Large Language Model (LLM) Pricing
Model
Quantization Context / Max output
$ / M in
$ / M out
Speed
kimi-k2.5
int4 196,608 / 131,072 vision
$0.45
$2.00
~55 t/s
kimi-k2.5-instant
int4 131,072 / 8,192 vision
$0.50
$2.40
~50 t/s
kimi-k2.5-canopy
int4 256,000 / 256,000
$0.80
$3.50
~169 t/s
glm-5
fp8 202,752 / 202,752
$0.75
$2.40
~43 t/s
glm-5-turbo
int4 202,752 / 202,752
$0.80
$2.50
~112 t/s
minimax-m2.5
awq 204,800 / 131,072
$0.25
$1.15
~89 t/s
qwen3.5-397b-a17b
fp8 262,144 / 262,144 vision
$0.35
$1.75
~23 t/s
nemotron-3-nano-30b-a3b
Q4_0 131,072 / 131,072
$0.00
$0.00
~760 t/s
glm-4.7-flash
fp8 202,752 / 131,072
$0.00
$0.00
~25 t/s
glm-4.7
fp4 202,752 / 202,752
$0.40
$1.40
~133 t/s
glm-4.7-canopy
fp8 202,752 / 202,752
$0.50
$2.10
~31 t/s
minimax-m2.1
awq 131,072 / 131,072
$0.28
$0.90
~58 t/s
minimax-m2.1-canopy
fp8 196,608 / 196,608
$0.35
$1.27
~1111 t/s
kimi-k2-0905
Q8_0 131,072 / 131,072
$0.15
$0.55
~184 t/s
deepseek-v3.2
Q4_0 163,840 / 163,840
$0.28
$0.38
~175 t/s
deepseek-v3.2-chat
Q4_0 163,840 / 163,840
$0.28
$0.38
~2 t/s
deepseek-v3.2-canopy
fp8 163,840 / 163,840
$0.35
$0.45
~28 t/s
deepseek-v3.2-speciale
Q4_0 163,840 / 163,840
$0.35
$0.45
~142 t/s
devstral-2
fp8 262,144 / 262,144
$0.07
$0.31
~112 t/s
intellect-3
Q8_0 128,000 / 128,000
$0.15
$1.00
~325 t/s
ring-1t
Q4_0 131,072 / 131,072
$0.40
$1.00
~110 t/s
deepseek-v3.2-exp
Q4_0 131,072 / 131,072
$0.15
$0.30
~189 t/s
deepseek-v3.1-terminus
Q4_0 131,072 / 131,072
$0.20
$0.50
~9 t/s
deepseek-v3.1-terminus-reasoner
Q4_0 131,072 / 131,072
$0.20
$0.50
~432 t/s
deepseek-v3-0324-turbo
Q4_0 131,072 / 8,192
$0.50
$1.00
~596 t/s
deepseek-r1-0528
Q4_0 131,072 / 131,072
$0.25
$0.25
~80 t/s
deepseek-r1-0528-turbo
Q4_0 131,072 / 131,072
$1.00
$2.00
~40 t/s
qwen3-next-80b-a3b-instruct
Q8_0 262,144 / 262,144
$0.08
$0.38
~399 t/s
qwen3-235b-a22b-2507-instruct
Q8_0 131,072 / 131,072
$0.10
$0.25
~40 t/s
qwen3-235b-a22b-2507-thinking
Q8_0 131,072 / 131,072
$0.10
$0.30
~622 t/s
qwen3-coder
fp8 131,072 / 131,072
$0.15
$0.35
~190 t/s
gpt-oss-120b
Q4_0 131,072 / 131,072
$0.07
$0.27
~242 t/s
gpt-oss-safeguard-120b
Q8_0 131,072 / 131,072
$0.07
$0.27
~149 t/s
gemma-3-27b-it
Q8_0 131,072 / 131,072 vision
$0.04
$0.10
~51 t/s
llama-4-scout
fp8 262,144 / 16,384 vision
$0.08
$0.40
~126 t/s
llama3.3-70b
fp8 131,072 / 8,192
$0.12
$0.20
~875 t/s
stok-0.4.1
stok 2,048 / 2,048
$0.00
$0.00
~6007 t/s