modelgrep

LLM pricing comparison

Match · Updated July 2026

The cheapest paid LLM API right now is Ling-2.6-flash at $0.010 per million input tokens, the top-ranked model, Claude Fable 5, costs $10.00/M in and $50.00/M out, and 17 models have a free tier. Every price below is live, per million tokens, from the cheapest provider serving each model.

Live API pricing for every tracked model, in dollars per million tokens, sorted cheapest-first. Blended cost assumes the conventional 3:1 input:output ratio. Estimate a real workload with the pricing calculator, or jump straight to the cheapest models and free models rankings.

ModelInput $/MOutput $/MBlended $/MContext
ling-2.6-flash
inclusionai
$0.010$0.030$0.015262K
granite-4.0-h-micro
ibm-granite
$0.017$0.112$0.041131K
mistral-nemo
mistralai
$0.019$0.030$0.022131K
nex-n2-mini
nex-agi
$0.025$0.100$0.044262K
llama-3.2-1b-instruct
meta-llama
$0.027$0.201$0.07160K
gpt-oss-20b
openai
$0.029$0.140$0.057131K
nova-micro-v1
amazon
$0.035$0.140$0.061128K
gpt-oss-120b
openai
$0.037$0.170$0.070131K
command-r7b-12-2024
cohere
$0.037$0.150$0.066128K
qwen-2.5-7b-instruct
qwen
$0.040$0.100$0.05533K
l3-lunaris-8b
sao10k
$0.040$0.050$0.0428K
granite-4.1-8b
ibm-granite
$0.050$0.100$0.063131K
nemotron-3-nano-30b-a3b
nvidia
$0.050$0.200$0.088262K
gpt-5-nano
openai
$0.050$0.400$0.138400K
gemma-3-4b-it
google
$0.050$0.100$0.063131K
gemma-3-12b-it
google
$0.050$0.150$0.075131K
mistral-small-24b-instruct-2501
mistralai
$0.050$0.080$0.05833K
llama-3.2-3b-instruct
meta-llama
$0.050$0.330$0.120131K
llama-3.1-8b-instruct
meta-llama
$0.050$0.080$0.058131K
laguna-xs-2.1
poolside
$0.060$0.120$0.075262K
glm-4.7-flash
z-ai
$0.060$0.400$0.145203K
gemma-3n-e4b-it
google
$0.060$0.120$0.07533K
nova-lite-v1
amazon
$0.060$0.240$0.105300K
mythomax-l2-13b
gryphe
$0.060$0.060$0.0608K
hy3-preview
tencent
$0.063$0.210$0.100262K
qwen3.5-flash-02-23
qwen
$0.065$0.260$0.1141M
qwen3-coder-30b-a3b-instruct
qwen
$0.070$0.270$0.120262K
phi-4
microsoft
$0.070$0.140$0.08816K
ring-2.6-1t
inclusionai
$0.075$0.625$0.212262K
ling-2.6-1t
inclusionai
$0.075$0.625$0.212262K
seed-1.6-flash
bytedance-seed
$0.075$0.300$0.131262K
gpt-oss-safeguard-20b
openai
$0.075$0.300$0.131131K
nemotron-3-super-120b-a12b
nvidia
$0.080$0.450$0.1721M
qwen3-32b
qwen
$0.080$0.280$0.130131K
gemma-3-27b-it
google
$0.080$0.450$0.172262K
qwen3-235b-a22b-2507
qwen
$0.090$0.550$0.205262K
qwen3-next-80b-a3b-thinking
qwen
$0.098$0.780$0.268262K
deepseek-v4-flash
deepseek
$0.098$0.196$0.1231.0M
laguna-s-2.1
poolside
$0.100$0.200$0.1251.0M
reka-edge
rekaai
$0.100$0.100$0.10016K
qwen3.5-9b
qwen
$0.100$0.150$0.113262K
seed-2.0-mini
bytedance-seed
