0.36$0.40$3.88
GLM 5.3 FlashXZhipu AIAPIReasoning1,048.576k$0.37$1.25$9.86
GLM 4.7Zhipu AIAPIReasoning204.8k$0.40$1.75$13.45
Devstral 2 2512MistralOpenReasoning262.144k$0.40$2.00$15.20
Qwen3 VL 235B A22B ThinkingAlibabaOpenReasoning131.072k$0.40$4.00$29.20
Qwen 2.5 72BAlibabaOpenReasoning131.072k$0.40$0.8088/100$6.80
Mistral Medium 3.1MistralOpenReasoning131.072k$0.40$2.00$15.20
MiniMax M1MiniMaxAPIReasoning1,000k$0.40$2.20$16.60
Mistral Medium 3MistralOpenReasoning131.072k$0.40$2.00$15.20
GPT-4.1 MiniOpenAIAPIReasoning1,047.576k$0.40$1.60$12.40
UnslopNemo 12BThe DrummerAPIReasoning1,024k$0.40$0.40$4.00
Llama 3.1 70B InstructMetaOpenReasoning131.072k$0.40$0.40$4.00
Qwen3.8 27BAlibabaOpenReasoning1,000k$0.42$3.00$22.26
ERNIE 4.5 VL 424B A47BBaiduAPIReasoning123k$0.42$1.25$10.01
GLM 4.6Zhipu AIAPIReasoning204.8k$0.43$1.75$13.54
MiMo-V2.5-ProXiaomiAPIReasoning1,050k$0.43$0.87$7.39
Inkling SmallThinking MachinesAPIReasoning1,048.576k$0.45$1.20$9.75
Kimi K2.5Moonshot AIAPIReasoning262.144k$0.45$2.25$17.10
Qwen3 235B A22BAlibabaOpenReasoning131.072k$0.46$1.82$14.11
Seed 2.1 TurboByteDanceAPIReasoning262.144k$0.50$2.50$19.00
Seed-2.0-CodeByteDanceAPIReasoning262.144k$0.50$3.00$22.50
Nano Banana 2 (Gemini 3.1 Flash Image)GoogleAPIReasoning131.072k$0.50$3.00$22.50
Nano Banana 2 (Gemini 3.1 Flash Image Preview)GoogleAPIReasoning65.536k$0.50$3.00$22.50
Gemini 3 Flash PreviewGoogleAPIReasoning1,048.576k$0.50$3.00$22.50
Mistral Large 3 2512MistralOpenReasoning262.144k$0.50$1.50$12.00
R1 0528DeepSeekOpenReasoning163.84k$0.50$2.15$16.55
Mixtral 8x22BMistralOpenReasoning65.536k$0.50$1.0087/100$8.50
Mistral Large 3MistralAPIReasoning262.144k$0.50$1.5091/100$12.00
GPT-3.5 TurboOpenAIAPIReasoning16.385k$0.50$1.50$12.00
Qwen3.5 397B A17BAlibabaOpenReasoning262.144k$0.55$3.50$26.15
Skyfall 36B V2The DrummerAPIReasoning32.768k$0.55$0.80$7.25
Kimi K2 0711Moonshot AIAPIReasoning131.072k$0.57$2.30$17.81
Nemotron 3 UltraNvidiaAPIReasoning262.144k$0.60$2.40$18.60
GLM 5Zhipu AIAPIReasoning204.8k$0.60$1.92$15.24
Palmyra X5WriterAPIReasoning1,040k$0.60$6.00$43.80
GPT Audio MiniOpenAIAPIReasoning128k$0.60$2.40$18.60
Kimi K2 ThinkingMoonshot AIAPIReasoning262.144k$0.60$2.50$19.30
Hunyuan ProTencentAPIReasoning256k$0.60$1.2085/100$10.20
Kimi K2 0905Moonshot AIAPIReasoning262.144k$0.60$2.50$19.30
GLM 4.5VZhipu AIAPIReasoning65.536k$0.60$1.80$14.40
GLM 4.5Zhipu AIAPIReasoning131.072k$0.60$2.20$17.20
Mistral Large 2MistralAPIReasoning1,048.576k$0.60$1.8093/100$14.40
WizardLM-2 8x22BMicrosoftAPIReasoning65.535k$0.62$0.62$6.20
