PricingUSD per million tokens

Pay for tokens, nothing else

Prepaid balance, billed per token at the price shown when the request starts. Cached input is billed at a lower rate. No seat fees, no minimum commitment.

Start for freeContact sales
Estimate a month

What a month would cost

Pick a model and drag the sliders. The estimate uses the same prices as the table below.

drag to adjust
zai-org/GLM-5.3
20M
6M
30%
Estimated monthly cost
$47.56
Fresh input$19.60
Cached input$1.56
Output$26.40
Requests at 1.5K in / 400 out13,333
Model prices

All models and prices

DeepSeek uses the official off-peak base price at all times. Pending models cannot be called. Batch discounts follow GridPort’s batch policy.

11 models
ModelContexttokensInputUSD / 1MCached inputUSD / 1MOutputUSD / 1MBatch inputUSD / 1MBatch outputUSD / 1M
DeepSeek V4 Flashdeepseek-ai/DeepSeek-V4-Flash
1.0M$0.15$0.003$0.60$0.075$0.30
DeepSeek V4 Prodeepseek-ai/DeepSeek-V4-Pro
1.0M$0.66$0.022$1.98——
GLM-5.3zai-org/GLM-5.3
1.0M$1.40$0.26$4.40——
GLM-5.3 Flashzai-org/GLM-5.3-Flash
1.0M$0.15$0.03$0.50$0.075$0.25
Kimi K2.6Awaiting connectionmoonshotai/Kimi-K2.6
256K$0.95$0.16$4.00——
Kimi K2.7 CodeAwaiting connectionmoonshotai/Kimi-K2.7-Code
256K$0.95$0.19$4.00——
Kimi K3Awaiting connectionmoonshotai/Kimi-K3
1.0M$3.00$0.30$15.00——
Qwen3 Embedding 8BQwen/Qwen3-Embedding-8B
32K$0.01————
Qwen3-VL 235BQwen/Qwen3-VL-235B-A22B-Instruct
256K$0.40—$1.60——
Qwen3.8 27BQwen/Qwen3.8-27B
256K$0.50—$3.00$0.25$1.50
Qwen3.8 Flash NextQwen/Qwen3.8-Flash-Next
256K$0.07$0.018$0.22$0.035$0.11
Rate limits

Rate limits by tier

Checking payment availability…

Start using GridPort
Create an account