$0.100$0.400$0.175262K
step-3.5-flash
stepfun
$0.100$0.300$0.150262K
ministral-3b-2512
mistralai
$0.100$0.100$0.100131K
voxtral-small-24b-2507
mistralai
$0.100$0.300$0.15032K
qwen3-30b-a3b-instruct-2507
qwen
$0.100$0.300$0.150262K
ui-tars-1.5-7b
bytedance
$0.100$0.200$0.125128K
gemini-2.5-flash-lite
google
$0.100$0.400$0.1751.0M
mistral-small-3.2-24b-instruct
mistralai
$0.100$0.300$0.150256K
gpt-4.1-nano
openai
$0.100$0.400$0.1751.0M
llama-4-scout
meta-llama
$0.100$0.300$0.1501.3M
reka-flash-3
rekaai
$0.100$0.200$0.12566K
qwen3-vl-32b-instruct
qwen
$0.104$0.416$0.182131K
qwen3-coder-next
qwen
$0.110$0.800$0.283262K
qwen3-vl-8b-thinking
qwen
$0.117$1.36$0.429131K
qwen3-vl-8b-instruct
qwen
$0.117$0.455$0.202262K
qwen3-8b
qwen
$0.117$0.455$0.202131K
gemma-4-26b-a4b-it
google
$0.120$0.350$0.177262K
qwen3-vl-30b-a3b-thinking
qwen
$0.130$1.56$0.488262K
qwen3-30b-a3b-thinking-2507
qwen
$0.130$1.56$0.48882K
hermes-4-70b
nousresearch
$0.130$0.400$0.198131K
glm-4.5-air
z-ai
$0.130$0.850$0.310131K
qwen3-30b-a3b
qwen
$0.130$0.520$0.228131K
llama-3.3-70b-instruct
meta-llama
$0.130$0.400$0.198131K
hy3
tencent
$0.132$0.528$0.231262K
qwen3.6-35b-a3b
qwen
$0.140$1.00$0.355262K
mimo-v2.5
xiaomi
$0.140$0.280$0.1751.1M
gemma-4-31b-it
google
$0.140$0.400$0.205262K
qwen3.5-35b-a3b
qwen
$0.140$1.00$0.355262K
hunyuan-a13b-instruct
tencent
$0.140$0.570$0.247131K
kat-coder-air-v2.5
kwaipilot
$0.150$0.600$0.262256K
perceptron-mk1
perceptron
$0.150$1.50$0.48733K
mistral-small-2603
mistralai
$0.150$0.600$0.262262K
minimax-m2.5
minimax
$0.150$0.900$0.338205K
solar-pro-3
upstage
$0.150$0.600$0.262128K
ministral-8b-2512
mistralai
$0.150$0.150$0.150262K
olmo-3-32b-think
allenai
$0.150$0.500$0.23766K
qwen3-vl-30b-a3b-instruct
qwen
$0.150$0.600$0.262262K
qwen3-next-80b-a3b-instruct
qwen
$0.150$1.20$0.412262K
gpt-4o-mini-search-preview
openai
$0.150$0.600$0.262128K
command-r-08-2024
cohere
$0.150$0.600$0.262128K
gpt-4o-mini
openai
$0.150$0.600$0.262128K
gpt-4o-mini-2024-07-18
openai
$0.150$0.600$0.262128K
llama-guard-4-12b
meta-llama
$0.180$0.180$0.1801.0M
qwen3.6-flash
qwen
$0.188$1.13$0.4221M
qwen3.5-27b
qwen
$0.195$1.56$0.536262K
qwen3-coder-flash
qwen
$0.195$0.975$0.3901M
step-3.7-flash
stepfun
$0.200$1.15$0.438262K
laguna-m.1
poolside
$0.200$0.400$0.250262K
gpt-5.4-nano
openai
$0.200$1.25$0.463400K
ministral-14b-2512
mistralai
$0.200$0.200$0.200262K
dolphin-mistral-24b-venice-edition
cognitivecomputations
$0.200$0.900$0.375128K
llama-4-maverick
meta-llama
$0.200$0.800$0.3501.0M
mistral-saba
mistralai
$0.200$0.600$0.30033K
minimax-01
minimax
$0.200$1.10$0.4251.0M
deepseek-chat
deepseek
$0.200$0.800$0.350164K
qwen3-vl-235b-a22b-instruct
