Skip to main content

How billing works

You pay per token. Three rates apply to each request: input for the tokens you send, cached for input tokens served from a prefix cache, and output for the tokens the model generates. Every figure in the table below is in USD per 1M tokens. Caching is automatic: Valar matches shared prompt prefixes for you and charges the lower cached rate on the tokens that hit. You can raise your hit rate by passing prompt_cache_key as a routing hint, but it’s optional. The rate you pay also depends on the completion window you request. Faster scheduling carries a higher rate: the on-demand Now window costs the most, Priority about 25% less, Standard about 50% less, and Flex the least. The table prices out the windows available for each model; coverage varies, and you can mix windows per request. Completion Windows explains the trade-offs.
Window coverage differs by model, and we keep adding models and widening window support. If a model or window you want isn’t shown, get in touch.

Rate table

USDper 1M tokens
ModelWindowInputCachedOutput
DeepSeek V4 Pro
deepseek-ai/DeepSeek-V4-Pro
Now1.1310.0942.262
Priority0.8480.0711.697
Standard0.5660.0471.131
Flex0.3960.0330.792
Nemotron Ultra
nvidia/nemotron-3-ultra-550b-a55b
Now0.50.12.2
Priority0.3750.0751.65
Standard0.250.051.1
Flex0.1750.0350.77
DeepSeek-V4-Flash-0731
deepseek-ai/DeepSeek-V4-Flash
Now0.090.030.19
Priority0.0680.0230.143
Standard0.050.0150.10
Flex0.0350.0120.075
Kimi K2.7 Code
moonshotai/kimi-k2.7-code
Now0.750.153.5
Priority0.60.122.8
Standard0.3750.0751.75
Flex0.26250.05251.225
Kimi-K3
moonshotai/Kimi-K3
Now2.250.22511.25
Priority1.68750.168758.4375
Standard1.1250.11255.625
Flex0.78750.078753.9375
GLM-5.2
zai-org/GLM-5.2-FP8
Now0.980.1123.4
Priority0.7840.08962.72
Standard0.490.0911.54
Flex0.3430.0641.078
GLM-5.2 Fast
zai-org/GLM-5.2-Fast
Now1.680.1685.28
Priority1.260.1263.96
Standard0.840.0842.64
Flex0.5880.05881.848
gpt-oss-120b
openai/gpt-oss-120b
Now0.060.030.40
Priority0.0450.0230.3
Standard0.040.020.30
Flex0.0240.0120.155
Qwen3.5-397B-A17B
Qwen/Qwen3.5-397B-A17B
Now0.450.091.35
Priority0.3380.0681.013
Standard0.250.050.75
Flex0.1750.0350.525
Qwen3.6 35B-A3B
Qwen/Qwen3.6-35B-A3B
Now0.2250.0450.9
Priority0.1690.03380.675
Standard0.130.0260.52
Flex0.09250.01850.37
Gemma 4 31B IT
google/gemma-4-31B-it
Now0.360.200.60
Priority0.270.150.45
Standard0.180.100.30
Flex0.140.080.24
Gemma 4 26B A4B
google/gemma-4-26B-A4B-it
Now0.090.0180.27
Priority0.0680.01360.203
Standard0.0520.01040.156
Flex0.0370.00740.111
MiniMax M2.7
MiniMaxAI/MiniMax-M2.7
Now0.270.0541.08
Priority0.2030.0410.81
Standard0.150.030.60
Flex0.1050.0210.42
MiniMax M3
MiniMaxAI/MiniMax-M3
Now0.200.061.20
Priority0.150.0450.9
Standard0.100.031.00
Flex0.070.020.80
For each model’s capabilities (e.g., image input and reasoning support), see Models.