Skip to main content
All prices are in USD per million tokens. Updated 2026-06-26.
ModelInputOutputCache ReadQuantContext
openai/gpt-oss-20b$0.07$0.25mxfp4131,072
openai/gpt-oss-120b$0.09$0.36mxfp4131,072
google/gemma-4-26B-A4B-it$0.15$0.60$0.015managed262,144
Qwen/Qwen3-Next-80B-A3B-Instruct$0.15$1.20managed262,144
Qwen/Qwen3-Next-80B-A3B-Thinking$0.15$1.20managed262,144
deepseek-ai/DeepSeek-V4-Flash$0.19$0.51managed1,048,576
Qwen/Qwen3-235B-A22B-Instruct-2507$0.22$0.88managed262,144
Qwen/Qwen3-Coder-480B-A35B-Instruct$0.22$1.80$0.022managed262,144
MiniMaxAI/MiniMax-M2$0.30$1.20$0.03managed-fp8196,608
deepseek-ai/DeepSeek-V3.2$0.56$1.68$0.056managed163,840
deepseek-ai/DeepSeek-V3.1$0.60$1.70$0.06managed163,840
moonshotai/Kimi-K2.5$0.60$3.00managed262,144
moonshotai/kimi-k2-thinking$0.60$2.50$0.06managed-int4262,144
zai-org/GLM-4.7$0.60$2.20managed200,000
meta-llama/Llama-3.3-70B-Instruct$0.72$0.72managed128,000
moonshotai/Kimi-K2.6$0.95$4.00managed262,144
zai-org/GLM-5$1.00$3.20$0.10managed200,000
deepseek-ai/DeepSeek-R1-0528$1.35$5.40managed163,840
zai-org/GLM-5.2$1.49$4.62$0.27managed262,144
deepseek-ai/DeepSeek-V4-Pro$1.74$3.48managed1,048,576
Pricing is the same whether requests stream or not. Failed requests (5xx, 429) are not billed.

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_content tokens count toward output.
  • Cache read tokens are cached input tokens reported by the backend. They appear in pricing only for models with non-zero cache-read rates.

Volume discounts

Reach out at hello@tera.gw for committed-use pricing.