qwen
$0.210$1.90$0.632262K
qwen3-14b
qwen
$0.228$0.910$0.398131K
gemini-3.1-flash-lite-image
google
$0.250$1.50$0.56366K
nex-n2-pro
nex-agi
$0.250$1.00$0.438262K
gemini-3.1-flash-lite
google
$0.250$1.50$0.5631.0M
trinity-large-thinking
arcee-ai
$0.250$0.800$0.388262K
minimax-m2.7
minimax
$0.250$1.00$0.438205K
seed-2.0-lite
bytedance-seed
$0.250$2.00$0.688262K
mercury-2
inception
$0.250$0.750$0.375128K
gemini-3.1-flash-lite-preview
google
$0.250$1.50$0.5631.0M
seed-1.6
bytedance-seed
$0.250$2.00$0.688262K
gpt-5.1-codex-mini
openai
$0.250$2.00$0.688400K
deepseek-chat-v3.1
deepseek
$0.250$0.950$0.425164K
gpt-5-mini
openai
$0.250$2.00$0.688400K
rocinante-12b
thedrummer
$0.250$0.500$0.31366K
claude-3-haiku
anthropic
$0.250$1.25$0.500200K
minimax-m2
minimax
$0.255$1.02$0.446205K
qwen3.5-122b-a10b
qwen
$0.260$2.08$0.715262K
qwen3.5-plus-02-15
qwen
$0.260$1.56$0.5851M
qwen3-vl-235b-a22b-thinking
qwen
$0.260$2.60$0.845131K
qwen-plus-2025-07-28
qwen
$0.260$0.780$0.3901M
qwen-plus-2025-07-28:thinking
qwen
$0.260$0.780$0.3901M
qwen-plus
qwen
$0.260$0.780$0.3901M
deepseek-v3.2
deepseek
$0.269$0.400$0.302164K
deepseek-v3.2-exp
deepseek
$0.270$0.410$0.305164K
deepseek-v3.1-terminus
deepseek
$0.270$1.00$0.453164K
deepseek-chat-v3-0324
deepseek
$0.270$1.12$0.483164K
qwen3.6-27b
qwen
$0.288$2.40$0.816262K
gemini-3.5-flash-lite
google
$0.300$2.50$0.8501.0M
longcat-2.0
meituan
$0.300$1.20$0.5251.0M
minimax-m3
minimax
$0.300$1.20$0.5251.0M
qwen3.5-plus-20260420
qwen
$0.300$1.80$0.6751M
kat-coder-pro-v2
kwaipilot
$0.300$1.20$0.525262K
minimax-m2-her
minimax
$0.300$1.20$0.52566K
minimax-m2.1
minimax
$0.300$1.20$0.525205K
glm-4.6v
z-ai
$0.300$0.900$0.450131K
nova-2-lite-v1
amazon
$0.300$2.50$0.8501M
gemini-2.5-flash-image
google
$0.300$2.50$0.85033K
cydonia-24b-v4.1
thedrummer
$0.300$0.500$0.350131K
codestral-2508
mistralai
$0.300$0.900$0.450256K
qwen3-235b-a22b-thinking-2507
qwen
$0.300$3.00$0.975262K
qwen3-coder
qwen
$0.300$1.00$0.475262K
gemini-2.5-flash
google
$0.300$2.50$0.8501.0M
qwen3.7-plus
qwen
$0.320$1.28$0.5601M
qwen3.6-plus
qwen
$0.325$1.95$0.7311M
mistral-small-3.1-24b-instruct
mistralai
$0.351$0.555$0.402128K
qwen-2.5-72b-instruct
qwen
$0.360$0.400$0.37033K
qwen3.5-397b-a17b
qwen
$0.390$2.34$0.877262K
glm-4.7
z-ai
$0.400$1.75$0.738205K
devstral-2512
mistralai
$0.400$2.00$0.800262K
mistral-medium-3.1
mistralai
$0.400$2.00$0.800131K
mistral-medium-3
mistralai
$0.400$2.00$0.800131K
gpt-4.1-mini
openai
$0.400$1.60$0.7001.0M
unslopnemo-12b
thedrummer
$0.400$0.400$0.40033K
llama-3.1-70b-instruct
meta-llama
$0.400$0.400$0.400131K
ernie-4.5-vl-424b-a47b
baidu
$0.420$1.25$0.627123K
deepseek-v4-pro
deepseek
$0.435$0.870$0.5441.0M
