All prices are in USD per million tokens. Updated 2026-05-11.Documentation Index
Fetch the complete documentation index at: https://docs.tera.gw/llms.txt
Use this file to discover all available pages before exploring further.
| Model | Input | Output | Quant | Context |
|---|---|---|---|---|
Qwen/Qwen3.5-4B | $0.04 | $0.08 | bf16 | 262,144 |
Qwen/Qwen2.5-7B-Instruct | $0.05 | $0.10 | bf16 | 8,192 |
Qwen/Qwen3.5-27B | $0.10 | $0.30 | fp8 | 8,192 |
hexgrad/Kokoro-82M | $0.62 | Free | fp32 | 4,096 |
openai/gpt-oss-20b | $0.75 | $4.00 | mxfp4 | 131,072 |
openai/gpt-oss-120b | $1.50 | $8.00 | mxfp4 | 131,072 |
How billing works
- Input tokens are counted from the rendered prompt after applying the model’s chat template.
- Output tokens include generated text. For reasoning models,
reasoning_contenttokens count toward output. - TTS (Kokoro) bills on input characters, surfaced as
prompttoken cost.