Tokens & Costs · Updated daily
AI pricing changes: the daily LLM API price log
Every change to AI API prices in our data, newest first: price cuts, increases, new models and removed ones, with the old and new price per million tokens. Data clean-ups and routing noise are filtered out, and list prices are kept apart from open-weight host prices. Last checked 12 November 2026.
Tracking since 9 October 2026Last change 12 November 2026Atom feedLicence: CC BY 4.0
Summary
Biggest moves in November 2026
Net change per model this month, combining every logged change, measured on the blended price (three parts input to one part output, per million tokens).
List prices
Closed-weight models, priced by their developer.
Cuts
- Weaver (alpha)$0.4875 → $0.35 blended−28%
Increases
No increases this month.
Open-weight host prices
The price of OpenRouter’s top-ranked host, which moves when hosts change.
Cuts
- Nemotron 3 Super$0.825 → $0.1563 blended−81%
- Llama 3.1 8B Instruct$0.0575 → $0.025 blended−57%
- DeepSeek V4 Pro 0423$2 → $1.1153 blended · 6 changes−44%
Increases
- Llama 3.3 70B Instruct$0.155 → $0.71 blended · 5 changes+358%
- Qwen3 Coder 30B A3B Instruct$0.1225 → $0.2625 blended+114%
- DeepSeek V4 Flash Vision Exp$0.3234 → $0.66 blended+104%
Log
Every change, by day
315 changes over 35 days.
4 price cuts, 2 increases, 1 new model, 3 removed
- Output
- from $0.25 to $0.15
- −40%
- Input
- from $0.17 to $0.135
- −21%
- Output
- from $0.25 to $0.198
- −21%
- Input
- from $0.10 to $0.12
- +20%
- Output
- from $0.22 to $0.24
- +9.1%
- Output
- from $0.45 to $0.35
- −22%
- Input
- from $0.9553 to $0.8923
- −6.6%
- Output
- from $1.9105 to $1.7845
- −6.6%
- Cached input
- from $0.0796 to $0.0744
- −6.6%
- Input
- from $1.33 to $1.40
- +5.3%
- Output
- from $4.18 to $4.40
- +5.3%
- Cached input
- from $0.247 to $0.26
- +5.3%
New model
Pareto 26.10 Previewunbiased
First listed by our source on this day.
Removed
seed-1.6ByteDance Seed
No longer listed by our source. This doesn’t always mean the provider retired it.
Removed
seed-1.6-flashByteDance Seed
No longer listed by our source. This doesn’t always mean the provider retired it.
Removed
seed-2.0-codeByteDance Seed
No longer listed by our source. This doesn’t always mean the provider retired it.
5 price cuts, 4 new models, 1 removed
- Input
- from $0.40 to $0.30
- −25%
- Output
- from $0.75 to $0.50
- −33%
- Cached input
- from $0.40 to $0.30
- −25%
- Input
- from $0.15 to $0.0399
- −73%
- Output
- from $0.50 to $0.0784
- −84%
- Input
- from $0.35 to $0.30
- −14%
- Output
- from $0.65 to $0.50
- −23%
- Cached input
- from $0.35 to $0.20
- −43%
- Input
- from $0.30 to $0.27
- −10.0%
- Output
- from $1.20 to $1.08
- −10.0%
- Cached input
- from $0.06 to $0.027
- −55%
- Input
- from $1.40 to $1.33
- −5.0%
- Output
- from $4.40 to $4.18
- −5.0%
- Cached input
- from $0.26 to $0.247
- −5.0%
New model
ERNIE-Light-DT-1.0Baidu
First listed by our source on this day.
New model
Gemini 4 CarbonGoogle
First listed by our source on this day.
New model
First listed by our source on this day.
New model
Motif 3Motif Technologies
First listed by our source on this day.
Removed
qwen-2.5-7b-instructQwen
No longer listed by our source. This doesn’t always mean the provider retired it.
3 price cuts, 4 increases, 3 new models, 2 removed
- Input
- from $0.0335 to $0.15
- +348%
- Output
- from $0.083 to $0.50
- +502%
- Input
- from $0.018 to $0.03
- +67%
- Output
- from $0.09 to $0.13
- +44%
- Cached input
- from $0.009 to $0.03
- +233%
- Input
- from $0.09 to $0.08
- −11%
- Output
- from $0.30 to $0.10
- −67%
- Cached input
- from $0.05 to $0.046
- −8.0%
- Input
- from $0.12 to $0.10
- −17%
- Output
- from $0.24 to $0.22
- −8.3%
- Input
- from $0.59 to $0.71
- +20%
- Output
- from $0.79 to $0.71
- −10%
- Cached input
- from $0.295 to $0.71
- +141%
Price increaseOpen weights · host price
DeepSeek V4 Pro 0423DeepSeek
Blended price $1.1175 → $1.1941 +6.9%
- Input
- from $0.894 to $0.9553
- +6.9%
- Output
- from $1.788 to $1.9105
- +6.9%
- Cached input
- from $0.0745 to $0.0796
- +6.9%
- Output
- from $0.50 to $0.47
- −6.0%
New model
Claude Fable 5.2Anthropic
First listed by our source on this day.
New model
Muse EmberMeta
First listed by our source on this day.
New model
Nex-N2.6Nex AGI
First listed by our source on this day.
Removed
crouton-alphastealth
No longer listed by our source. This doesn’t always mean the provider retired it.
Removed
minimax-m1MiniMax
No longer listed by our source. This doesn’t always mean the provider retired it.