mimo-v2.5-pro
xiaomi
$0.435$0.870$0.5441.1M
remm-slerp-l2-13b
undi95
$0.450$0.650$0.5006K
qwen3-235b-a22b
qwen
$0.455$1.82$0.796131K
gemini-3.1-flash-image
google
$0.500$3.00$1.13131K
nemotron-3-ultra-550b-a55b
nvidia
$0.500$2.20$0.925512K
gemini-3.1-flash-image-preview
google
$0.500$3.00$1.13131K
gemini-3-flash-preview
google
$0.500$3.00$1.131.0M
mistral-large-2512
mistralai
$0.500$1.50$0.750262K
glm-4.6
z-ai
$0.500$2.00$0.875205K
deepseek-r1-0528
deepseek
$0.500$2.15$0.912164K
weaver
mancer
$0.500$0.750$0.5638K
gpt-3.5-turbo
openai
$0.500$1.50$0.75016K
minimax-m1
minimax
$0.550$2.20$0.9631M
skyfall-36b-v2
thedrummer
$0.550$0.800$0.61333K
kimi-k2.5
moonshotai
$0.570$2.85$1.14262K
kimi-k2
moonshotai
$0.570$2.30$1.00131K
palmyra-x5
writer
$0.600$6.00$1.951.0M
gpt-audio-mini
openai
$0.600$2.40$1.05128K
kimi-k2-thinking
moonshotai
$0.600$2.50$1.07262K
kimi-k2-0905
moonshotai
$0.600$2.50$1.07262K
glm-4.5v
z-ai
$0.600$1.80$0.90066K
glm-4.5
z-ai
$0.600$2.20$1.00131K
wizardlm-2-8x22b
microsoft
$0.620$0.620$0.62066K
qwen3-coder-plus
qwen
$0.650$3.25$1.301M
l3.3-euryale-70b
sao10k
$0.650$0.750$0.675131K
gemma-2-27b-it
google
$0.650$0.650$0.6508K
qwen-2.5-coder-32b-instruct
qwen
$0.660$1.00$0.74533K
kimi-k2.6
moonshotai
$0.684$3.42$1.37262K
aion-3.0-mini
aion-labs
$0.700$1.40$0.875131K
deepseek-r1
deepseek
$0.700$2.50$1.15164K
hermes-3-llama-3.1-70b
nousresearch
$0.700$0.700$0.700131K
kimi-k2.7-code
moonshotai
$0.710$3.49$1.41262K
kat-coder-pro-v2.5
kwaipilot
$0.740$2.96$1.29256K
gpt-5.4-mini
openai
$0.750$4.50$1.69400K
virtuoso-large
arcee-ai
$0.750$1.20$0.863131K
qwen3-max-thinking
qwen
$0.780$3.90$1.56262K
qwen3-max
qwen
$0.780$3.90$1.56262K
aion-2.0
aion-labs
$0.800$1.60$1.00131K
morph-v3-fast
morph
$0.800$1.20$0.90082K
aion-rp-llama-3.1-8b
aion-labs
$0.800$1.60$1.0033K
qwen2.5-vl-72b-instruct
qwen
$0.800$1.00$0.850128K
deepseek-r1-distill-llama-70b
deepseek
$0.800$0.800$0.8008K
nova-pro-v1
amazon
$0.800$3.20$1.40300K
glm-5.2
z-ai
$0.808$2.54$1.241.0M
relace-apply-3
relace
$0.850$1.25$0.950256K
l3.1-euryale-70b
sao10k
$0.850$0.850$0.850131K
morph-v3-large
morph
$0.900$1.90$1.15262K
glm-5
z-ai
$0.950$2.55$1.35205K
glm-5.1
z-ai
$0.966$3.04$1.48205K
inkling
thinkingmachines
$1.00$4.05$1.761.0M
gpt-5.6-luna-pro
openai
$1.00$6.00$2.251.1M
gpt-5.6-luna
openai
$1.00$6.00$2.251.1M
grok-build-0.1
x-ai
$1.00$2.00$1.25256K
relace-search
relace
$1.00$3.00$1.50256K
claude-haiku-4.5
anthropic
$1.00$5.00$2.00200K
hermes-4-405b
nousresearch
$1.00$3.00$1.50131K
sonar
perplexity
$1.00$1.00$1.00127K
hermes-3-llama-3.1-405b
nousresearch
$1.00$1.00$1.00131K
gpt-3.5-turbo-0613
openai
$1.00$2.00$1.254K
qwen3.6-max-preview
qwen