GLM 5.2Zhipu AIAPIReasoning1,048.576k$0.65$2.04$16.24
Qwen3 Coder PlusAlibabaOpenReasoning1,000k$0.65$3.25$24.70
Gemma 2 27BGoogleAPIReasoning8.192k$0.65$0.65$6.50
DeepSeek V4 Pro 0813DeepSeekOpenReasoning1,048.576k$0.66$1.98$15.84
Qwen2.5 Coder 32B InstructAlibabaOpenReasoning32.768k$0.66$1.00$8.98
R1DeepSeekOpenReasoning64k$0.70$2.50$19.60
DeepSeek R1DeepSeekAPIReasoning163.84k$0.70$2.5078/100$19.60
Hermes 3 70B InstructNous ResearchOpenReasoning131.072k$0.70$0.70$7.00
Kimi K2.7 CodeMoonshot AIAPIReasoning262.144k$0.71$3.21$24.59
KAT-Coder-Pro V2.5KuaishouAPIReasoning262.144k$0.74$2.96$22.94
Gemini 3.8 FlashGoogleAPIReasoning1,048.576k$0.75$3.75$28.50
Gemini 3.7 FlashGoogleAPIReasoning1,048.576k$0.75$3.75$28.50
Gemini 3.6 FlashGoogleAPIReasoning1,048.576k$0.75$3.75$28.50
Gemini Flash LatestGoogleAPIReasoning1,048.576k$0.75$3.75$28.50
Google Gemini Flash LatestGoogleAPIReasoning1,048.576k$0.75$3.75$28.50
GPT-5.4 MiniOpenAIAPIReasoning400k$0.75$4.50$33.75
GLM LatestZhipu AIAPIReasoning1,310.72k$0.77$2.43$19.32
Qwen3 Max ThinkingAlibabaOpenReasoning262.144k$0.78$3.90$29.64
Qwen3 MaxAlibabaOpenReasoning262.144k$0.78$3.90$29.64
Doubao ProByteDanceAPIReasoning256k$0.80$1.6086/100$13.60
Morph V3 FastMorph AIAPIReasoning81.92k$0.80$1.20$10.80
Qwen2.5 VL 72B InstructAlibabaOpenReasoning128k$0.80$1.00$9.40
R1 Distill Llama 70BDeepSeekOpenReasoning8.192k$0.80$0.80$8.00
Nova Pro 1.0AmazonAPIReasoning300k$0.80$3.20$24.80
Llama 3.1 405BMetaOpenReasoning131.072k$0.80$0.8090/100$8.00
Hy4 previewTencentAPIReasoning1,048.576k$0.83$2.50$20.01
Morph V3 LargeMorph AIAPIReasoning262.144k$0.90$1.90$16.00
GLM 5.3Zhipu AIAPIReasoning1,310.72k$0.91$2.86$22.75
DeepSeek V4 Pro 0423DeepSeekOpenReasoning1,048.576k$0.92$1.85$15.69
DeepSeek V4 ProDeepSeekAPIReasoning1,048.576k$0.92$1.8594/100$15.69
Sakana NamazuSakana AIAPIReasoning262.144k$0.95$4.00$30.85
Kimi K2.6Moonshot AIAPIReasoning262.144k$0.95$4.00$30.85
GLM 5.1Zhipu AIAPIReasoning204.8k$0.97$3.04$24.15
InklingThinking MachinesAPIReasoning1,048.576k$1.00$4.05$31.35
Grok Build 0.1xAIAPIReasoning256k$1.00$2.00$17.00
Claude Haiku LatestAnthropicAPIReasoning200k$1.00$5.00$38.00
Anthropic Claude Haiku LatestAnthropicAPIReasoning200k$1.00$5.00$38.00
Claude Haiku 4.5AnthropicAPIReasoning200k$1.00$5.0087/100$38.00
Hermes 4 405BNous ResearchAPIReasoning131.072k$1.00$3.00$24.00
SonarPerplexityAPIReasoning127.072k$1.00$1.00$10.00
Hermes 3 405B InstructNous ResearchOpenReasoning131.072k$1.00$1.00$10.00