2 price cuts, 7 increases
- Input
- from $0.014 to $0.15
- +971%
- Output
- from $0.053 to $0.60
- +1,032%
- Cached input
- from $0.013 to $0.075
- +477%
Price increaseOpen weights · host price
DeepSeek V4 Pro 0423DeepSeek
Blended price $0.3397 → $1.1175 +229%
- Input
- from $0.2718 to $0.894
- +229%
- Output
- from $0.5436 to $1.788
- +229%
- Cached input
- from $0.0226 to $0.0745
- +229%
- Input
- from $0.05 to $0.02
- −60%
- Output
- from $0.08 to $0.04
- −50%
Price increaseOpen weights · host price
Mistral Small 3.2 24BMistral
Blended price $0.1063 → $0.15 +41%
- Input
- from $0.075 to $0.10
- +33%
- Output
- from $0.20 to $0.30
- +50%
- Input
- from $0.13 to $0.20
- +54%
- Output
- from $0.85 to $1.10
- +29%
- Cached input
- from $0.025 to $0.03
- +20%
- Input
- from $0.03 to $0.018
- −40%
- Output
- from $0.13 to $0.09
- −31%
- Cached input
- from $0.03 to $0.009
- −70%
- Input
- from $0.0675 to $0.09
- +33%
- Output
- from $0.225 to $0.30
- +33%
- Cached input
- from $0.0375 to $0.05
- +33%
- Output
- from $0.35 to $0.45
- +29%
- Input
- from $0.50 to $0.60
- +20%
- Cached input
- from $0.30 to $0.12
- −60%
4 price cuts, 2 increases, 3 removed
- Input
- from $0.15 to $0.0335
- −78%
- Output
- from $0.50 to $0.083
- −83%
- Input
- from $0.7484 to $0.2718
- −64%
- Output
- from $1.4967 to $0.5436
- −64%
- Cached input
- from $0.0624 to $0.0226
- −64%
- Input
- from $0.50 to $0.532
- +6.4%
- Output
- from $2.50 to $3.325
- +33%
- Cached input
- from $0.15 to $0.209
- +39%
- Input
- from $0.016 to $0.014
- −13%
- Output
- from $0.059 to $0.053
- −10%
- Cached input
- from $0.014 to $0.013
- −7.1%
- Input
- from $0.45 to $0.32
- −29%
- Output
- from $2.70 to $3.20
- +19%
- Input
- from $0.0509 to $0.05
- −1.8%
- Output
- from $0.335 to $0.33
- −1.5%
Removed
mercury-2inception
No longer listed by our source. This doesn’t always mean the provider retired it.
Removed
mercury-2.5inception
No longer listed by our source. This doesn’t always mean the provider retired it.
Removed
mercury-3inception
No longer listed by our source. This doesn’t always mean the provider retired it.
4 price cuts, 1 increase, 1 new model
- Input
- from $0.15 to $0.016
- −89%
- Output
- from $0.60 to $0.059
- −90%
- Cached input
- from $0.075 to $0.014
- −81%
- Input
- from $0.075 to $0.045
- −40%
- Output
- from $0.225 to $0.135
- −40%
- Cached input
- from $0.015 to $0.009
- −40%
- Input
- from $0.09 to $0.0675
- −25%
- Output
- from $0.30 to $0.225
- −25%
- Cached input
- from $0.05 to $0.0375
- −25%
- Input
- from $0.27 to $0.30
- +11%
- Output
- from $0.95 to $1.20
- +26%
- Cached input
- from $0.03 to $0.06
- +100%
- Input
- from $0.8973 to $0.7484
- −17%
- Output
- from $1.7946 to $1.4967
- −17%
- Cached input
- from $0.0748 to $0.0624
- −17%
New model
LFM3-1.7BLiquidAI
First listed by our source on this day.
2 price cuts, 6 increases, 2 new models
- Input
- from $0.039 to $0.09
- +131%
- Output
- from $0.118 to $0.30
- +154%
- Cached input
- from $0.02 to $0.05
- +150%
- Input
- from $0.20 to $0.59
- +195%
- Output
- from $0.52 to $0.79
- +52%
- Cached input
- from $0.10 to $0.295
- +195%
Price increaseOpen weights · host price
DeepSeek V4 Flash Vision ExpDeepSeek
Blended price $0.3234 → $0.66 +104%
- Input
- from $0.2156 to $0.44
- +104%
- Output
- from $0.6468 to $1.32
- +104%
- Cached input
- from $0.00686 to $0.014
- +104%
- Input
- from $0.30 to $0.075
- −75%
- Output
- from $2.40 to $0.40
- −83%
- Input
- from $1.60 to $0.8973
- −44%
- Output
- from $3.20 to $1.7946
- −44%
- Cached input
- from $0.135 to $0.0748
- −45%
Price increaseOpen weights · host price
Beam 1.0 501B A23BReflection
Blended price $0.4375 → $0.475 +8.6%
- Input
- from $0.25 to $0.30
- +20%
- Cached input
- from $0.05 to $0.04
- −20%
Price increaseOpen weights · host price
Kimi K2.7 CodeMoonshot AI
- Cached input
- from $0.15 to $0.16
- +6.7%
- Input
- from $0.2574 to $0.32
- +24%
- Output
- from $1.0287 to $0.89
- −13%
New model
Gemini Omni 1.1 FlashGoogle
First listed by our source on this day.
New model
Gemini Omni 1.2 FlashGoogle
First listed by our source on this day.
3 price cuts, 4 increases, 2 new models, 4 removed
- Input
- from $0.024 to $0.15
- +525%
- Output
- from $0.087 to $0.60
- +590%
- Cached input
- from $0.021 to $0.075
- +257%
- Input
- from $0.0269 to $0.15
- +458%
- Output
- from $0.0996 to $0.50
- +402%
- Cached input
- from $0.0269 to $0.03
- +12%
- Input
- from $0.10 to $0.20
- +100%
- Output
- from $0.32 to $0.52
- +63%
- Input
- from $0.1875 to $0.35
- +87%
- Output
- from $0.6525 to $1
- +53%
- Cached input
- from $0.05 to $0.17
- +240%
- Input
- from $0.092 to $0.039
- −58%
- Output
- from $0.276 to $0.118
- −57%
- Cached input
- from $0.046 to $0.02
- −57%
- Input
- from $0.30 to $0.21
- −30%
- Output
- from $1.20 to $0.84
- −30%
- Cached input
- from $0.06 to $0.042
- −30%
Price cutOpen weights · host price
Qwen3 Next 80B A3B InstructQwen
Blended price $0.35 → $0.3425 −2.1%
- Input
- from $0.10 to $0.09
- −10%
New model
Ling 3.0 TinyinclusionAI
First listed by our source on this day.
New model
Ripple 65B PreviewRicursive
First listed by our source on this day.
Removed
minimax-01MiniMax
No longer listed by our source. This doesn’t always mean the provider retired it.
Removed
minimax-m2MiniMax
No longer listed by our source. This doesn’t always mean the provider retired it.
Removed
minimax-m2-herMiniMax
No longer listed by our source. This doesn’t always mean the provider retired it.
Removed
minimax-m2.1MiniMax
No longer listed by our source. This doesn’t always mean the provider retired it.