$1.04$6.24$2.34262K
o4-mini-high
openai
$1.10$4.40$1.93200K
o4-mini
openai
$1.10$4.40$1.93200K
o3-mini-high
openai
$1.10$4.40$1.93200K
o3-mini
openai
$1.10$4.40$1.93200K
glm-5v-turbo
z-ai
$1.20$4.00$1.90203K
glm-5-turbo
z-ai
$1.20$4.00$1.90203K
muse-spark-1.1
meta
$1.25$4.25$2.001.0M
grok-4.3
x-ai
$1.25$2.50$1.561M
grok-4.20-multi-agent
x-ai
$1.25$2.50$1.562M
grok-4.20
x-ai
$1.25$2.50$1.562M
gpt-5.1-codex-max
openai
$1.25$10.00$3.44400K
cogito-v2.1-671b
deepcogito
$1.25$1.25$1.25128K
gpt-5.1
openai
$1.25$10.00$3.44400K
gpt-5.1-chat
openai
$1.25$10.00$3.44128K
gpt-5.1-codex
openai
$1.25$10.00$3.44400K
gpt-5-codex
openai
$1.25$10.00$3.44400K
gpt-5-chat
openai
$1.25$10.00$3.44128K
gpt-5
openai
$1.25$10.00$3.44400K
gemini-2.5-pro
google
$1.25$10.00$3.441.0M
gemini-2.5-pro-preview
google
$1.25$10.00$3.441.0M
gemini-2.5-pro-preview-05-06
google
$1.25$10.00$3.441.0M
qwen3.7-max
qwen
$1.48$4.42$2.211M
gemini-3.6-flash
google
$1.50$7.50$3.001.0M
gemini-3.5-flash
google
$1.50$9.00$3.381.0M
mistral-medium-3-5
mistralai
$1.50$7.50$3.00262K
gpt-3.5-turbo-instruct
openai
$1.50$2.00$1.634K
gpt-5.3-chat
openai
$1.75$14.00$4.81128K
gpt-5.3-codex
openai
$1.75$14.00$4.81400K
gpt-5.2-codex
openai
$1.75$14.00$4.81400K
gpt-5.2-chat
openai
$1.75$14.00$4.81128K
gpt-5.2
openai
$1.75$14.00$4.81400K
grok-4.5
x-ai
$2.00$6.00$3.00500K
claude-sonnet-5
anthropic
$2.00$10.00$4.001M
gemini-3-pro-image
google
$2.00$12.00$4.50131K
gemini-3.1-pro-preview-customtools
google
$2.00$12.00$4.501.0M
gemini-3.1-pro-preview
google
$2.00$12.00$4.501.0M
gemini-3-pro-image-preview
google
$2.00$12.00$4.5066K
o4-mini-deep-research
openai
$2.00$8.00$3.50200K
jamba-large-1.7
ai21
$2.00$8.00$3.50256K
o3
openai
$2.00$8.00$3.50200K
gpt-4.1
openai
$2.00$8.00$3.501.0M
sonar-reasoning-pro
perplexity
$2.00$8.00$3.50128K
sonar-deep-research
perplexity
$2.00$8.00$3.50128K
mistral-large-2407
mistralai
$2.00$6.00$3.00131K
mixtral-8x22b-instruct
mistralai
$2.00$6.00$3.0066K
mistral-large
mistralai
$2.00$6.00$3.00128K
gpt-5.6-terra-pro
openai
$2.50$15.00$5.631.1M
gpt-5.6-terra
openai
$2.50$15.00$5.631.1M
gpt-5.4
openai
$2.50$15.00$5.631.1M
gpt-audio
openai
$2.50$10.00$4.38128K
nova-premier-v1
amazon
$2.50$12.50$5.001M
gpt-5-image-mini
openai
$2.50$2.00$2.38400K
command-a
cohere
$2.50$10.00$4.38256K
gpt-4o-search-preview
openai
$2.50$10.00$4.38128K
gpt-4o-2024-11-20
openai
$2.50$10.00$4.38128K
inflection-3-pi
inflection
$2.50$10.00$4.388K
inflection-3-productivity
inflection
$2.50$10.00$4.388K
command-r-plus-08-2024
cohere
$2.50$10.00$4.38128K
gpt-4o-2024-08-06
openai
$2.50$10.00$4.38128K
gpt-4o
openai
$2.50$10.00$4.38128K
kimi-k3
moonshotai
$3.00$15.00$6.001.0M
