// pricing · September 2026

LLM API Pricing

Every model’s list price per 1M tokens — input, output and cached input — with context windows, LiveBench scores and what a real workload costs per month. Sort any column.

OpenRouter · refreshed every 15 minutesBest value modelsCheapest with tool calling

343 LLM API models are listed, with a median list price of $0.400 per 1M input tokens and $1.60 per 1M output tokens. Paid prices run from $0.022 (Mistral Nemo) to $262.50 (o1-pro) per 1M tokens blended. 23 have a free listing.

Models
343
23 with a free listing
Median input / 1M
$0.400
paid models
Median output / 1M
$1.60
paid models
Cheapest paid
$0.022
Mistral Nemo
Prompt caching
208
publish a cached-input price

Every model, every price

List prices in USD per 1M tokens. “Blended” is a 3:1 input:output mix; the per-month column prices the selected workload using each model's cached-input rate where it publishes one.

Showing 343 of 343 models · per-month column: 8K in / 600 out × 100K requests, 50% of input cached

LLM API list prices per 1M tokens, context windows and monthly workload cost
inclusionai/ling-3.0-flash-sante:freeFreeFreeFree262K$0
dots-studio/dots-3-note-preview:freeFreeFreeFree512K$0
liquid/lfm-2.5-2.6b:freeFreeFreeFree66K$0
cohere/north-mini-code:freeFreeFreeFree256K$0
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:freeFreeFreeFree256K$0
google/lyria-3-pro-previewFreeFreeFree1.0M$0
google/lyria-3-clip-previewFreeFreeFree1.0M$0
mistralai/mistral-nemo$0.019$0.030$0.022131K$17.00
inclusionai/ling-3.0-flash$0.021$0.063$0.0042$0.032262K$13.86
openai/gpt-oss-20b$0.018$0.090$0.036131K$19.80
ibm-granite/granite-4.0-h-micro$0.017$0.112$0.041131K$20.32
sao10k/l3-lunaris-8b$0.040$0.050$0.0428K$35.00
nex-agi/nex-n2.5-mini$0.025$0.100$0.0025$0.044262K$17.00
qwen/qwen3.7-flash$0.030$0.130$0.0060$0.0551M$22.20
mistralai/mistral-small-24b-instruct-2501$0.050$0.080$0.05733K$44.80
meta-llama/llama-3.1-8b-instruct$0.050$0.080$0.025$0.057131K$34.80
inference-net/schematron-v2-turbo$0.030$0.150$0.030$0.060128K$33.00
deepseek/deepseek-v4-flash$0.049$0.098$0.0098$0.0611.0M65.5$29.40
amazon/nova-micro-v1$0.035$0.140$0.061128K$36.40
google/gemma-3-4b-it$0.050$0.100$0.063131K$46.00
cohere/command-r7b-12-2024$0.037$0.150$0.066128K$39.00
inception/mercury-2.5$0.040$0.150$0.0040$0.068260K$26.60
meta-llama/llama-3.2-1b-instruct$0.027$0.201$0.07160K$33.66
poolside/laguna-xs-2.1$0.060$0.120$0.030$0.075262K$43.20
google/gemma-3-12b-it$0.050$0.150$0.075131K$49.00
tencent/hy-mt2-1.8b$0.044$0.177$0.0778K$45.82
qwen/qwen3-30b-a3b-instruct-2507$0.048$0.193$0.084262K$50.10
nvidia/nemotron-3-nano-30b-a3b$0.050$0.200$0.030$0.087262K$44.00
gryphe/mythomax-l2-13b$0.080$0.110$0.0878K$70.60
microsoft/phi-4$0.070$0.140$0.08816K$64.40
inclusionai/ling-3.0-flash-vl$0.060$0.180$0.012$0.090131K$39.60
inclusionai/ling-3.0-flash-fin$0.060$0.180$0.012$0.090262K$39.60