2 price cuts, 4 increases, 2 new models
- Input
- from $0.15 to $0.024
- −84%
- Output
- from $0.60 to $0.087
- −86%
- Cached input
- from $0.075 to $0.021
- −72%
Price increaseOpen weights · host price
Qwen3 235B A22B Instruct 2507Qwen
Blended price $0.205 → $0.305 +49%
- Input
- from $0.09 to $0.14
- +56%
- Output
- from $0.55 to $0.80
- +45%
- Input
- from $0.20 to $0.10
- −50%
- Output
- from $0.52 to $0.32
- −38%
- Output
- from $0.15 to $0.25
- +67%
- Input
- from $0.081 to $0.092
- +14%
- Output
- from $0.242 to $0.276
- +14%
- Cached input
- from $0.04 to $0.046
- +15%
- Input
- from $0.0313 to $0.0269
- −14%
- Output
- from $0.0846 to $0.0996
- +18%
- Cached input
- from $0.03 to $0.0269
- −10%
New model
crouton-alphastealth
First listed by our source on this day.
New model
Hy4Tencent
First listed by our source on this day.
6 increases, 1 new model
Price increaseOpen weights · host price
Qwen3 Coder 30B A3B InstructQwen
Blended price $0.1225 → $0.2625 +114%
- Input
- from $0.07 to $0.15
- +114%
- Output
- from $0.28 to $0.60
- +114%
- Input
- from $0.10 to $0.20
- +100%
- Output
- from $0.32 to $0.52
- +63%
- Input
- from $0.40 to $0.72
- +80%
- Output
- from $0.40 to $0.72
- +80%
- Input
- from $0.065 to $0.081
- +25%
- Output
- from $0.194 to $0.242
- +25%
- Cached input
- from $0.032 to $0.04
- +25%
Price increaseOpen weights · host price
Qwen3 Next 80B A3B InstructQwen
Blended price $0.3425 → $0.35 +2.2%
- Input
- from $0.09 to $0.10
- +11%
- Input
- from $0.0285 to $0.0313
- +9.8%
- Output
- from $0.0923 to $0.0846
- −8.3%
- Cached input
- from $0.0285 to $0.03
- +5.3%
New model
First listed by our source on this day.
1 price cut, 2 increases, 2 removed
- Input
- from $0.02 to $0.15
- +650%
- Output
- from $0.074 to $0.60
- +711%
- Input
- from $0.0675 to $0.065
- −3.7%
- Output
- from $0.225 to $0.194
- −14%
- Cached input
- from $0.0375 to $0.032
- −15%
- Input
- from $0.05 to $0.0509
- +1.8%
- Output
- from $0.33 to $0.335
- +1.5%
Removed
hermes-3-llama-3.1-405bNous
No longer listed by our source. This doesn’t always mean the provider retired it.
Removed
hermes-3-llama-3.1-70bNous
No longer listed by our source. This doesn’t always mean the provider retired it.
2 price cuts, 2 increases, 2 removed
- Input
- from $0.15 to $0.02
- −87%
- Output
- from $0.60 to $0.074
- −88%
- Input
- from $0.018 to $0.03
- +67%
- Output
- from $0.09 to $0.13
- +44%
- Cached input
- from $0.009 to $0.03
- +233%
- Input
- from $0.54 to $0.60
- +11%
- Output
- from $1.98 to $2.20
- +11%
- Cached input
- from $0.099 to $0.11
- +11%
- Input
- from $0.0163 to $0.0285
- +75%
- Output
- from $0.1479 to $0.0923
- −38%
- Cached input
- from $0.0163 to $0.0285
- +75%
Removed
laguna-s-2.1poolside
No longer listed by our source. This doesn’t always mean the provider retired it.
Removed
laguna-xs-2.1poolside
No longer listed by our source. This doesn’t always mean the provider retired it.
6 price cuts, 2 increases
- Input
- from $0.25 to $0.05
- −80%
- Output
- from $1 to $0.50
- −50%
- Input
- from $0.8162 to $1.60
- +96%
- Output
- from $1.6325 to $3.20
- +96%
- Cached input
- from $0.068 to $0.135
- +98%
- Input
- from $0.15 to $0.0163
- −89%
- Output
- from $0.50 to $0.1479
- −70%
- Cached input
- from $0.03 to $0.0163
- −46%
- Input
- from $0.09 to $0.0675
- −25%
- Output
- from $0.30 to $0.225
- −25%
- Cached input
- from $0.05 to $0.0375
- −25%
- Input
- from $0.30 to $0.27
- −10.0%
- Output
- from $1.20 to $0.95
- −21%
- Input
- from $0.56 to $0.60
- +7.1%
- Output
- from $3.10 to $3.50
- +13%
- Input
- from $0.28 to $0.26
- −7.1%
- Output
- from $0.42 to $0.38
- −9.5%
- Cached input
- from $0.028 to $0.13
- +364%
- Input
- from $0.32 to $0.45
- +41%
- Output
- from $3.20 to $2.70
- −16%
4 price cuts, 3 increases, 1 removed
Price cutList price
Particle-1Particle AI
- Cached input
- from $0.03 to $0.003
- −90%
- Input
- from $0.0457 to $0.15
- +228%
- Output
- from $0.0742 to $0.50
- +574%
- Input
- from $1.36 to $0.70
- −49%
- Output
- from $4.18 to $2.10
- −50%
- Cached input
- from $0.14 to $0.07
- −50%
- Input
- from $0.20 to $0.15
- −25%
- Output
- from $2.50 to $1.875
- −25%
- Cached input
- from $0.09 to $0.0375
- −58%
- Input
- from $0.9553 to $0.8162
- −15%
- Output
- from $1.9105 to $1.6325
- −15%
- Cached input
- from $0.0796 to $0.068
- −15%
Price increaseOpen weights · host price
GLM 4.6VZ.ai
- Cached input
- from $0.05 to $0.055
- +10.0%
- Input
- from $0.45 to $0.32
- −29%
- Output
- from $2.70 to $3.20
- +19%
Removed
solar-pro-3Upstage
No longer listed by our source. This doesn’t always mean the provider retired it.
4 price cuts, 1 increase, 1 new model, 8 removed
Price increaseOpen weights · host price
Blended price $0.025 → $0.0575 +130%
- Input
- from $0.02 to $0.05
- +150%
- Output
- from $0.04 to $0.08
- +100%
- Input
- from $0.15 to $0.0457
- −70%
- Output
- from $0.50 to $0.0742
- −85%
- Output
- from $0.25 to $0.15
- −40%
- Input
- from $0.55 to $0.50
- −9.1%
- Output
- from $2.20 to $2
- −9.1%
- Cached input
- from $0.11 to $0.10
- −9.1%
- Input
- from $0.6725 to $0.56
- −17%
New model
Particle-1Particle AI
First listed by our source on this day.