GPT-3.5 Turbo (older v0613)OpenAIAPIReasoning4.095k$1.00$2.00$17.00
Qwen3.6 Max PreviewAlibabaOpenReasoning262.144k$1.03$6.16$46.22
o4 MiniOpenAIAPIReasoning200k$1.10$4.40$34.10
o4 Mini HighOpenAIAPIReasoning200k$1.10$4.40$34.10
o3 Mini HighOpenAIAPIReasoning200k$1.10$4.40$34.10
o3 MiniOpenAIAPIReasoning200k$1.10$4.4091/100$34.10
GLM 5V TurboZhipu AIAPIReasoning202.752k$1.20$4.00$31.60
GLM 5 TurboZhipu AIAPIReasoning202.752k$1.20$4.00$31.60
ERNIE 4.0BaiduAPIReasoning128k$1.20$2.4087/100$20.40
Muse Spark 1.3MetaAPIReasoning1,048.576k$1.25$4.25$33.50
Muse Spark 1.2MetaAPIReasoning1,048.576k$1.25$4.25$33.50
Muse Spark 1.1MetaAPIReasoning1,048.576k$1.25$4.25$33.50
Grok 4.20xAIAPIReasoning2,000k$1.25$2.5090/100$21.25
Grok 4.3xAIAPIReasoning1,000k$1.25$2.5087/100$21.25
Grok 4.20 Multi-AgentxAIAPIReasoning2,000k$1.25$2.50$21.25
Grok 4.20xAIAPIReasoning2,000k$1.25$2.50$21.25
GPT-5.1-Codex-MaxOpenAIAPIReasoning400k$1.25$10.00$73.75
GPT-5.1OpenAIAPIReasoning400k$1.25$10.00$73.75
GPT-5.1 ChatOpenAIAPIReasoning128k$1.25$10.00$73.75
GPT-5.1-CodexOpenAIAPIReasoning400k$1.25$10.00$73.75
GPT-5 CodexOpenAIAPIReasoning400k$1.25$10.00$73.75
GPT-5 ChatOpenAIAPIReasoning128k$1.25$10.00$73.75
GPT-5OpenAIAPIReasoning400k$1.25$10.0092/100$73.75
Gemini 2.5 ProGoogleAPIReasoning1,048.576k$1.25$10.0090/100$73.75
Gemini 2.5 Pro Preview 06-05GoogleAPIReasoning1,048.576k$1.25$10.00$73.75
Gemini 2.5 Pro Preview 05-06GoogleAPIReasoning1,048.576k$1.25$10.00$73.75
Qwen3.7 MaxAlibabaOpenReasoning1,000k$1.48$4.42$35.40
Gemini 3.5 FlashGoogleAPIReasoning1,048.576k$1.50$9.0088/100$67.50
Mistral Medium 3.5MistralOpenReasoning262.144k$1.50$7.50$57.00
GPT-3.5 Turbo InstructOpenAIAPIReasoning4.095k$1.50$2.00$18.50
Grok 4.7xAIAPIReasoning500k$1.60$4.80$38.40
Kimi LatestMoonshot AIAPIReasoning1,048.576k$1.70$8.50$64.60
MoonshotAI Kimi LatestMoonshot AIAPIReasoning1,048.576k$1.70$8.50$64.60
GPT-5.3 ChatOpenAIAPIReasoning128k$1.75$14.00$103.25
GPT-5.3-CodexOpenAIAPIReasoning400k$1.75$14.00$103.25
GPT-5.2-CodexOpenAIAPIReasoning400k$1.75$14.00$103.25
GPT-5.2 ChatOpenAIAPIReasoning128k$1.75$14.00$103.25
GPT-5.2OpenAIAPIReasoning400k$1.75$14.00$103.25
Fugu MaxSakana AIAPIReasoning1,000k$2.00$6.00$48.00
Qwen3.8 Max (0902)AlibabaOpenReasoning1,000k$2.00$6.00$48.00
Qwen3.8 2.4T A95BAlibabaOpenReasoning1,048.576k$2.00$6.00$48.00
Grok 4.6xAIAPIReasoning500k$2.00$6.00$48.00
Qwen3.8 MaxAlibabaOpenReasoning1,000k$2.00$6.00$48.00
GPT-5.6 Sol ProOpenAIAPIReasoning1,050k$2.00$10.00$76.00
GPT-5.6 Terra ProOpenAIAPIReasoning1,050k$2.00$12.00$90.00
