基础价格 · HALO Docs

These base rates mirror the HALO production pricing catalog checked on September 3, 2026. Text prices are in USD per 1 million tokens unless a provider-specific unit is shown.

#价格说明

#Google Gemini

Model	输入	缓存输入	输出
`gemini-3.8-flash`	$0.75	$0.075	$3.75
`gemini-3.7-flash`	$0.75	$0.075	$3.75
`gemini-3.6-flash`	$0.75	$0.075	$3.75
`gemini-3.5-flash`	$1.50	$0.15	$9.00
`gemini-3.5-flash-lite`	$0.30	$0.03	$2.50
`gemini-3.1-pro-preview`	$2.00 / $4.00	$0.20 / $0.40	$12.00 / $18.00
`gemini-3.1-flash-lite`	$0.25	$0.025	$1.50
`gemini-3-flash-preview`	$0.50	$0.05	$3.00
`gemini-2.5-pro`	$1.25 / $2.50	$0.125 / $0.25	$10.00 / $15.00
`gemini-2.5-flash`	$0.30	$0.03	$2.50
`gemini-2.5-flash-lite`	$0.10	$0.01	$0.40

Paired Gemini rates apply at up to 200,000 input tokens and above 200,000 input tokens. Gemini 3.8 Flash, Gemini 3.7 Flash and Gemini 3.6 Flash use introductory pricing through December 31, 2026; Google lists $1.50 input, $0.15 cached input, and $7.50 output starting January 1, 2027.

#OpenAI

Model	非缓存输入	缓存输入	缓存写入	输出
`gpt-5.6`	$4.00 / $8.00	$0.40 / $0.80	$5.00 / $10.00	$20.00 / $30.00
`gpt-5.6-sol`	$4.00 / $8.00	$0.40 / $0.80	$5.00 / $10.00	$20.00 / $30.00
`gpt-5.6-terra`	$2.00 / $4.00	$0.20 / $0.40	$2.50 / $5.00	$12.00 / $18.00
`gpt-5.6-luna`	$0.20 / $0.40	$0.02 / $0.04	$0.25 / $0.50	$1.20 / $1.80
`gpt-5.5`	$5.00 / $10.00	$0.50 / $1.00	—	$30.00 / $45.00
`gpt-5.4`	$2.50 / $5.00	$0.25 / $0.50	—	$15.00 / $22.50
`gpt-5.4-mini`	$0.75	$0.075	—	$4.50
`gpt-5.4-nano`	$0.20	$0.02	—	$1.25
`gpt-5.2`	$1.75	$0.175	—	$14.00
`gpt-5.1`	$1.25	$0.125	—	$10.00
`gpt-5`	$1.25	$0.125	—	$10.00
`gpt-5-mini`	$0.25	$0.025	—	$2.00
`gpt-5-nano`	$0.05	$0.005	—	$0.40
`gpt-4.1`	$2.00	$0.50	—	$8.00
`gpt-4.1-mini`	$0.40	$0.10	—	$1.60
`gpt-4.1-nano`	$0.10	$0.025	—	$0.40
`gpt-4o`	$2.50	$1.25	—	$10.00
`gpt-4o-mini`	$0.15	$0.075	—	$0.60
`o3`	$2.00	$0.50	—	$8.00
`o4-mini`	$1.10	$0.275	—	$4.40

OpenAI Chat Completions reports cached input separately. All remaining prompt input is billed at the uncached-input rate. Paired rates apply at up to 272,000 input tokens and above 272,000 input tokens. GPT-5.6 Sol uses OpenAI's current promotional rates.

#OpenAI GPT Image

GPT Image 价格单位为每 100 万 token 的美元价格，并按文本和图片模态分别计量。

Model	文本输入	缓存文本输入	文本输出	图片输入	缓存图片输入	图片输出
`gpt-image-2`	$5.00	$1.25	—	$8.00	$2.00	$30.00
`gpt-image-1.5`	$5.00	$1.25	$10.00	$8.00	$2.00	$32.00
`gpt-image-1-mini`	$2.00	$0.20	—	$2.50	$0.25	$8.00
`gpt-image-1`	$5.00	$1.25	—	$10.00	$2.50	$40.00
`chatgpt-image-latest`	$5.00	$1.25	$10.00	$8.00	$2.00	$32.00

#Anthropic

Model	输入	缓存输入	缓存写入	输出
`claude-fable-5-1`	$10.00	$0.25	$12.50	$50.00
`claude-opus-5`	$5.00	$0.50	$6.25	$25.00
`claude-sonnet-5`	$2.00	$0.20	$2.50	$10.00
`claude-fable-5`	$10.00	$1.00	$12.50	$50.00
`claude-opus-4-8`	$5.00	$0.50	$6.25	$25.00
`claude-opus-4-7`	$5.00	$0.50	$6.25	$25.00
`claude-opus-4-6`	$5.00	$0.50	$6.25	$25.00
`claude-opus-4-5-20251101`	$5.00	$0.50	$6.25	$25.00
`claude-sonnet-4-6`	$3.00	$0.30	$3.75	$15.00
`claude-sonnet-4-5-20250929`	$3.00	$0.30	$3.75	$15.00
`claude-sonnet-4-20250514`	$3.00	$0.30	$3.75	$15.00
`claude-haiku-4-5-20251001`	$1.00	$0.10	$1.25	$5.00
`claude-3-5-haiku-20241022`	$0.80	$0.08	$1.00	$4.00