Removed
gpt-4-turboOpenAI
No longer listed by our source. This doesn’t always mean the provider retired it.
Removed
o1OpenAI
No longer listed by our source. This doesn’t always mean the provider retired it.
Removed
o1-proOpenAI
No longer listed by our source. This doesn’t always mean the provider retired it.
Removed
o3-miniOpenAI
No longer listed by our source. This doesn’t always mean the provider retired it.
Removed
o3-mini-highOpenAI
No longer listed by our source. This doesn’t always mean the provider retired it.
Removed
o4-miniOpenAI
No longer listed by our source. This doesn’t always mean the provider retired it.
Removed
o4-mini-highOpenAI
No longer listed by our source. This doesn’t always mean the provider retired it.
Removed
qwen3-next-80b-a3b-thinkingQwen
No longer listed by our source. This doesn’t always mean the provider retired it.
3 price cuts, 2 increases, 1 new model
- Input
- from $0.05 to $0.02
- −60%
- Output
- from $0.08 to $0.04
- −50%
- Input
- from $0.966 to $1.40
- +45%
- Output
- from $3.036 to $4.40
- +45%
- Cached input
- from $0.1794 to $0.26
- +45%
Price increaseOpen weights · host price
Kimi K2.7 CodeMoonshot AI
Blended price $1.195 → $1.2794 +7.1%
- Input
- from $0.56 to $0.6725
- +20%
- Output
- from $0.95 to $0.90
- −5.3%
- Cached input
- from $0.05 to $0.025
- −50%
- Input
- from $0.32 to $0.45
- +41%
- Output
- from $3.20 to $2.70
- −16%
New model
Ternary Bonsai 2 9BPrismML
First listed by our source on this day.
2 price cuts, 4 increases, 2 new models, 2 removed
- Input
- from $0.119 to $0.40
- +236%
- Output
- from $0.238 to $2
- +740%
- Cached input
- from $0.00255 to $0.08
- +3,037%
- Input
- from $0.3045 to $0.48
- +58%
- Output
- from $0.609 to $1.80
- +196%
- Cached input
- from $0.0028 to $0.096
- +3,329%
- Input
- from $0.04 to $0.05
- +25%
- Output
- from $0.05 to $0.10
- +100%
- Input
- from $1.40 to $0.966
- −31%
- Output
- from $4.40 to $3.036
- −31%
- Cached input
- from $0.26 to $0.1794
- −31%
- Input
- from $0.27 to $0.26
- −3.7%
- Output
- from $2.16 to $2.60
- +20%
- Input
- from $0.6712 to $0.56
- −17%
- Output
- from $3.35 to $3.10
- −7.5%
New model
GPT-6.1 TerraOpenAI
First listed by our source on this day.
New model
GPT-6.1 Terra ProOpenAI
First listed by our source on this day.
Removed
granite-4.0-h-microIBM
No longer listed by our source. This doesn’t always mean the provider retired it.
Removed
trinity-large-thinkingarcee-ai
No longer listed by our source. This doesn’t always mean the provider retired it.
1 price cut, 5 increases
Price increaseList price
GPT-4.1 NanoOpenAI
- Cached input
- from $0.025 to $0.03
- +20%
Price increaseOpen weights · host price
DeepSeek V4 Pro 0423DeepSeek
Blended price $0.261 → $1.1941 +358%
- Input
- from $0.2088 to $0.9553
- +358%
- Output
- from $0.4176 to $1.9105
- +358%
- Cached input
- from $0.0174 to $0.0796
- +358%
- Input
- from $0.25 to $0.32
- +28%
- Output
- from $2 to $3.20
- +60%
- Input
- from $0.40 to $0.26
- −35%
- Output
- from $3.20 to $2.08
- −35%
- Input
- from $0.0675 to $0.09
- +33%
- Output
- from $0.225 to $0.30
- +33%
- Cached input
- from $0.0375 to $0.05
- +33%
Price increaseOpen weights · host price
Qwen3 30B A3B Instruct 2507Qwen
Blended price $0.1425 → $0.15 +5.3%
- Input
- from $0.09 to $0.10
- +11%
3 price cuts, 1 increase, 1 new model, 2 removed
- Input
- from $0.3884 to $0.2088
- −46%
- Output
- from $0.7767 to $0.4176
- −46%
- Cached input
- from $0.0324 to $0.0174
- −46%
- Input
- from $0.27 to $0.30
- +11%
- Output
- from $0.95 to $1.20
- +26%
Price cutOpen weights · host price
GLM 4.6VZ.ai
- Cached input
- from $0.055 to $0.05
- −9.1%
- Input
- from $0.0509 to $0.05
- −1.8%
- Output
- from $0.335 to $0.33
- −1.5%
New model
LFM2.5-2.6BLiquidAI
First listed by our source on this day.
Removed
gpt-3.5-turboOpenAI
No longer listed by our source. This doesn’t always mean the provider retired it.
Removed
gpt-3.5-turbo-instructOpenAI
No longer listed by our source. This doesn’t always mean the provider retired it.
3 price cuts, 1 increase, 1 new model
- Input
- from $0.0412 to $0.15
- +264%
- Output
- from $0.12 to $0.50
- +317%
- Cached input
- from $0.00375 to $0.03
- +700%
- Input
- from $0.9553 to $0.3884
- −59%
- Output
- from $1.9105 to $0.7767
- −59%
- Cached input
- from $0.0796 to $0.0324
- −59%
- Input
- from $0.09 to $0.0675
- −25%
- Output
- from $0.30 to $0.225
- −25%
- Cached input
- from $0.05 to $0.0375
- −25%
Price cutOpen weights · host price
Kimi K2.7 CodeMoonshot AI
- Cached input
- from $0.18 to $0.15
- −17%
New model
Kimi K3.1 ProMoonshot AI
First listed by our source on this day.