inference-net/schematron-v2-small$0.050$0.230$0.050$0.095128K$53.80
rekaai/reka-edge$0.100$0.100$0.10016K$86.00
mistralai/ministral-3b-2512$0.100$0.100$0.010$0.100131K$50.00
nvidia/nemotron-3.5-lightning$0.070$0.200$0.040$0.103262K$56.00
amazon/nova-lite-v1$0.060$0.240$0.105300K$62.40
ibm-granite/granite-4.2-8b$0.060$0.250$0.015$0.107131K$45.00
qwen/qwen3.5-9b$0.100$0.150$0.112262K$89.00
poolside/laguna-s-2.1$0.090$0.180$0.0090$0.1131.0M$50.40
qwen/qwen3.5-flash-02-23$0.065$0.260$0.1141M$67.60
nex-agi/nex-n2.5-pro$0.075$0.250$0.015$0.119262K$51.00
meta-llama/llama-3.2-3b-instruct$0.050$0.330$0.120131K$59.80
qwen/qwen3-coder-30b-a3b-instruct$0.070$0.280$0.123262K$72.80
meta/muse-spark-1.3-contributor$0.100$0.200$0.0020$0.1251.0M$52.80
meta/muse-spark-1.2-contributor$0.100$0.200$0.0020$0.1251.0M$52.80
bytedance/ui-tars-1.5-7b$0.100$0.200$0.100$0.125128K$92.00
rekaai/reka-flash-3$0.100$0.200$0.12566K$92.00
qwen/qwen-2.5-7b-instruct$0.100$0.200$0.12533K$92.00
tencent/hy-mt2-30b-a3b$0.074$0.295$0.1298K$76.90
tencent/hy-mt2-7b$0.074$0.295$0.1298K$76.90
qwen/qwen3-32b$0.080$0.280$0.130131K$80.80
bytedance-seed/seed-1.6-flash$0.075$0.300$0.131262K$78.00
openai/gpt-oss-safeguard-20b$0.075$0.300$0.037$0.131131K$63.00
mistralai/mistral-small-3.2-24b-instruct$0.094$0.250$0.133256K$90.00
openai/gpt-5-nano$0.050$0.400$0.0050$0.137400K$46.00
google/gemma-4-26b-a4b-it$0.090$0.300$0.050$0.143262K$74.00
tencent/hy3$0.083$0.330$0.021$0.144262K$61.05
z-ai/glm-4.7-flash$0.061$0.400$0.145200K$72.40
stepfun/step-3.5-flash$0.100$0.300$0.150262K$98.00
mistralai/ministral-8b-2512$0.150$0.150$0.015$0.150262K$75.00
mistralai/voxtral-small-24b-2507$0.100$0.300$0.010$0.15033K$62.00
qwen/qwen3-14b$0.120$0.240$0.150131K$110.40
meta-llama/llama-4-scout$0.100$0.300$0.1501.3M$98.00
google/gemma-4-31b-it$0.090$0.340$0.050$0.152262K$76.40
qwen/qwen3-235b-a22b-2507$0.087$0.350$0.018$0.153262K$63.00
meta-llama/llama-3.3-70b-instruct$0.100$0.320$0.155131K$99.20
upstage/solar-pro4$0.090$0.360$0.018$0.158524K$64.80
nvidia/nemotron-3-super-120b-a12b$0.080$0.450$0.172262K$91.00
google/gemma-3-27b-it$0.080$0.450$0.040$0.172131K$75.00
bytedance-seed/seed-2.0-mini$0.100$0.400$0.175262K$104.00
google/gemini-2.5-flash-lite$0.100$0.400$0.010$0.1751.0M$68.00
openai/gpt-4.1-nano$0.100$0.400$0.025$0.1751.0M$74.00
xiaomi/mimo-v2.6-flash$0.140$0.280$0.0028$0.1751.0M$73.92
xiaomi/mimo-v2.5$0.140$0.280$0.0028$0.1751.1M$73.92
meta-llama/llama-guard-4-12b$0.180$0.180$0.180164K$154.80
prism-ml/ternary-bonsai-2-27b$0.075$0.500$0.181262K$90.00
qwen/qwen3-vl-32b-instruct$0.104$0.416$0.182131K$108.16
deepseek/deepseek-v4-flash-0731$0.040$0.640$0.016$0.1901.3M74.2$60.80
nvidia/nemotron-3.5-content-safety$0.200$0.200$0.200131K$172.00
mistralai/ministral-14b-2512$0.200$0.200$0.020$0.200262K$100.00
openai/gpt-6-luna-pro$0.100$0.500$0.010$0.2001.1M$74.00