aion-3.0
aion-labs
$3.00$6.00$3.75131K
claude-sonnet-4.6
anthropic
$3.00$15.00$6.001M
sonar-pro-search
perplexity
$3.00$15.00$6.00200K
claude-sonnet-4.5
anthropic
$3.00$15.00$6.001M
claude-sonnet-4
anthropic
$3.00$15.00$6.001M
sonar-pro
perplexity
$3.00$15.00$6.00200K
magnum-v4-72b
anthracite-org
$3.00$5.00$3.5016K
gpt-3.5-turbo-16k
openai
$3.00$4.00$3.2516K
gpt-5.6-sol-pro
openai
$5.00$30.00$11.251.1M
gpt-5.6-sol
openai
$5.00$30.00$11.251.1M
fugu-ultra
sakana
$5.00$30.00$11.251M
claude-opus-4.8
anthropic
$5.00$25.00$10.001M
gpt-chat-latest
openai
$5.00$30.00$11.25400K
gpt-5.5
openai
$5.00$30.00$11.251.1M
claude-opus-4.7
anthropic
$5.00$25.00$10.001M
claude-opus-4.6
anthropic
$5.00$25.00$10.001M
claude-opus-4.5
anthropic
$5.00$25.00$10.00200K
gpt-4o-2024-05-13
openai
$5.00$15.00$7.50128K
gpt-5.4-image-2
openai
$8.00$15.00$9.75272K
claude-fable-5
anthropic
$10.00$50.00$20.001M
claude-opus-4.8-fast
anthropic
$10.00$50.00$20.001M
gpt-5-image
openai
$10.00$10.00$10.00400K
o3-deep-research
openai
$10.00$40.00$17.50200K
gpt-4-turbo
openai
$10.00$30.00$15.00128K
gpt-4-turbo-preview
openai
$10.00$30.00$15.00128K
gpt-5-pro
openai
$15.00$120.00$41.25400K
claude-opus-4.1
anthropic
$15.00$75.00$30.00200K
claude-opus-4
anthropic
$15.00$75.00$30.00200K
o1
openai
$15.00$60.00$26.25200K
o3-pro
openai
$20.00$80.00$35.00200K
gpt-5.2-pro
openai
$21.00$168.00$57.75400K
claude-opus-4.7-fast
anthropic
$30.00$150.00$60.001M
gpt-5.5-pro
openai
$30.00$180.00$67.501.1M
gpt-5.4-pro
openai
$30.00$180.00$67.501.1M
gpt-4
openai
$30.00$60.00$37.508K
o1-pro
openai
$150.00$600.00$262.50200K

Frequently asked

How is LLM API pricing calculated?

LLM APIs charge per token — roughly 4 characters of text — with separate rates for input (your prompt) and output (the response). Prices here are US dollars per million tokens. Output tokens typically cost 2–5× more than input tokens, so response length drives cost more than prompt length.

What is the cheapest LLM API?

Ling-2.6-flash is currently the cheapest paid model at $0.010 per million input tokens, and 17 models offer a free tier with no per-token cost at all.

What is blended cost?

Blended cost combines input and output prices at the conventional 3:1 ratio — (3 × input + output) ÷ 4 — approximating a typical workload where prompts are longer than responses. It's the fairest single number for comparing models whose input/output spreads differ.

Do these prices include prompt caching?

No — the table shows standard rates. Models with prompt caching can serve repeated context at a fraction of the input price (often 10×+ cheaper); the cache-read rate is listed where the provider publishes one.