2 price cuts, 2 increases, 1 new model
- Input
- from $0.08 to $0.17
- +113%
- Output
- from $0.13 to $0.25
- +92%
- Input
- from $0.0938 to $0.075
- −20%
- Output
- from $0.25 to $0.20
- −20%
- Input
- from $0.30 to $0.25
- −17%
- Cached input
- from $0.04 to $0.05
- +25%
- Input
- from $0.24 to $0.20
- −17%
- Output
- from $2.20 to $2.50
- +14%
- Cached input
- from $0.05 to $0.09
- +80%
New model
MiniMax M3.1 FlashMiniMax
First listed by our source on this day.
4 increases
Price increaseOpen weights · host price
DeepSeek V4 Pro 0813DeepSeek
Blended price $0.99 → $1.98 +100%
- Input
- from $0.66 to $1.32
- +100%
- Output
- from $1.98 to $3.96
- +100%
- Cached input
- from $0.022 to $0.044
- +100%
- Input
- from $0.26 to $0.40
- +54%
- Output
- from $2.08 to $3.20
- +54%
- Input
- from $0.39 to $0.50
- +28%
- Output
- from $2.34 to $3.60
- +54%
Price increaseOpen weights · host price
Kimi K2.7 CodeMoonshot AI
Blended price $1.2794 → $1.3419 +4.9%
- Output
- from $3.10 to $3.35
- +8.1%
6 price cuts, 4 increases
- Input
- from $0.08 to $0.30
- +275%
- Output
- from $0.45 to $2.40
- +433%
- Input
- from $0.68 to $1.36
- +100%
- Output
- from $2.09 to $4.18
- +100%
- Cached input
- from $0.07 to $0.14
- +100%
- Input
- from $0.60 to $1
- +67%
- Output
- from $1.92 to $3.20
- +67%
- Cached input
- from $0.12 to $0.20
- +67%
- Input
- from $0.966 to $1.40
- +45%
- Output
- from $3.036 to $4.40
- +45%
- Cached input
- from $0.1794 to $0.26
- +45%
- Input
- from $0.435 to $0.3045
- −30%
- Output
- from $0.87 to $0.609
- −30%
- Cached input
- from $0.0036 to $0.0028
- −22%
- Input
- from $0.0471 to $0.0412
- −13%
- Output
- from $0.16 to $0.12
- −25%
- Cached input
- from $0.006 to $0.00375
- −38%
- Input
- from $0.10 to $0.08
- −20%
- Output
- from $0.15 to $0.13
- −13%
- Input
- from $0.14 to $0.119
- −15%
- Output
- from $0.28 to $0.238
- −15%
- Cached input
- from $0.0028 to $0.00255
- −8.9%
- Output
- from $3.35 to $3.10
- −7.5%
- Input
- from $0.15 to $0.14
- −6.7%
7 price cuts, 2 increases, 1 new model
- Input
- from $0.09 to $0.15
- +67%
- Output
- from $0.36 to $0.60
- +67%
- Cached input
- from $0.018 to $0.03
- +67%
- Input
- from $1 to $0.30
- −70%
- Output
- from $3 to $1
- −67%
- Cached input
- from $0.10 to $0.04
- −60%
- Input
- from $1 to $0.60
- −40%
- Output
- from $3.20 to $1.92
- −40%
- Cached input
- from $0.20 to $0.12
- −40%
Price increaseOpen weights · host price
Nemotron 3.5 Super VLNVIDIA
Blended price $0.175 → $0.2375 +36%
- Input
- from $0.10 to $0.15
- +50%
- Output
- from $0.40 to $0.50
- +25%
- Cached input
- from $0.08 to $0.02
- −75%
- Input
- from $0.05 to $0.04
- −20%
- Output
- from $0.10 to $0.05
- −50%
- Input
- from $0.50 to $0.39
- −22%
- Output
- from $3.60 to $2.34
- −35%
- Input
- from $0.15 to $0.10
- −33%
- Output
- from $1 to $0.95
- −5.0%
- Input
- from $0.32 to $0.2574
- −20%
- Output
- from $0.89 to $1.0287
- +16%
- Input
- from $0.048 to $0.0471
- −1.9%
New model
mercury-3inception
First listed by our source on this day.
2 price cuts, 4 increases, 3 removed
Price increaseOpen weights · host price
DeepSeek V4 Pro 0423DeepSeek
Blended price $0.261 → $1.1941 +358%
- Input
- from $0.2088 to $0.9553
- +358%
- Output
- from $0.4176 to $1.9105
- +358%
- Cached input
- from $0.0174 to $0.0796
- +358%
- Input
- from $0.0675 to $0.09
- +33%
- Output
- from $0.225 to $0.30
- +33%
- Cached input
- from $0.0375 to $0.05
- +33%
- Input
- from $0.26 to $0.27
- +3.8%
- Output
- from $2.60 to $2.16
- −17%
- Output
- from $0.20 to $0.16
- −20%
- Input
- from $0.50 to $0.55
- +10%
- Output
- from $2 to $2.20
- +10%
- Cached input
- from $0.10 to $0.11
- +10.0%
- Input
- from $0.05 to $0.0509
- +1.8%
- Output
- from $0.33 to $0.335
- +1.5%
Removed
deepseek-r1DeepSeek
No longer listed by our source. This doesn’t always mean the provider retired it.
Removed
l3.3-euryale-70bSao10K
No longer listed by our source. This doesn’t always mean the provider retired it.
Removed
wizardlm-2-8x22bMicrosoft
No longer listed by our source. This doesn’t always mean the provider retired it.
4 price cuts, 1 new model
- Input
- from $1.32 to $0.66
- −50%
- Output
- from $3.96 to $1.98
- −50%
- Cached input
- from $0.044 to $0.022
- −50%
- Input
- from $0.0293 to $0.048
- +64%
- Output
- from $0.4182 to $0.20
- −52%
- Cached input
- from $0.0094 to $0.006
- −36%
- Output
- from $0.45 to $0.35
- −22%
Price cutOpen weights · host price
Qwen3 30B A3B Instruct 2507Qwen
Blended price $0.15 → $0.1425 −5.0%
- Input
- from $0.10 to $0.09
- −10%
New model
Pareto 26.10unbiased
First listed by our source on this day.