openai/gpt-6-luna$0.100$0.500$0.010$0.2001.1M72.0$74.00
deepseek/deepseek-v4.1-flash$0.100$0.500$0.010$0.2001.0M81.1$74.00
qwen/qwen3-vl-8b-instruct$0.117$0.455$0.202262K$120.90
qwen/qwen3-8b$0.117$0.455$0.202131K$120.90
qwen/qwen3-30b-a3b$0.120$0.500$0.215131K$126.00
qwen/qwen3-vl-30b-a3b-instruct$0.130$0.520$0.228262K$135.20
qwen/qwen3.8-omni-flash$0.150$0.470$0.016$0.2301M$94.60
qwen/qwen3.8-flash$0.150$0.470$0.016$0.2301M$94.60
z-ai/glm-5.3-flash$0.150$0.500$0.050$0.2371.3M71.6$110.00
tencent/hunyuan-a13b-instruct$0.140$0.570$0.248131K$146.20
mistralai/mistral-small-2603$0.150$0.600$0.015$0.262262K$102.00
upstage/solar-pro-3$0.150$0.600$0.015$0.262131K$102.00
openai/gpt-oss-120b$0.150$0.600$0.075$0.262131K$126.00
cohere/command-r-08-2024$0.150$0.600$0.262128K$156.00
openai/gpt-4o-mini$0.150$0.600$0.075$0.262128K$126.00
openai/gpt-4o-mini-2024-07-18$0.150$0.600$0.075$0.262128K$126.00
tencent/hy3-preview$0.180$0.600$0.060$0.285262K$132.00
qwen/qwen3-coder-next$0.120$0.800$0.070$0.290262K$124.00
mistralai/mistral-saba$0.200$0.600$0.020$0.30033K$124.00
deepseek/deepseek-v3.2$0.269$0.400$0.134$0.302164K$185.40
meta-llama/llama-4-maverick$0.188$0.652$0.3041.0M$189.15
deepseek/deepseek-v3.2-exp$0.270$0.410$0.305164K$240.60
z-ai/glm-4.5-air$0.130$0.850$0.025$0.310131K$113.00
deepseek/deepseek-v4-flash-vision-exp$0.220$0.660$0.0070$0.3301.0M76.8$130.40
qwen/qwen3-next-80b-a3b-instruct$0.090$1.10$0.343262K$138.00
thedrummer/cydonia-24b-v4.1$0.300$0.500$0.150$0.350131K$210.00
qwen/qwen3.6-35b-a3b$0.150$1.00$0.050$0.362262K$140.00
qwen/qwen-2.5-72b-instruct$0.360$0.400$0.37033K$312.00
inception/mercury-2$0.250$0.750$0.025$0.375128K$155.00
mistralai/mistral-large-2512:batch$0.250$0.750$0.025$0.375262K$155.00
cognitivecomputations/dolphin-mistral-24b-venice-edition$0.200$0.900$0.375128K$214.00
arcee-ai/trinity-large-thinking$0.250$0.800$0.060$0.387262K$172.00
qwen/qwen3-coder-flash$0.195$0.975$0.039$0.3901M$152.10
qwen/qwen-plus-2025-07-28$0.260$0.780$0.3901M$254.80
qwen/qwen-plus$0.260$0.780$0.052$0.3901M$171.60
thedrummer/unslopnemo-12b$0.400$0.400$0.4001.0M$344.00
meta-llama/llama-3.1-70b-instruct$0.400$0.400$0.400131K$344.00
mistralai/mistral-small-3.1-24b-instruct$0.351$0.555$0.402128K$314.10
qwen/qwen3-next-80b-a3b-thinking$0.150$1.20$0.412262K$192.00
qwen/qwen3.6-flash$0.188$1.13$0.4221M$217.50
undi95/remm-slerp-l2-13b$0.350$0.650$0.4256K$319.00
deepseek/deepseek-chat-v3.1$0.250$0.950$0.130$0.425164K$209.00
minimax/minimax-01$0.200$1.10$0.4251.0M$226.00
stepfun/step-3.7-flash$0.200$1.15$0.040$0.438262K$165.00
deepseek/deepseek-chat-v3-0324$0.250$1.00$0.438164K$260.00
minimax/minimax-m2$0.255$1.02$0.446205K$265.20
openai/gpt-5.6-luna-pro$0.200$1.20$0.020$0.4501.1M$160.00
openai/gpt-5.6-luna$0.200$1.20$0.020$0.4501.1M73.6$160.00
z-ai/glm-4.6v$0.300$0.900$0.055$0.450131K$196.00
mistralai/codestral-2508$0.300$0.900$0.030$0.450256K$186.00
