Pricing
Every current rate
Token rows are USD per 1M tokens. Media rows are a flat amount per unit. Showing 901–950 of 2347 prices.
| Model | Provider | Unit | Input | Output | Cache read | Cache write | 1h cache write | Flat | Confidence |
|---|---|---|---|---|---|---|---|---|---|
| inferencenet/deepseek-v4-pro-0813 | inferencenet | token | $1.32/1M | $3.96/1M | $0.044/1M | Not published— | Not published— | Not published— | official |
| inferencenet/deepseek-v4.1-flash | inferencenet | token | $0.3/1M | $1/1M | $0.007/1M | Not published— | Not published— | Not published— | official |
| inferencenet/deepseek-v4.1-flash-1017 | inferencenet | token | $0.3/1M | $1/1M | $0.007/1M | Not published— | Not published— | Not published— | official |
| inferencenet/deepseek-v4.1-flash-1017-cyber | inferencenet | token | $0.3/1M | $1/1M | $0.007/1M | Not published— | Not published— | Not published— | official |
| inferencenet/deepseek-v4.1-pro | inferencenet | token | $1.32/1M | $3.96/1M | $0.132/1M | Not published— | Not published— | Not published— | official |
| inferencenet/gemini-2.5-flash | inferencenet | token | $0.3/1M | $2.5/1M | $0.03/1M | Not published— | Not published— | Not published— | official |
| inferencenet/gemini-2.5-flash-lite | inferencenet | token | $0.1/1M | $0.4/1M | $0.01/1M | Not published— | Not published— | Not published— | official |
| inferencenet/gemini-2.5-pro | inferencenet | token | $1.25/1M | $10/1M | $0.125/1M | Not published— | Not published— | Not published— | official |
| inferencenet/gemini-3-flash-preview | inferencenet | token | $0.5/1M | $3/1M | $0.05/1M | Not published— | Not published— | Not published— | official |
| inferencenet/gemini-3.1-flash-lite | inferencenet | token | $0.25/1M | $1.5/1M | $0.025/1M | Not published— | Not published— | Not published— | official |
| inferencenet/gemini-3.1-pro-preview | inferencenet | token | $2/1M | $12/1M | $0.2/1M | Not published— | Not published— | Not published— | official |
| inferencenet/gemini-3.5-flash | inferencenet | token | $1.5/1M | $9/1M | $0.15/1M | Not published— | Not published— | Not published— | official |
| inferencenet/gemini-3.5-flash-lite | inferencenet | token | $0.3/1M | $2.5/1M | $0.03/1M | Not published— | Not published— | Not published— | official |
| inferencenet/gemini-3.6-flash | inferencenet | token | $1.5/1M | $7.5/1M | $0.15/1M | Not published— | Not published— | Not published— | official |
| inferencenet/gemini-3.7-flash | inferencenet | token | $1.5/1M | $7.5/1M | $0.15/1M | Not published— | Not published— | Not published— | official |
| inferencenet/gemma-3-27b-it | inferencenet | token | $0.09/1M | $0.25/1M | Not published— | Not published— | Not published— | Not published— | official |
| inferencenet/gemma-3-4b-it | inferencenet | token | $0.05/1M | $0.1/1M | Not published— | Not published— | Not published— | Not published— | official |
| inferencenet/glm-5 | inferencenet | token | $0.95/1M | $2.55/1M | $0.2/1M | Not published— | Not published— | Not published— | official |
| inferencenet/glm-5.2 | inferencenet | token | $1.3/1M | $4.4/1M | $0.2/1M | Not published— | Not published— | Not published— | official |
| inferencenet/glm-5.2-fast | inferencenet | token | $2.6/1M | $8.8/1M | $0.4/1M | Not published— | Not published— | Not published— | official |
| inferencenet/glm-5.3 | inferencenet | token | $0.9/1M | $3/1M | $0.15/1M | Not published— | Not published— | Not published— | official |
| inferencenet/glm-5.3-flash | inferencenet | token | $0.1/1M | $0.45/1M | $0.03/1M | Not published— | Not published— | Not published— | official |
| inferencenet/gpt-4.1 | inferencenet | token | $2/1M | $8/1M | $0.5/1M | Not published— | Not published— | Not published— | official |
| inferencenet/gpt-4.1-mini | inferencenet | token | $0.4/1M | $1.6/1M | $0.1/1M | Not published— | Not published— | Not published— | official |
