Source: https://www.tera.gw/pricing
Retrieved: 2026-09-29T06:18:20.867Z (page retrieval, not inventory verification)
Content SHA-256: 79b7ecef5cb7d8a9d72139b8a4f2b7aa07a211c90780eb5eb2b012453f066828

Pricing

# Simple per-token pricing.

No minimums. No contracts. No platform fees. Every model, same key.

| Model | Context | Input $/Mtok | Cache Read $/Mtok | Output $/Mtok | Docs |
| --- | --- | --- | --- | --- | --- |

| claude-fable-5 Anthropic | 200K context | $10 | $1 | $50 | [Docs ↗](<https://docs.tera.gw/models/claude-fable-5>) |

| claude-opus-4-8 Anthropic | 200K context | $5 | $0.5 | $25 | [Docs ↗](<https://docs.tera.gw/models/claude-opus-4-8>) |

| claude-sonnet-5 Anthropic | 200K context | $2 | $0.2 | $10 | [Docs ↗](<https://docs.tera.gw/models/claude-sonnet-5>) |

| DeepSeek-R1-0528 DeepSeek | 164K context | $1.35 | - | $5.4 | [Docs ↗](<https://docs.tera.gw/models/deepseek-r1-0528>) |

| DeepSeek-V3.1 DeepSeek | 164K context | $0.6 | $0.06 | $1.7 | [Docs ↗](<https://docs.tera.gw/models/deepseek-v3-1>) |

| DeepSeek-V3.2 DeepSeek | 164K context | $0.56 | $0.06 | $1.68 | [Docs ↗](<https://docs.tera.gw/models/deepseek-v3-2>) |

| DeepSeek-V4-Flash DeepSeek | 1M context | $0.19 | $0.03 | $0.51 | [Docs ↗](<https://docs.tera.gw/models/deepseek-v4-flash>) |

| DeepSeek-V4-Pro DeepSeek | 1M context | $1.74 | $0.14 | $3.48 | [Docs ↗](<https://docs.tera.gw/models/deepseek-v4-pro>) |

| gemma-4-26B-A4B-it Google | 262K context | $0.15 | $0.01 | $0.6 | [Docs ↗](<https://docs.tera.gw/models/gemma-4-26b-a4b-it>) |

| Llama-3.3-70B-Instruct Meta | 128K context | $0.72 | - | $0.72 | [Docs ↗](<https://docs.tera.gw/models/llama-3-3-70b-instruct>) |

| MiniMax-M2 MiniMax | 197K context | $0.3 | $0.03 | $1.2 | [Docs ↗](<https://docs.tera.gw/models/minimax-m2>) |

| kimi-k2-thinking Moonshot | 262K context | $0.6 | $0.06 | $2.5 | [Docs ↗](<https://docs.tera.gw/models/kimi-k2-thinking>) |

| Kimi-K2.5 Moonshot | 262K context | $0.6 | $0.1 | $3 | [Docs ↗](<https://docs.tera.gw/models/kimi-k2-5>) |

| Kimi-K2.6 Moonshot | 262K context | $0.95 | $0.16 | $4 | [Docs ↗](<https://docs.tera.gw/models/kimi-k2-6>) |

| Kimi-K3 Moonshot AI | 1M context | $3 | $0.3 | $15 | [Docs ↗](<https://docs.tera.gw/models/kimi-k3>) |

| gpt-5.5 OpenAI | 1M context | $5 | $0.5 | $30 | [Docs ↗](<https://docs.tera.gw/models/gpt-5-5>) |

| gpt-5.6-luna OpenAI | 1M context | $0.2 | $0.02 | $1.2 | [Docs ↗](<https://docs.tera.gw/models/gpt-5-6-luna>) |

| gpt-5.6-sol OpenAI | 1M context | $5 | $0.5 | $30 | [Docs ↗](<https://docs.tera.gw/models/gpt-5-6-sol>) |

| gpt-5.6-terra OpenAI | 1M context | $2 | $0.2 | $12 | [Docs ↗](<https://docs.tera.gw/models/gpt-5-6-terra>) |

| gpt-oss-120b OpenAI | 131K context | $0.09 | - | $0.36 | [Docs ↗](<https://docs.tera.gw/models/gpt-oss-120b>) |

| gpt-oss-20b OpenAI | 131K context | $0.07 | - | $0.25 | [Docs ↗](<https://docs.tera.gw/models/gpt-oss-20b>) |

| Qwen3-235B-A22B-Instruct-2507 Qwen / Alibaba | 262K context | $0.22 | - | $0.88 | [Docs ↗](<https://docs.tera.gw/models/qwen3-235b-a22b-instruct-2507>) |

| Qwen3-Coder-480B-A35B-Instruct Qwen / Alibaba | 262K context | $0.22 | $0.02 | $1.8 | [Docs ↗](<https://docs.tera.gw/models/qwen3-coder-480b-a35b-instruct>) |

| Qwen3-Next-80B-A3B-Instruct Qwen / Alibaba | 262K context | $0.15 | - | $1.2 | [Docs ↗](<https://docs.tera.gw/models/qwen3-next-80b-a3b-instruct>) |

| Qwen3-Next-80B-A3B-Thinking Qwen / Alibaba | 262K context | $0.15 | - | $1.2 | [Docs ↗](<https://docs.tera.gw/models/qwen3-next-80b-a3b-thinking>) |

| GLM-4.7 Z.ai | 200K context | $0.6 | - | $2.2 | [Docs ↗](<https://docs.tera.gw/models/glm-4-7>) |

| GLM-5 Z.ai | 200K context | $1 | $0.1 | $3.2 | [Docs ↗](<https://docs.tera.gw/models/glm-5>) |

| GLM-5.2 Z.ai | 262K context | $1.49 | $0.27 | $4.62 | [Docs ↗](<https://docs.tera.gw/models/glm-5-2>) |

Prices are in USD per million tokens. All inference is processed on US-owned infrastructure with zero data retention.

Questions? [deepak@tera.gw](<mailto:deepak@tera.gw>). API docs and integration guides at [tera.gw](<https://www.tera.gw/inference#integrate>).

---
Interactive controls above are described, not submitted. Reading does not reserve capacity or authorize payment.
For GPU requirements: https://www.tera.gw/gpu-rentals#capacity-brief