GPT-5.6 SolOpenAIAPIReasoning1,050k$2.00$10.00$76.00
GPT-5.6 TerraOpenAIAPIReasoning1,050k$2.00$12.00$90.00
Grok 4.5xAIAPIReasoning500k$2.00$6.00$48.00
Claude Sonnet 5AnthropicAPIReasoning1,000k$2.00$10.00$76.00
Nano Banana Pro (Gemini 3 Pro Image)GoogleAPIReasoning131.072k$2.00$12.00$90.00
Claude Sonnet LatestAnthropicAPIReasoning1,000k$2.00$10.00$76.00
Gemini Pro LatestGoogleAPIReasoning1,048.576k$2.00$12.00$90.00
Anthropic Claude Sonnet LatestAnthropicAPIReasoning1,000k$2.00$10.00$76.00
Google Gemini Pro LatestGoogleAPIReasoning1,048.576k$2.00$12.00$90.00
Gemini 3.1 ProGoogleAPIReasoning2,000k$2.00$12.0093/100$90.00
Gemini 3.1 Pro Preview Custom ToolsGoogleAPIReasoning1,048.576k$2.00$12.00$90.00
Gemini 3.1 Pro PreviewGoogleAPIReasoning1,048.576k$2.00$12.00$90.00
Nano Banana Pro (Gemini 3 Pro Image Preview)GoogleAPIReasoning65.536k$2.00$12.00$90.00
o4 Mini Deep ResearchOpenAIAPIReasoning200k$2.00$8.00$62.00
Jamba Large 1.7AI21 LabsAPIReasoning256k$2.00$8.00$62.00
o3OpenAIAPIReasoning200k$2.00$8.00$62.00
GPT-4.1OpenAIAPIReasoning1,047.576k$2.00$8.0091/100$62.00
Sonar Reasoning ProPerplexityAPIReasoning128k$2.00$8.00$62.00
Sonar Deep ResearchPerplexityAPIReasoning128k$2.00$8.00$62.00
Mistral Large 2407MistralOpenReasoning131.072k$2.00$6.00$48.00
Mixtral 8x22B InstructMistralOpenReasoning65.536k$2.00$6.00$48.00
Mistral LargeMistralOpenReasoning128k$2.00$6.00$48.00
GPT-5.4OpenAIAPIReasoning1,050k$2.50$15.00$112.50
GPT AudioOpenAIAPIReasoning128k$2.50$10.00$77.50
Nova Premier 1.0AmazonAPIReasoning1,000k$2.50$12.50$95.00
GPT-5 Image MiniOpenAIAPIReasoning400k$2.50$2.00$21.50
Command ACohereAPIReasoning256k$2.50$10.00$77.50
GPT-4o Search PreviewOpenAIAPIReasoning128k$2.50$10.00$77.50
GPT-4o (2024-11-20)OpenAIAPIReasoning128k$2.50$10.00$77.50
Inflection 3 ProductivityInflectionAPIReasoning8k$2.50$10.00$77.50
Inflection 3 PiInflectionAPIReasoning8k$2.50$10.00$77.50
GPT-4o (2024-08-06)OpenAIAPIReasoning128k$2.50$10.00$77.50
GPT-4oOpenAIAPIReasoning128k$2.50$10.0090/100$77.50
Command R+CohereAPIReasoning128k$2.50$10.0086/100$77.50
Kimi K3Moonshot AIAPIReasoning1,048.576k$3.00$15.00$114.00
Claude Sonnet 4.6AnthropicAPIReasoning1,000k$3.00$15.0094/100$114.00
Sonar Pro SearchPerplexityAPIReasoning200k$3.00$15.00$114.00
Claude Sonnet 4.5AnthropicAPIReasoning1,000k$3.00$15.0091/100$114.00
Claude Sonnet 4AnthropicAPIReasoning200k$3.00$15.00$114.00
Sonar ProPerplexityAPIReasoning200k$3.00$15.00$114.00
Claude 3.5 Sonnet v2AnthropicAPIReasoning200k$3.00$15.0092/100$114.00