#DeepSeek

Model	输入	缓存输入	输出
`deepseek-v4-flash`	$0.44 / $0.22	$0.014 / $0.007	$1.32 / $0.66
`deepseek-v4-pro`	$1.32 / $0.66	$0.044 / $0.022	$3.96 / $1.98

Paired DeepSeek rates show peak and off-peak pricing. Peak pricing applies on weekdays from 01:00–04:00 and 06:00–10:00 UTC; all other times use the off-peak rate. HALO snapshots the applicable rate when dispatch starts.

#Fish Audio

Fish Audio TTS is metered by the UTF-8 byte length of the input text, not by language-model tokens. The table shows HALO's 0 bps base price; the selected platform key's buyer price adjustment is applied to the exact request price.

Model	USD per 1M UTF-8 bytes
`s2.1-pro`	$15.00
`s2-pro`	$15.00
`s1`	$15.00

#开源

开源价格是所列运行时池的 HALO 目录价格，并仍受项目可见性和健康提供商容量限制。

#AllenAI · OLMo

Model	输入	缓存输入	输出
`allenai/olmo-3-32b-think`	$0.15	$0.15	$0.50

#DeepSeek

Model	输入	缓存输入	输出
`deepseek/deepseek-v4-flash`	$0.135883	$0.045979	$0.266656
`deepseek/deepseek-v4-pro`	$1.310879	$0.133455	$2.632670

#Google · Gemma

Model	输入	缓存输入	输出
`google/gemma-4-31b-it`	$0.29	$0.272222	$0.668889
`google/gemma-4-26b-a4b-it`	$0.11	$0.075556	$0.368889

#Meta · Llama

Model	输入	缓存输入	输出
`meta-llama/llama-4-maverick`	$0.284	$0.248	$0.934
`meta-llama/llama-4-scout`	$0.16	$0.146250	$0.482500

#MiniMax

Model	输入	缓存输入	输出
`minimax/minimax-m3`	$0.36	$0.168	$1.44

#Mistral AI

Model	输入	缓存输入	输出
`mistralai/mistral-small-2603`	$0.168750	$0.101250	$0.675
`mistralai/mistral-large-2512`	$0.50	$0.05	$1.50

#Moonshot AI · Kimi

Model	输入	缓存输入	输出
`moonshotai/kimi-k3`	$3.00	$0.30	$15.00
`moonshotai/kimi-k2.7-code`	$0.928744	$0.186155	$4.059333

#NVIDIA · Nemotron

Model	输入	缓存输入	输出
`nvidia/nemotron-3-nano-30b-a3b`	$0.055	$0.055	$0.22
`nvidia/nemotron-3-ultra-550b-a55b`	$0.55	$0.15	$2.90

#OpenAI · GPT-OSS

Model	输入	缓存输入	输出
`openai/gpt-oss-120b`	$0.112800	$0.104467	$0.478333
`openai/gpt-oss-20b`	$0.051167	$0.043458	$0.190833

#Qwen

Model	输入	缓存输入	输出
`qwen/qwen3.6-35b-a3b`	$0.176	$0.159333	$1.160625
`qwen/qwen3-coder-next`	$0.182	$0.135200	$1.10

#Xiaomi · MiMo

Model	输入	缓存输入	输出
`xiaomi/mimo-v2.5-pro`	$0.549707	$0.062359	$1.566080
`xiaomi/mimo-v2.5`	$0.138250	$0.021050	$0.294

#Z.ai · GLM

Model	输入	缓存输入	输出
`z-ai/glm-5.2`	$1.354196	$0.260500	$4.348842

#媒体生成

#Imagen · 每张生成图片

Model	价格
`imagen-3.0-generate-002`	$0.03
`imagen-4.0-fast-generate-001`	$0.02
`imagen-4.0-generate-001`	$0.04
`imagen-4.0-ultra-generate-001`	$0.06

#Veo · 每生成秒的美元价格

Model	720p	1080p	4K
`veo-3.1-lite-generate-preview`	$0.05	$0.08	—
`veo-3.1-fast-generate-preview`	$0.10	$0.12	$0.30
`veo-3.1-generate-preview`	$0.40	$0.40	$0.60
`veo-3.0-fast-generate-001`	$0.10	$0.12	$0.30
`veo-3.0-generate-001`	$0.40	$0.40	$0.40
`veo-2.0-generate-001`	$0.35	—	—

破折号表示该分辨率不可用，请求会在发送给提供商之前被拒绝。

#计费说明

本表未列出 Batch、Flex、Priority 和区域处理价格。
搜索、缓存存储以及音频、图片或视频模态专用 token 价格可能产生额外用量。
最终扣款由已完成的上游用量和请求所附的计费快照决定。
请在控制台的模型页面查看当前项目可见的目录。