deepseek/deepseek-v3.1-terminus$0.270$1.00$0.135$0.453164K$222.00
deepseek/deepseek-chat$0.320$0.890$0.462164K$309.40
openai/gpt-5.4-nano$0.200$1.25$0.020$0.463400K69.6$163.00
minimax/minimax-m2.5$0.270$1.08$0.027$0.473205K$183.60
qwen/qwen3-coder$0.300$1.00$0.100$0.475262K$220.00
perceptron/perceptron-mk1$0.150$1.50$0.48733K$210.00
mancer/weaver$0.400$0.750$0.4878K$365.00
anthropic/claude-3-haiku$0.250$1.25$0.030$0.500200K$187.00
meta/muse-glimmer-30b$0.300$1.20$0.040$0.525131K$208.00
meituan/longcat-2.0$0.300$1.20$0.0060$0.5251.0M$194.40
minimax/minimax-m3$0.300$1.20$0.060$0.5251.0M67.3$216.00
minimax/minimax-m2.7$0.300$1.20$0.060$0.525205K$216.00
minimax/minimax-m2-her$0.300$1.20$0.030$0.52566K$204.00
minimax/minimax-m2.1$0.300$1.20$0.030$0.525205K$204.00
qwen/qwen3.5-27b$0.195$1.56$0.536262K$249.60
xiaomi/mimo-v2.6-pro$0.435$0.870$0.0036$0.5441.0M$227.64
xiaomi/mimo-v2.5-pro$0.435$0.870$0.0036$0.5441.1M$227.64
qwen/qwen3.5-35b-a3b$0.313$1.25$0.156$0.547262K$262.50
qwen/qwen3.7-plus$0.320$1.28$0.064$0.5601M$230.40
google/gemini-3.1-flash-lite-image$0.250$1.50$0.56366K$290.00
google/gemini-3.1-flash-lite$0.250$1.50$0.025$0.5631.0M$200.00
google/gemini-3.1-flash-lite-preview$0.250$1.50$0.025$0.5631.0M$200.00
qwen/qwen3.5-plus-02-15$0.260$1.56$0.5851M$301.60
z-ai/glm-5.3-flashx$0.370$1.25$0.075$0.5901.0M$253.00
thedrummer/skyfall-36b-v2$0.550$0.800$0.250$0.61333K$368.00
microsoft/wizardlm-2-8x22b$0.620$0.620$0.62066K$533.20
baidu/ernie-4.5-vl-424b-a47b$0.420$1.25$0.627123K$411.00
qwen/qwen3-vl-235b-a22b-instruct$0.210$1.90$0.100$0.632262K$238.00
thinkingmachines/inkling-small$0.450$1.20$0.100$0.6371.0M$292.00
google/gemma-2-27b-it$0.650$0.650$0.6508K$559.00
qwen/qwen3-vl-8b-thinking$0.180$2.10$0.660131K$270.00
qwen/qwen3.5-plus-20260420$0.300$1.80$0.6751M$348.00
sao10k/l3.3-euryale-70b$0.650$0.750$0.675131K$565.00
bytedance-seed/seed-2.0-lite$0.250$2.00$0.688262K$320.00
bytedance-seed/seed-1.6$0.250$2.00$0.688262K$320.00
openai/gpt-5.1-codex-mini$0.250$2.00$0.030$0.688400K$232.00
openai/gpt-5-mini$0.250$2.00$0.025$0.688400K$230.00
openai/gpt-4.1-mini$0.400$1.60$0.100$0.7001.0M$296.00
nousresearch/hermes-3-llama-3.1-70b$0.700$0.700$0.700131K$602.00
qwen/qwen3.5-122b-a10b$0.260$2.08$0.715262K$332.80
qwen/qwen3.6-plus$0.325$1.95$0.7311M68.9$377.00
z-ai/glm-4.7$0.400$1.75$0.080$0.738205K$297.00
qwen/qwen-2.5-coder-32b-instruct$0.660$1.00$0.74533K$588.00
qwen/qwen3-235b-a22b-thinking-2507$0.230$2.30$0.747131K$322.00
qwen/qwen3-vl-30b-a3b-thinking$0.200$2.40$0.750262K$304.00
qwen/qwen3-30b-a3b-thinking-2507$0.200$2.40$0.75082K$304.00
openai/gpt-3.5-turbo$0.500$1.50$0.75016K$490.00
z-ai/glm-4.6$0.430$1.75$0.080$0.760205K$309.00
qwen/qwen3-235b-a22b$0.455$1.82$0.796131K$473.20
deepseek/deepseek-r1-distill-llama-70b$0.800$0.800$0.8008K$688.00
mistralai/devstral-2512$0.400$2.00$0.040$0.800262K$296.00
mistralai/mistral-medium-3.1$0.400$2.00$0.040$0.800131K$296.00