GPT-3.5 Turbo 16kOpenAIAPIReasoning16.385k$3.00$4.00$37.00
Fugu Ultra v2Sakana AIAPIReasoning1,000k$5.00$30.00$225.00
Claude Opus 5AnthropicAPIReasoning1,000k$5.00$25.00$190.00
Fugu UltraSakana AIAPIReasoning1,000k$5.00$30.00$225.00
Claude Opus 4.8AnthropicAPIReasoning1,000k$5.00$25.0097/100$190.00
GPT Chat LatestOpenAIAPIReasoning400k$5.00$30.00$225.00
GPT-5.5OpenAIAPIReasoning1,050k$5.00$30.0095/100$225.00
Claude Opus LatestAnthropicAPIReasoning1,000k$5.00$25.00$190.00
Claude Opus 4.7AnthropicAPIReasoning1,000k$5.00$25.0096/100$190.00
Claude Opus 4.6AnthropicAPIReasoning1,000k$5.00$25.0095/100$190.00
Claude Opus 4.5AnthropicAPIReasoning200k$5.00$25.0093/100$190.00
GPT-4o (2024-05-13)OpenAIAPIReasoning128k$5.00$15.00$120.00
GPT-5.4 Image 2OpenAIAPIReasoning272k$8.00$15.00$129.00
GPT-6 AstraOpenAIAPIReasoning1,050k$10.00$50.00$380.00
GPT-6 Astra ProOpenAIAPIReasoning1,050k$10.00$50.00$380.00
Claude Fable 5.1AnthropicAPIReasoning1,000k$10.00$50.00$380.00
Claude Opus 5 (Fast)AnthropicAPIReasoning1,000k$10.00$50.00$380.00
Claude Fable 5AnthropicAPIReasoning1,000k$10.00$50.00$380.00
Claude Fable LatestAnthropicAPIReasoning1,000k$10.00$50.00$380.00
Claude Opus 4.8 (Fast)AnthropicAPIReasoning1,000k$10.00$50.00$380.00
GPT-5 ImageOpenAIAPIReasoning400k$10.00$10.00$100.00
o3 Deep ResearchOpenAIAPIReasoning200k$10.00$40.00$310.00
GPT-4 TurboOpenAIAPIReasoning128k$10.00$30.00$240.00
GPT-4 Turbo PreviewOpenAIAPIReasoning128k$10.00$30.00$240.00
GPT-5 ProOpenAIAPIReasoning400k$15.00$120.00$885.00
Claude Opus 4.1AnthropicAPIReasoning200k$15.00$75.00$570.00
Claude Opus 4AnthropicAPIReasoning200k$15.00$75.00$570.00
o1OpenAIAPIReasoning200k$15.00$60.0088/100$465.00
o3 ProOpenAIAPIReasoning200k$20.00$80.00$620.00
GPT-5.2 ProOpenAIAPIReasoning400k$21.00$168.00$1239.00
Claude Opus 4.7 (Fast)AnthropicAPIReasoning1,000k$30.00$150.00$1140.00
GPT-5.5 ProOpenAIAPIReasoning1,050k$30.00$180.0098/100$1350.00
GPT-5.4 ProOpenAIAPIReasoning1,050k$30.00$180.00$1350.00
GPT-4OpenAIAPIReasoning8.191k$30.00$60.00$510.00
o1-proOpenAIAPIReasoning200k$150.00$600.00$4650.00

* Calculated cost based on 10M tokens/mo (30% in / 70% out) × simple request loop multiplier.

LLMDB.APP × ARAHO DIGITAL

Build with Araho

Compare and optimize your AI spend. Need a custom pipeline? Araho Digital builds production-ready AI systems.

Talk to an AI builder →
mail

Sign up for price change alerts

Stay updated on the latest price drops and context window expansions across OpenAI, Anthropic, Google, and more. Delivered weekly.