Models
Supported models and per-token pricing on AI Gateway
The tables below list every model currently routed through AI Gateway. Prices are denominated in CNY (¥) per 1M tokens, except image models which are billed per call. Live pricing is published at the Model Marketplace.
| Model ID | Input / 1M | Output / 1M | Cache read / 1M | Cache write / 1M |
|---|
claude-opus-4-7 | ¥2.0000 | ¥10.0000 | ¥0.2000 | ¥2.5000 |
claude-opus-4-6 | ¥2.0000 | ¥10.0000 | ¥0.2000 | ¥2.5000 |
claude-opus-4-5-20251101 | ¥2.0000 | ¥10.0000 | ¥0.2000 | ¥2.5000 |
claude-sonnet-4-6 | ¥1.2000 | ¥6.0000 | ¥0.1200 | ¥1.5000 |
claude-sonnet-4-5-20250929 | ¥1.2000 | ¥6.0000 | ¥0.1200 | ¥1.5000 |
claude-haiku-4-5-20251001 | ¥0.4000 | ¥2.0000 | ¥0.0400 | ¥0.5000 |
| Model ID | Input / 1M | Output / 1M | Cache read / 1M | Cache write / 1M |
|---|
gpt-5.5 | ¥0.2500 | ¥1.5000 | ¥0.0250 | ¥0.0250 |
gpt-5.5-openai-compact | ¥0.2500 | ¥1.5000 | ¥0.0250 | ¥0.0250 |
gpt-5.4 | ¥0.1250 | ¥0.7500 | ¥0.0130 | — |
gpt-5.4-openai-compact | ¥0.1250 | ¥0.7500 | ¥0.0130 | — |
gpt-5.4-mini | ¥0.0380 | ¥0.2250 | ¥0.0040 | — |
gpt-5.3-codex-openai-compact | ¥0.3750 | ¥3.0000 | ¥0.0380 | — |
gpt-5.3-codex | ¥0.0880 | ¥0.7000 | ¥0.0090 | ¥0.0090 |
gpt-5.2 | ¥0.0880 | ¥0.7000 | ¥0.0090 | ¥0.0090 |
| Model ID | Input / 1M | Output / 1M | Cache read / 1M | Cache write / 1M |
|---|
gpt-5.3-codex-spark | ¥1.5750 | ¥12.6000 | ¥0.1580 | ¥0.1580 |
| Model ID | Price / call |
|---|
gpt-image-2 | ¥0.100 |
gpt-image-2-pro | ¥0.100 |
- Per-token billing — input and output tokens are priced separately. Prompt-cache hits settle at the cache read / cache write rate, materially reducing the cost of repeated context.
- Per-call billing — image models are billed by request count, independent of input resolution or parameters.
- Live pricing wins — group tiers and promotional discounts may differ; the authoritative source is code.b886.top/pricing. This page is a snapshot taken on 2026-05-24.