mistralai/mistral-medium-3$0.400$2.00$0.040$0.800131K$296.00
google/gemini-3.5-flash-lite$0.300$2.50$0.030$0.8501.0M63.9$282.00
amazon/nova-2-lite-v1$0.300$2.50$0.8501M$390.00
google/gemini-2.5-flash-image$0.300$2.50$0.030$0.85033K$282.00
google/gemini-2.5-flash$0.300$2.50$0.030$0.8501.0M$282.00
qwen/qwen2.5-vl-72b-instruct$0.800$1.00$0.400$0.850128K$540.00
sao10k/l3.1-euryale-70b$0.850$0.850$0.850131K$731.00
minimax/minimax-m1$0.400$2.20$0.8501M$452.00
z-ai/glm-5.3$0.561$1.76$0.104$0.8621.3M76.1$372.13
aion-labs/aion-3.0-mini$0.700$1.40$0.180$0.875131K$436.00
moonshotai/kimi-k2.5$0.450$2.25$0.070$0.900262K$343.00
z-ai/glm-4.5v$0.600$1.80$0.110$0.90066K$392.00
morph/morph-v3-fast$0.800$1.20$0.90082K$712.00
deepseek/deepseek-r1-0528$0.500$2.15$0.350$0.913164K$469.00
qwen/qwen3.6-27b$0.320$2.70$0.150$0.915262K64.0$350.00
z-ai/glm-5$0.600$1.92$0.120$0.930205K$403.20
relace/relace-apply-3$0.850$1.25$0.950256K$755.00
deepseek/deepseek-v4-pro-0813$0.660$1.98$0.022$0.9901.0M77.4$391.60
z-ai/glm-5.2$0.650$2.04$0.121$0.9981.0M73.2$430.59
bytedance-seed/seed-2-1-turbo$0.500$2.50$1.00262K$550.00
aion-labs/aion-2.0$0.800$1.60$0.200$1.00131K$496.00
z-ai/glm-4.5$0.600$2.20$0.110$1.00131K$416.00
aion-labs/aion-rp-llama-3.1-8b$0.800$1.60$1.0033K$736.00
perplexity/sonar$1.00$1.00$1.00127K$860.00
nousresearch/hermes-3-llama-3.1-405b$1.00$1.00$1.00131K$860.00
moonshotai/kimi-k2$0.570$2.30$1.00131K$594.00
nvidia/nemotron-3-ultra-550b-a55b$0.600$2.40$0.120$1.05262K67.4$432.00
openai/gpt-audio-mini$0.600$2.40$1.05128K$624.00
qwen/qwen3.8-27b$0.420$3.00$0.085$1.061M75.3$382.00
moonshotai/kimi-k2-thinking$0.600$2.50$0.150$1.07262K$450.00
moonshotai/kimi-k2-0905$0.600$2.50$1.07262K$630.00
deepseek/deepseek-v4-pro$0.865$1.73$0.072$1.081.0M71.6$478.80
bytedance-seed/seed-2.0-code$0.500$3.00$1.13262K$580.00
google/gemini-3.1-flash-image$0.500$3.00$1.13131K$580.00
google/gemini-3.1-flash-image-preview$0.500$3.00$1.1366K$580.00
google/gemini-3-flash-preview$0.500$3.00$0.050$1.131.0M$400.00
morph/morph-v3-large$0.900$1.90$1.15262K$834.00
deepseek/deepseek-r1$0.700$2.50$1.1564K$710.00
x-ai/grok-build-0.1$1.00$2.00$0.200$1.25256K67.8$600.00
openai/gpt-3.5-turbo-0613$1.00$2.00$1.254K$920.00
tencent/hy4-preview$0.834$2.50$0.042$1.251.0M$500.46
qwen/qwen3.5-397b-a17b$0.550$3.50$0.225$1.29262K$520.00
kwaipilot/kat-coder-pro-v2.5$0.740$2.96$0.150$1.29262K$533.60
qwen/qwen3-vl-235b-a22b-thinking$0.400$4.00$1.30131K$560.00
qwen/qwen3-coder-plus$0.650$3.25$0.130$1.301M$507.00
moonshotai/kimi-k2.7-code$0.706$3.30$0.180$1.35262K68.4$552.48
amazon/nova-pro-v1$0.800$3.20$1.40300K$832.00
z-ai/glm-5.1$0.966$3.04$0.179$1.48205K$640.32
google/gemini-3.8-flash$0.750$3.75$0.075$1.501.0M75.8$555.00
google/gemini-3.7-flash$0.750$3.75$0.075$1.501.0M78.8$555.00
google/gemini-3.6-flash$0.750$3.75$0.075$1.501.0M73.6$555.00
relace/relace-search$1.00$3.00$1.50256K$980.00