7 price cuts, 1 increase, 3 new models
- Input
- from $0.9553 to $0.2088
- −78%
- Output
- from $1.9105 to $0.4176
- −78%
- Cached input
- from $0.0796 to $0.0174
- −78%
- Input
- from $0.18 to $0.10
- −44%
- Output
- from $0.59 to $0.30
- −49%
- Input
- from $0.15 to $0.0293
- −80%
- Output
- from $0.50 to $0.4182
- −16%
- Cached input
- from $0.03 to $0.0094
- −69%
- Input
- from $0.15 to $0.10
- −33%
- Output
- from $0.50 to $0.40
- −20%
- Cached input
- from $0.02 to $0.08
- +300%
- Input
- from $0.09 to $0.0675
- −25%
- Output
- from $0.30 to $0.225
- −25%
- Cached input
- from $0.05 to $0.0375
- −25%
- Input
- from $0.259 to $0.28
- +8.1%
- Output
- from $0.80 to $0.42
- −48%
- Cached input
- from $0.14 to $0.028
- −80%
- Input
- from $0.60 to $0.54
- −10.0%
- Output
- from $2.20 to $1.98
- −10%
- Cached input
- from $0.11 to $0.099
- −10.0%
- Input
- from $0.2574 to $0.32
- +24%
- Output
- from $1.0287 to $0.89
- −13%
New model
GlimpseElorian
First listed by our source on this day.
New model
Beam 1.0 501B A23BReflection
First listed by our source on this day.
New model
DeepSeek V4.1 Flash 1017DeepSeek
First listed by our source on this day.
4 price cuts, 3 increases, 4 new models, 2 removed
- Input
- from $0.75 to $0.825
- +10.0%
- Output
- from $3.75 to $4.125
- +10%
- Cached input
- from $0.075 to $0.0825
- +10%
Price increaseOpen weights · host price
Step 5 PreviewStepFun
- Cached input
- from $0.05 to $0.10
- +100%
- Input
- from $0.59 to $0.10
- −83%
- Output
- from $0.79 to $0.32
- −59%
- Input
- from $0.32 to $0.25
- −22%
- Output
- from $3.20 to $2
- −38%
Price increaseOpen weights · host price
Mistral Small 3.2 24BMistral
Blended price $0.1063 → $0.1328 +25%
- Input
- from $0.075 to $0.0938
- +25%
- Output
- from $0.20 to $0.25
- +25%
- Input
- from $0.32 to $0.2574
- −20%
- Output
- from $0.89 to $1.0287
- +16%
Price cutOpen weights · host price
Qwen3 Next 80B A3B InstructQwen
Blended price $0.35 → $0.3425 −2.1%
- Input
- from $0.10 to $0.09
- −10%
New model
Moondream 3 PreviewMoondream
First listed by our source on this day.
New model
Moondream 3.1Moondream
First listed by our source on this day.
New model
Muse Spark OpenMeta
First listed by our source on this day.
New model
Nemotron 3.5 Super VLNVIDIA
First listed by our source on this day.
Removed
Pareto 26.10 Previewunbiased
No longer listed by our source. This doesn’t always mean the provider retired it.
Removed
claude-sonnet-4Anthropic
No longer listed by our source. This doesn’t always mean the provider retired it.
4 price cuts, 4 increases, 1 new model
- Input
- from $0.037 to $0.15
- +305%
- Output
- from $0.17 to $0.60
- +253%
- Input
- from $0.60 to $1
- +67%
- Output
- from $1.92 to $3.20
- +67%
- Cached input
- from $0.12 to $0.20
- +67%
- Input
- from $0.09 to $0.20
- +122%
- Output
- from $0.34 to $0.40
- +18%
- Input
- from $1.33 to $0.966
- −27%
- Output
- from $4.18 to $3.036
- −27%
- Cached input
- from $0.247 to $0.1794
- −27%
- Input
- from $0.0938 to $0.075
- −20%
- Output
- from $0.25 to $0.20
- −20%
- Input
- from $0.10 to $0.15
- +50%
- Output
- from $0.95 to $1
- +5.3%
- Cached input
- from $0.10 to $0.05
- −50%
- Output
- from $1.08 to $0.95
- −12%
- Cached input
- from $0.027 to $0.03
- +11%
- Input
- from $0.036 to $0.15
- +317%
- Output
- from $0.90 to $0.50
- −44%
- Cached input
- from $0.0108 to $0.03
- +178%
New model
Qwen3.8 27BQwen
First listed by our source on this day.
3 price cuts, 6 increases, 3 new models, 3 removed
Price increaseOpen weights · host price
Ling 3.0 Flash VLinclusionAI
Blended price $0.0312 → $0.09 +189%
- Input
- from $0.021 to $0.06
- +186%
- Output
- from $0.0616 to $0.18
- +192%
- Cached input
- from $0.0042 to $0.012
- +186%
Price increaseOpen weights · host price
DeepSeek V4 Pro 0423DeepSeek
Blended price $0.5598 → $1.1941 +113%
- Input
- from $0.4479 to $0.9553
- +113%
- Output
- from $0.8958 to $1.9105
- +113%
- Cached input
- from $0.0373 to $0.0796
- +113%
- Input
- from $0.15 to $0.037
- −75%
- Output
- from $0.60 to $0.17
- −72%
- Input
- from $0.08 to $0.15
- +87%
- Output
- from $0.75 to $1
- +33%
- Cached input
- from $0.04 to $0.05
- +25%
- Input
- from $0.966 to $1.33
- +38%
- Output
- from $3.036 to $4.18
- +38%
- Cached input
- from $0.1794 to $0.247
- +38%
- Input
- from $0.0261 to $0.036
- +38%
- Input
- from $0.55 to $0.50
- −9.1%
- Output
- from $3.50 to $3.60
- +2.9%
- Cached input
- from $0.225 to $0.30
- +33%
Price increaseOpen weights · host price
Ling 3.1 FlashinclusionAI
- Input
- from $0 to $0.075
- new price
- Output
- from $0 to $0.225
- new price
Price cutPrice via OpenRouter
minimax-m2MiniMax
- Input
- from $0.30 to $0.255
- −15%
- Output
- from $1.20 to $1.02
- −15%
New model
Gemini 4 ArgonGoogle
First listed by our source on this day.
New model
Pareto 26.9unbiased
First listed by our source on this day.
New model
LFM2.5-24B-A2BLiquidAI
First listed by our source on this day.
Removed
ling-3.0-flash-fininclusionAI
No longer listed by our source. This doesn’t always mean the provider retired it.
Removed
ling-3.0-flash-santeinclusionAI
No longer listed by our source. This doesn’t always mean the provider retired it.
Removed
paretounbiased
No longer listed by our source. This doesn’t always mean the provider retired it.