| inferencenet/gpt-4.1-nano | inferencenet | token | $0.1/1M | $0.4/1M | $0.025/1M | Not published— | Not published— | Not published— | official |
| inferencenet/gpt-4o | inferencenet | token | $2.5/1M | $10/1M | $1.25/1M | Not published— | Not published— | Not published— | official |
| inferencenet/gpt-4o-mini | inferencenet | token | $0.15/1M | $0.6/1M | $0.075/1M | Not published— | Not published— | Not published— | official |
| inferencenet/gpt-5-mini | inferencenet | token | $0.25/1M | $2/1M | $0.025/1M | Not published— | Not published— | Not published— | official |
| inferencenet/gpt-5-nano | inferencenet | token | $0.05/1M | $0.4/1M | $0.005/1M | Not published— | Not published— | Not published— | official |
| inferencenet/gpt-5.4 | inferencenet | token | $2.5/1M | $15/1M | $0.25/1M | Not published— | Not published— | Not published— | official |
| inferencenet/gpt-5.5 | inferencenet | token | $5/1M | $30/1M | $0.5/1M | Not published— | Not published— | Not published— | official |
| inferencenet/gpt-5.6-luna | inferencenet | token | $0.2/1M | $1.2/1M | $0.02/1M | Not published— | Not published— | Not published— | official |
| inferencenet/gpt-5.6-sol | inferencenet | token | $5/1M | $30/1M | $0.5/1M | Not published— | Not published— | Not published— | official |
| inferencenet/gpt-5.6-terra | inferencenet | token | $2/1M | $12/1M | $0.2/1M | Not published— | Not published— | Not published— | official |
| inferencenet/gpt-6-astra | inferencenet | token | $10/1M | $50/1M | $1/1M | Not published— | Not published— | Not published— | official |
| inferencenet/gpt-6-luna | inferencenet | token | $0.1/1M | $0.5/1M | $0.01/1M | Not published— | Not published— | Not published— | official |
| inferencenet/gpt-6-sol | inferencenet | token | $2/1M | $10/1M | $0.2/1M | Not published— | Not published— | Not published— | official |
| inferencenet/gpt-6.1-sol | inferencenet | token | $2/1M | $10/1M | $0.1/1M | Not published— | Not published— | Not published— | official |
| inferencenet/grok-4.5 | inferencenet | token | $2/1M | $6/1M | $0.3/1M | Not published— | Not published— | Not published— | official |
| inferencenet/grok-4.6 | inferencenet | token | $2/1M | $6/1M | $0.5/1M | Not published— | Not published— | Not published— | official |
| inferencenet/inference-net/schematron-v2-small | inferencenet | token | $0.05/1M | $0.23/1M | $0.05/1M | Not published— | Not published— | Not published— | official |
| inferencenet/inference-net/schematron-v2-turbo | inferencenet | token | $0.03/1M | $0.15/1M | $0.03/1M | Not published— | Not published— | Not published— | official |
| inferencenet/kimi-k2.5 | inferencenet | token | $0.8/1M | $3.95/1M | $0.13/1M | Not published— | Not published— | Not published— | official |
| inferencenet/kimi-k2.6 | inferencenet | token | $1.25/1M | $5.3/1M | $0.21/1M | Not published— | Not published— | Not published— | official |
| inferencenet/kimi-k3-fast | inferencenet | token | $4.5/1M | $22.5/1M | $0.45/1M | Not published— | Not published— | Not published— | official |
| inferencenet/kimi-k3.1-pro | inferencenet | token | $1.8/1M | $9/1M | $0.18/1M | Not published— | Not published— | Not published— | official |
| inferencenet/llama-3.2-1b-instruct | inferencenet | token | $0.027/1M | $0.201/1M | Not published— | Not published— | Not published— | Not published— | official |
| inferencenet/llama-3.2-3b-instruct | inferencenet | token | $0.05/1M | $0.33/1M | Not published— | Not published— | Not published— | Not published— | official |
| inferencenet/llama-3.3-70b-instruct | inferencenet | token | $0.13/1M | $0.4/1M | Not published— | Not published— | Not published— | Not published— | official |
| inferencenet/minimax-m3.1-flash | inferencenet | token | $0.1/1M | $0.5/1M | $0.005/1M | Not published— | Not published— | Not published— | official |