nousresearch/hermes-4-405b$1.00$3.00$1.50131K$980.00
qwen/qwen3-max-thinking$0.780$3.90$1.56262K$858.00
qwen/qwen3-max$0.780$3.90$0.156$1.56262K$608.40
x-ai/grok-4.3$1.25$2.50$0.200$1.561M62.2$730.00
x-ai/grok-4.20-multi-agent$1.25$2.50$0.200$1.562M$730.00
x-ai/grok-4.20$1.25$2.50$0.200$1.562M$730.00
openai/gpt-3.5-turbo-instruct$1.50$2.00$1.634K$1,320
openai/gpt-5.4-mini$0.750$4.50$0.075$1.69400K66.4$600.00
sakana/sakana-namazu$0.950$4.00$0.150$1.71262K$680.00
moonshotai/kimi-k2.6$0.950$4.00$0.160$1.71262K70.5$684.00
thinkingmachines/inkling$1.00$4.05$0.170$1.761.0M71.9$711.00
z-ai/glm-5v-turbo$1.20$4.00$0.240$1.90203K$816.00
z-ai/glm-5-turbo$1.20$4.00$0.240$1.90203K$816.00
openai/o4-mini-high$1.10$4.40$0.275$1.93200K$814.00
openai/o4-mini$1.10$4.40$0.275$1.93200K$814.00
openai/o3-mini-high$1.10$4.40$0.550$1.93200K$924.00
openai/o3-mini$1.10$4.40$0.550$1.93200K$924.00
writer/palmyra-x5$0.600$6.00$1.951.0M$840.00
meta/muse-spark-1.3$1.25$4.25$0.150$2.001.0M81.6$815.00
meta/muse-spark-1.2$1.25$4.25$0.150$2.001.0M78.0$815.00
meta/muse-spark-1.1$1.25$4.25$0.150$2.001.0M75.3$815.00
anthropic/claude-haiku-4.5$1.00$5.00$0.100$2.00200K$740.00
qwen/qwen3.7-max$1.48$4.42$0.295$2.211M73.1$973.50
qwen/qwen3.6-max-preview$1.03$6.16$2.31262K$1,191
openai/gpt-5-image-mini$2.50$2.00$0.250$2.38400K$1,220
x-ai/grok-4.7$1.60$4.80$0.400$2.40500K77.4$1,088
sakana/fugu-max$2.00$6.00$0.250$3.001M$1,260
qwen/qwen3.8-max-0902$2.00$6.00$0.250$3.001M$1,260
qwen/qwen3.8-2.4t-a95b$2.00$6.00$0.250$3.001.0M$1,260
x-ai/grok-4.6$2.00$6.00$0.500$3.00500K78.0$1,360
x-ai/grok-4.5$2.00$6.00$0.300$3.00500K75.8$1,280
mistralai/mistral-medium-3-5$1.50$7.50$3.00262K$1,650
mistralai/mistral-large-2407$2.00$6.00$0.200$3.00131K$1,240
mistralai/mixtral-8x22b-instruct$2.00$6.00$0.200$3.0066K$1,240
mistralai/mistral-large$2.00$6.00$0.200$3.00128K$1,240
anthracite-org/magnum-v4-72b$2.50$5.00$3.1333K$2,300
openai/gpt-3.5-turbo-16k$3.00$4.00$3.2516K$2,640
google/gemini-3.5-flash$1.50$9.00$0.150$3.381.0M74.6$1,200
openai/gpt-5.1-codex-max$1.25$10.00$0.125$3.44400K$1,150
openai/gpt-5.1$1.25$10.00$0.125$3.44400K$1,150
openai/gpt-5.1-codex$1.25$10.00$0.130$3.44400K$1,152
openai/gpt-5$1.25$10.00$0.125$3.44400K$1,150
google/gemini-2.5-pro$1.25$10.00$0.125$3.441.0M$1,150
google/gemini-2.5-pro-preview$1.25$10.00$0.125$3.441.0M$1,150
openai/o3$2.00$8.00$0.500$3.50200K$1,480
openai/gpt-4.1$2.00$8.00$0.500$3.501.0M$1,480
perplexity/sonar-reasoning-pro$2.00$8.00$3.50128K$2,080
perplexity/sonar-deep-research$2.00$8.00$3.50128K$2,080
unbiased/pareto$2.50$7.50$0.250$3.75262K$1,550
aion-labs/aion-3.0$3.00$6.00$0.750$3.75131K$1,860
openai/gpt-6-sol-pro$2.00$10.00$0.200$4.001.1M$1,480
openai/gpt-6-sol$2.00$10.00$0.200$4.001.1M79.2$1,480
openai/gpt-5.6-sol-pro$2.00$10.00$0.200$4.001.1M$1,480
openai/gpt-5.6-sol$2.00$10.00$0.200$4.001.1M81.1$1,480
anthropic/claude-sonnet-5$2.00$10.00$0.200$4.001M76.0$1,480