4 increases, 4 new models
- Input
- from $0.037 to $0.15
- +305%
- Output
- from $0.17 to $0.60
- +253%
- Input
- from $0.22 to $0.59
- +168%
- Output
- from $0.50 to $0.79
- +58%
- Cached input
- from $0.11 to $0.295
- +168%
- Input
- from $0.21 to $0.30
- +43%
- Output
- from $0.84 to $1.20
- +43%
- Cached input
- from $0.042 to $0.06
- +43%
Price increaseOpen weights · host price
GLM 4.6VZ.ai
- Cached input
- from $0.05 to $0.055
- +10.0%
New model
ExtractScaleDown
First listed by our source on this day.
New model
Muse WonderMeta
First listed by our source on this day.
New model
SummarizeScaleDown
First listed by our source on this day.
New model
GLM 5.3 FlashZ.ai
First listed by our source on this day.
1 price cut, 3 increases, 1 removed
Price increaseOpen weights · host price
DeepSeek V4 Pro 0423DeepSeek
Blended price $0.261 → $0.5577 +114%
- Input
- from $0.2088 to $0.4461
- +114%
- Output
- from $0.4176 to $0.8923
- +114%
- Cached input
- from $0.0174 to $0.0372
- +114%
- Input
- from $0.10 to $0.18
- +80%
- Output
- from $0.30 to $0.59
- +97%
- Input
- from $0.0675 to $0.09
- +33%
- Output
- from $0.225 to $0.30
- +33%
- Cached input
- from $0.0375 to $0.05
- +33%
Price cutOpen weights · host price
GLM 4.6VZ.ai
- Cached input
- from $0.055 to $0.05
- −9.1%
Removed
GLM 5.3 FlashZ.ai
No longer listed by our source. This doesn’t always mean the provider retired it.
2 price cuts, 2 increases, 3 new models, 1 removed
- Input
- from $0.9483 to $0.2088
- −78%
- Output
- from $1.8966 to $0.4176
- −78%
- Cached input
- from $0.079 to $0.0174
- −78%
- Input
- from $0.465 to $0.65
- +40%
- Output
- from $2.45 to $3.41
- +39%
- Cached input
- from $0.0875 to $0.15
- +71%
- Input
- from $0.15 to $0.10
- −33%
- Output
- from $1 to $0.95
- −5.0%
- Cached input
- from $0.05 to $0.10
- +100%
- Input
- from $0.50 to $0.60
- +20%
- Output
- from $2.20 to $2.40
- +9.1%
- Cached input
- from $0.10 to $0.12
- +20%
New model
DeepSeek V4 Pro 0813DeepSeek
First listed by our source on this day.
New model
Hy3Tencent
First listed by our source on this day.
New model
Hy4 previewTencent
First listed by our source on this day.
Removed
Qwen3.8 27BQwen
No longer listed by our source. This doesn’t always mean the provider retired it.
3 price cuts, 7 increases, 11 removed
- Input
- from $0.117 to $0.25
- +114%
- Output
- from $0.455 to $0.75
- +65%
Price increaseOpen weights · host price
Qwen3 235B A22B Thinking 2507Qwen
Blended price $0.7475 → $1.2125 +62%
- Input
- from $0.23 to $0.45
- +96%
- Output
- from $2.30 to $3.50
- +52%
Price increaseOpen weights · host price
Nemotron 3.5 LightningNVIDIA
Blended price $0.0687 → $0.1025 +49%
- Input
- from $0.0469 to $0.07
- +49%
- Output
- from $0.134 to $0.20
- +49%
- Cached input
- from $0.0235 to $0.04
- +71%
- Input
- from $0.20 to $0.29
- +45%
- Output
- from $2.40 to $1
- −58%
- Output
- from $0.42 to $0.80
- +90%
- Cached input
- from $0.135 to $0.14
- +3.7%
- Input
- from $0.09 to $0.0675
- −25%
- Output
- from $0.30 to $0.225
- −25%
- Cached input
- from $0.05 to $0.0375
- −25%
- Input
- from $0.43 to $0.50
- +16%
- Output
- from $1.75 to $2
- +14%
- Cached input
- from $0.08 to $0.10
- +25%
- Input
- from $0.45 to $0.50
- +11%
- Output
- from $2.25 to $2.50
- +11%
- Cached input
- from $0.07 to $0.15
- +114%
Price cutOpen weights · host price
Kimi K2.6Moonshot AI
- Cached input
- from $0.0975 to $0.0875
- −10%
- Input
- from $0.45 to $0.32
- −29%
- Output
- from $2.70 to $3.20
- +19%
Removed
qwen-plus-2025-07-28Qwen
No longer listed by our source. This doesn’t always mean the provider retired it.
Removed
qwen3-235b-a22bQwen
No longer listed by our source. This doesn’t always mean the provider retired it.
Removed
qwen3-30b-a3b-thinking-2507Qwen
No longer listed by our source. This doesn’t always mean the provider retired it.
Removed
qwen3-8bQwen
No longer listed by our source. This doesn’t always mean the provider retired it.
Removed
qwen3-coder-plusQwen
No longer listed by our source. This doesn’t always mean the provider retired it.
Removed
qwen3-maxQwen
No longer listed by our source. This doesn’t always mean the provider retired it.
Removed
qwen3-max-thinkingQwen
No longer listed by our source. This doesn’t always mean the provider retired it.
Removed
qwen3-vl-235b-a22b-thinkingQwen
No longer listed by our source. This doesn’t always mean the provider retired it.
Removed
qwen3-vl-32b-instructQwen
No longer listed by our source. This doesn’t always mean the provider retired it.
Removed
qwen3-vl-8b-thinkingQwen
No longer listed by our source. This doesn’t always mean the provider retired it.
Removed
qwen3.6-max-previewQwen
No longer listed by our source. This doesn’t always mean the provider retired it.
