Models & pricing

Every model. Every price.

Prices per 1M tokens, with no subscription and no minimum. This list is live from the NusaGate catalog, so it always matches what your account is charged.

Models available: 18
Support caching: 18
Starting at: $0.03/1M input
Save up to: 94%vs official

Accepts

18 of 18 models

Model	Input	Context	Input /1M	Output /1M	Cache hit	vs official
gpt-6.1-sol GPT 6.1 Sol	Input: Text, Image, Audio, Video	1.05M tokens	$0.56	$3.33	$0.06(10%)	-68%
gpt-6-sol GPT-6 Sol	Input: Text, Image, Audio, Video	1.05M tokens	$0.69	$3.44	$0.07(10%)	-66%
gpt-6-luna GPT 6 Luna	Input: Text, Image	1.05M tokens	$0.03	$0.17	$0.0033(10%)	-67%
glm-5.3-flash GLM 5.3 Flash	Input: Text, Image, Video	1.05M tokens	$0.06	$0.17	$0.0061(10%)	-65%
deepseek-v4.1-flash Deepseek V4.1 Flash	Input: Text, Image	1.05M tokens	$0.05	$0.18	$0.005(10%)	-70%
gpt-5.6-luna GPT-5.6 Luna	Input: Text, Image, Video	1.05M tokens	$0.07	$0.50	$0.0067(10%)	-60%
gpt-5.6-terra GPT-5.6 Terra	Input: Text, Image	1.05M tokens	$0.83	$3.61	$0.08(10%)	-68%
gpt-5.6-sol GPT-5.6 Sol	Input: Text, Image, Audio, Video	1.05M tokens	$1.94	$5.56	$0.19(10%)	-79%
qwen3.8-flash Qwen 3.8 Flash	Input: Text, Image	1.05M tokens	$0.05	$0.16	$0.005(10%)	-67%
gemini-3.8-flash80% off Gemini 3.8 Flash	Input: Text, Image	1.05M tokens	$0.06	$0.22	$0.0058(10%)	-94%
deepseek-v4-pro Deepseek V4 Pro	Input: Text	1.05M tokens	$0.22	$0.67	$0.02(10%)	-66%
glm-5.3 GLM 5.3	Input: Text	1.05M tokens	$0.46	$1.44	$0.05(10%)	-67%
grok-4.7 Grok 4.7	Input: Text, Image	1.05M tokens	$0.56	$1.42	$0.06(10%)	-75%
qwen3.8-max-0902 Qwen 3.8 Max 0902	Input: Text, Image	1.05M tokens	$0.66	$1.97	$0.07(10%)	-67%
glm-5.3-flash-uncensored GLM 5.3 Flash Uncensored	Input: Text	1.05M tokens	$1.22	$4.17	$0.23(19%)	no data yet
kimi-k3 Kimi K3	Input: Text, Image	1.05M tokens	$0.94	$4.94	$0.09(10%)	-67%
qwen3.8-27b-uncensored Qwen 3.8 27B Uncensored	Input: Text, Image	131K tokens	$1.67	$6.06	$0.42(25%)	no data yet
gpt-6-astra GPT-6 Astra	Input: Text, Image	272K tokens	$3.33	$17.22	$0.33(10%)	-66%