openai/gpt-audio$2.50$10.00$4.38128K$2,600
cohere/command-a$2.50$10.00$4.38256K$2,600
openai/gpt-4o-2024-11-20$2.50$10.00$1.25$4.38128K$2,100
cohere/command-r-plus-08-2024$2.50$10.00$4.38128K$2,600
openai/gpt-4o-2024-08-06$2.50$10.00$1.25$4.38128K$2,100
openai/gpt-4o$2.50$10.00$1.25$4.38128K$2,100
openai/gpt-5.6-terra-pro$2.00$12.00$0.200$4.501.1M$1,600
openai/gpt-5.6-terra$2.00$12.00$0.200$4.501.1M77.9$1,600
google/gemini-3-pro-image$2.00$12.00$0.200$4.50131K$1,600
google/gemini-3.1-pro-preview-customtools$2.00$12.00$0.200$4.501.0M$1,600
google/gemini-3.1-pro-preview$2.00$12.00$0.200$4.501.0M77.0$1,600
google/gemini-3-pro-image-preview$2.00$12.00$0.200$4.5066K$1,600
openai/gpt-5.3-codex$1.75$14.00$0.175$4.81400K$1,610
openai/gpt-5.2-codex$1.75$14.00$0.175$4.81400K74.0$1,610
openai/gpt-5.2-chat$1.75$14.00$0.175$4.81128K$1,610
openai/gpt-5.2$1.75$14.00$0.175$4.81400K74.6$1,610
amazon/nova-premier-v1$2.50$12.50$0.625$5.001M$2,000
xiaomi/mimo-v2.6-pro-ultraspeed$4.35$8.70$0.036$5.441.0M$2,276
openai/gpt-5.4$2.50$15.00$0.250$5.631.1M78.0$2,000
moonshotai/kimi-k3$3.00$15.00$0.300$6.001.0M79.2$2,220
anthropic/claude-sonnet-4.6$3.00$15.00$0.300$6.001M73.0$2,220
perplexity/sonar-pro-search$3.00$15.00$6.00200K$3,300
anthropic/claude-sonnet-4.5$3.00$15.00$0.300$6.001M$2,220
anthropic/claude-sonnet-4$3.00$15.00$0.300$6.00200K$2,220
perplexity/sonar-pro$3.00$15.00$6.00200K$3,300
openai/gpt-4o-2024-05-13$5.00$15.00$7.50128K$4,900
anthropic/claude-opus-5.5$4.00$20.00$0.200$8.001M83.2$2,880
openai/gpt-5.4-image-2$8.00$15.00$2.00$9.75272K$4,900
anthropic/claude-opus-5$5.00$25.00$0.500$10.001M80.1$3,700
anthropic/claude-opus-4.8$5.00$25.00$0.500$10.001M76.2$3,700
anthropic/claude-opus-4.7$5.00$25.00$0.500$10.001M76.5$3,700
anthropic/claude-opus-4.6$5.00$25.00$0.500$10.001M74.5$3,700
anthropic/claude-opus-4.5$5.00$25.00$0.500$10.00200K72.6$3,700
openai/gpt-5-image$10.00$10.00$1.25$10.00400K$5,100
sakana/fugu-ultra-v2$5.00$30.00$0.500$11.251M$4,000
sakana/fugu-ultra$5.00$30.00$0.500$11.251M$4,000
openai/gpt-chat-latest$5.00$30.00$0.500$11.25400K$4,000
openai/gpt-5.5$5.00$30.00$0.500$11.251.1M80.2$4,000
openai/gpt-4-turbo$10.00$30.00$15.00128K$9,800
openai/gpt-6-astra$10.00$50.00$1.00$20.001.1M82.2$7,400
openai/gpt-6-astra-pro$10.00$50.00$1.00$20.001.1M$7,400
anthropic/claude-fable-5.1$10.00$50.00$0.250$20.001M83.4$7,100
anthropic/claude-fable-5$10.00$50.00$1.00$20.001M83.0$7,400
openai/o1$15.00$60.00$7.50$26.25200K$12,600
anthropic/claude-opus-4.1$15.00$75.00$1.50$30.00200K$11,100
openai/o3-pro$20.00$80.00$35.00200K$20,800
openai/gpt-4$30.00$60.00$37.508K$27,600
openai/gpt-5-pro$15.00$120.00$41.25400K$19,200
openai/gpt-5.2-pro$21.00$168.00$57.75400K$26,880
openai/gpt-5.5-pro$30.00$180.00$67.501.1M$34,800
openai/gpt-5.4-pro$30.00$180.00$67.501.1M$34,800
openai/o1-pro$150.00$600.00$262.50200K$156,000
Price your own workload