3 price cuts, 7 increases, 2 new models, 1 removed
- Input
- from $0.10 to $0.22
- +120%
- Output
- from $0.32 to $0.50
- +56%
Price increaseOpen weights · host price
Qwen3 30B A3B Instruct 2507Qwen
Blended price $0.0844 → $0.15 +78%
- Input
- from $0.0482 to $0.10
- +108%
- Output
- from $0.1931 to $0.30
- +55%
- Input
- from $0.30 to $0.45
- +50%
- Output
- from $2 to $2.70
- +35%
- Input
- from $0.019 to $0.029
- +53%
- Input
- from $0.15 to $0.08
- −47%
- Output
- from $1 to $0.75
- −25%
- Cached input
- from $0.05 to $0.04
- −20%
- Input
- from $0.15 to $0.10
- −33%
- Output
- from $1.50 to $1.10
- −27%
- Input
- from $0.45 to $0.55
- +22%
- Output
- from $3 to $3.50
- +17%
- Cached input
- from $0.22 to $0.225
- +2.3%
- Input
- from $0.085 to $0.08
- −5.9%
- Output
- from $0.40 to $0.45
- +12%
- Input
- from $0.049 to $0.0469
- −4.3%
- Output
- from $0.14 to $0.134
- −4.3%
- Cached input
- from $0.0245 to $0.0235
- −4.3%
- Input
- from $0.2574 to $0.32
- +24%
- Output
- from $1.0287 to $0.89
- −13%
New model
ling-3.0-flash-santeinclusionAI
First listed by our source on this day.
New model
Step 5 PreviewStepFun
First listed by our source on this day.
Removed
ernie-4.5-vl-424b-a47bBaidu
No longer listed by our source. This doesn’t always mean the provider retired it.
Prices in US dollars per million tokens. Showing the last 90 days. Model names link to the model page, or to the comparison table when there is no page.
Method
How this log works
Where the data comes from
Once a day (scheduled for 05:17 UTC) a GitHub Action downloads the OpenRouter models API and the open-source LiteLLM price list, validates every record and compares it with the previous day. Each difference in a price (input, output, cached input, cache write or batch) and each model that appears or disappears is written to a change file. This page and its feed are rebuilt from that file, so every row is something the sources actually reported on that day.
List prices and host prices
OpenRouter’s documentation describes a model’s pricing field as the “pricing from the top provider for this model” (checked 11 October 2026). A closed-weight model such as GPT, Claude or Gemini is served only by its developer and the developer’s cloud partners, and OpenRouter states it adds no markup to inference, so a change there reflects the developer’s list price. Open-weight models are hosted by many companies at different prices, and the top-ranked host changes often. In our data, GLM 5.3 Flash’s listed price moved on 18 of the 35 days logged (input $0.0261 → $0.036 → $0.15 → $0.0293 → $0.048 → $0.0471 → $0.0412 → $0.15 → $0.0457 → $0.15 → $0.0163 → $0.0285 → $0.0313 → $0.0269 → $0.15 → $0.0335 → $0.15 → $0.0399 per million tokens). That is why open-weight rows are labelled host prices and summarised separately.
What we filter out
The raw change file holds 748 entries. 135 of them are hidden here because they are not price decisions:
- Our own corrections (4). When a source reports a wrong price, we fix it by hand from the provider’s pricing page (see the methodology). The fix shows up in the raw file as a change, but the provider’s price never moved.
- Prices that appear or disappear (117). A cached or batch price going from “not published” to a number, or back, usually means a source added a field or one of our sanity checks dropped an implausible value.
- Same-day reversals (6). When the data refreshes more than once in a day, the runs are combined, and a price that went down and back up again is not a change.
- Moves under 1% (8). In our data these were uniform shifts of every price of a model by the same fraction, typical of rounding or currency conversion.
How to read an entry
Each row gives the old and new price per million tokens and the change as (new − old) ÷ old. When input or output moved, the blended price weighs input three times as heavily as output, because typical chat and coding requests send several times more tokens than they get back. It decides whether a day counts as a cut or an increase when input and output move in opposite directions.
For example, on 10 November 2026 Llama 3.3 70B Instruct went from $0.59 input and $0.79 output to $0.71 and $0.71. Blended: (3 × $0.59 + $0.79) ÷ 4 = $0.64 before, and $0.71 after, a change of +11%, so it is logged as a price increase.
New and removed models
“New model” means our source listed it for the first time. “Removed” means it left the source’s public list or failed a price check; it isn’t proof that the provider retired it. For shutdown dates, the model ID reference tracks the providers’ own deprecation pages.
Report an error
If a row looks wrong, email hello@its-tahir.com or use the contact page with the model, the date and the provider’s pricing page. Always confirm a price on the provider’s own pricing page before you rely on it.
FAQ
Frequently asked questions
How often do AI API prices change?
List prices set by a model’s developer change far less often than hosted prices. In the 35 days we have logged since 9 October 2026, we recorded 6 list-price changes for closed-weight models and 212 hosted-price changes across 61 open-weight models.
Why does an open-weight model’s price change so often?
Open-weight models such as Llama, Qwen or Kimi are served by many hosting companies at different prices. OpenRouter’s model list shows the price of the top-ranked host for each model, so the listed price moves whenever that ranking changes, even if no host changed its own price. We label these as host prices and keep them apart from list prices.
Does a price cut here lower my bill?
Only if you buy through the route that changed. If you call a developer’s API directly, you pay its list price, so check the provider’s pricing page. If you use OpenRouter, you pay the host your request is routed to. A cut to an open-weight model’s host price may apply to one host only. Re-run your numbers in the LLM cost calculator.
What does “removed” mean?
The model is no longer in our data: it left OpenRouter’s public model list, or failed one of our price checks. That doesn’t always mean the provider retired it. Sometimes a model is only relisted under a new or dated name. For official shutdown dates, see our model ID reference and the provider’s deprecation page.
How is the percentage change calculated?
Each row shows the old price, the new price and (new − old) ÷ old. When input and output move together we also show the blended price, three parts input to one part output, which is the typical mix for chat and coding work. Same-day refreshes are combined, and moves under 1% are hidden as noise.
Is there an RSS or Atom feed?
Yes. /pricing-changes/feed.xml is an Atom feed with one entry per day that had changes, listing each model with its old and new prices. Any feed reader can follow it. It is rebuilt with the site after each daily data refresh, so it never needs your email address or an account.
I think a change is wrong. How do I report it?
Email hello@its-tahir.com with the model, the date and a link to the provider’s pricing page, or use the contact page. If our source was wrong, we add a correction with the source link, and the change disappears from this log because it was a data fix, not a price move.
Related
Related tools
- LLM API Cost CalculatorEstimate per-request, daily and monthly API costs.
- AI Model ComparisonCompare prices, context windows and features across models.
- AI Model Pricing PagesSpecs, real costs and cheaper alternatives for popular models.
- Batch API Savings CalculatorCompare batch and real-time API costs.
- Prompt Caching CalculatorEstimate savings from prompt caching.
- Subscription vs API CalculatorFind out whether a chat plan or the API is cheaper for you.