gpt-6.1-sol
GPT 6.1 Sol
-68%
Input: Text, Image, Audio, Video
Available through NusaGate, billed per token.
Input /1M
$0.56
Output /1M
$3.33
Context
1.05M tokens
Cache hit
$0.06
gpt-6-sol
GPT-6 Sol
-66%
Input: Text, Image, Audio, Video
Available through NusaGate, billed per token.
Input /1M
$0.69
Output /1M
$3.44
Context
1.05M tokens
Cache hit
$0.07
gpt-6-luna
GPT 6 Luna
-67%
Input: Text, Image
Available through NusaGate, billed per token.
Input /1M
$0.03
Output /1M
$0.17
Context
1.05M tokens
Cache hit
$0.0033
glm-5.3-flash
GLM 5.3 Flash
-65%
Input: Text, Image, Video
Multimodal model with 1M context for coding and agent workflows.
Input /1M
$0.06
Output /1M
$0.17
Context
1.05M tokens
Cache hit
$0.0061
deepseek-v4.1-flash
Deepseek V4.1 Flash
-70%
Input: Text, Image
1M context for coding, RAG, and high-volume processing.
Input /1M
$0.05
Output /1M
$0.18
Context
1.05M tokens
Cache hit
$0.005
gpt-5.6-luna
GPT-5.6 Luna
-60%
Input: Text, Image, Video
Budget model for high-volume agent workflows.
Input /1M
$0.07
Output /1M
$0.50
Context
1.05M tokens
Cache hit
$0.0067
gpt-5.6-terra
GPT-5.6 Terra
-68%
Input: Text, Image
A balance of quality, reasoning, and cost.
Input /1M
$0.83
Output /1M
$3.61
Context
1.05M tokens
Cache hit
$0.08
gpt-5.6-sol
GPT-5.6 Sol
-79%
Input: Text, Image, Audio, Video
Flagship model for complex work and long-horizon agents.
Input /1M
$1.94
Output /1M
$5.56
Context
1.05M tokens
Cache hit
$0.19
qwen3.8-flash
Qwen 3.8 Flash
-67%
Input: Text, Image
Available through NusaGate, billed per token.
Input /1M
$0.05
Output /1M
$0.16
Context
1.05M tokens
Cache hit
$0.005
gemini-3.8-flash
Gemini 3.8 Flash
-94%
Input: Text, Image
Available through NusaGate, billed per token.
Input /1M
$0.06
Output /1M
$0.22
Context
1.05M tokens
Cache hit
$0.0058
deepseek-v4-pro
Deepseek V4 Pro
-66%
Input: Text
Available through NusaGate, billed per token.
Input /1M
$0.22
Output /1M
$0.67
Context
1.05M tokens
Cache hit
$0.02
glm-5.3
GLM 5.3
-67%
Input: Text
Available through NusaGate, billed per token.
Input /1M
$0.46
Output /1M
$1.44
Context
1.05M tokens
Cache hit
$0.05
grok-4.7
Grok 4.7
-75%
Input: Text, Image
Available through NusaGate, billed per token.
Input /1M
$0.56
Output /1M
$1.42
Context
1.05M tokens
Cache hit
$0.06
qwen3.8-max-0902
Qwen 3.8 Max 0902
-67%
Input: Text, Image
Available through NusaGate, billed per token.
Input /1M
$0.66
Output /1M
$1.97
Context
1.05M tokens
Cache hit
$0.07
glm-5.3-flash-uncensored
GLM 5.3 Flash Uncensored
Input: Text
Available through NusaGate, billed per token.
Input /1M
$1.22
Output /1M
$4.17
Context
1.05M tokens
Cache hit
$0.23
kimi-k3
Kimi K3
-67%
Input: Text, Image
Available through NusaGate, billed per token.
Input /1M
$0.94
Output /1M
$4.94
Context
1.05M tokens
Cache hit
$0.09
qwen3.8-27b-uncensored
Qwen 3.8 27B Uncensored
Input: Text, Image
Available through NusaGate, billed per token.
Input /1M
$1.67
Output /1M
$6.06
Context
131K tokens
Cache hit
$0.42
gpt-6-astra
GPT-6 Astra
-66%
Input: Text, Image
Available through NusaGate, billed per token.
Input /1M
$3.33
Output /1M
$17.22
Context
272K tokens
Cache hit
$0.33

Cache hit prices apply to prompt/prefix caching: tokens served from cache are billed at the percentage shown, not the full input price.

The “vs official” column compares against the vendor's published price at Rp 18.000/USD. Models with no official comparison are marked “no data yet” instead of getting a savings claim.

Ready to try it?

Create an API key, point your client at NusaGate, pay per token.

Read the docs Sign up free