LLM pricing FAQ

What is the cheapest LLM API?

Mistral Nemo is the cheapest paid model, at $0.019 per 1M input tokens and $0.030 per 1M output tokens. 23 models also have a free listing, usually with tighter rate limits.

How much does the most capable LLM cost?

The highest LiveBench overall score belongs to Claude Fable 5.1 (83.4), priced at $10.00 input and $50.00 output per 1M tokens. A RAG assistant at 100K requests a month would list at about $7,100.

Why do output tokens cost more than input tokens?

Generating a token takes a full forward pass per token, while input is processed in parallel. Across the paid models listed here the median output price is $1.60 per 1M against $0.400 for input — reasoning tokens bill as output too.

Which models support prompt caching?

208 of 343 publish a separate cached-input price, which bills repeated prompt prefixes at a fraction of the normal input rate. Filter the table by "Caching" to see them.

How current are these prices?

List prices are pulled from OpenRouter’s public models API and refreshed every 15 minutes. Batch discounts and enterprise pricing are not included.

Pricing by provider

What these prices include

  • List prices from OpenRouter's public models API, which mirrors provider pricing. Batch discounts and negotiated enterprise rates are not included.
  • Variants:free and :batch listings are folded into their base model; its model page lists them.
  • Per-month cost is a floor: tokens you describe times list price. Cache writes and reasoning-token volume depend on your workload.