API PRICES
OpenAI · gpt-6-astra
Provider prices, cheapest first
OpenAI · gpt-6-astra official price: input 10.00, output 50.00 USD per million tokens (OpenAI, observed 2026-10-16). Cheapest inference provider: OpenRouter, input 10, output 50 USD per million tokens. Relays have only older quotes; the lowest is api.pezayo.com, group "codex anthropic" 0.06 USD_CREDIT per million total tokens (credit price, not cash, observed 2026-10-10). 195 sites have comparable prices; 929 sites list this model.Relay blended price uses 75% input and 25% output.
Official price
| Provider | Input | Output | Cache read | Cache write | Unit | Observed | Conditions and source |
|---|---|---|---|---|---|---|---|
| OpenAI | 10.00 | 50.00 | 1.00 | 12.50 | USD / 1M tokens | Official source | |
| OpenAI | 20.00 | 75.00 | 2.00 | 25.00 | USD / 1M tokens | Official source |
Official prices are the vendor's cash prices. Inference providers also list cash prices and can be compared directly. Relays list prices in site credit; what you actually pay depends on each site's top-up rate, so they cannot be compared with official prices directly.
Inference providers
| Provider | Input | Output | Cache read | Cache write | Unit | Observed | Conditions and source | vs official |
|---|---|---|---|---|---|---|---|---|
| OpenRouter · Aggregator | 10 | 50 | 1 | 12.5 | USD / 1M tokens | Official source |
Unit: USD credits per 1M tokens. These are site-credit prices; actual cost depends on each site’s top-up rate.
Searching…
Browse all providersRelays
Prices below are in site credit, not cash.
| # | Provider | Plan / conditions | Input ↑USD credits / 1M | Output USD credits / 1M | Cache readUSD credits / 1M | BlendedUSD credits / 1M | Details |
|---|---|---|---|---|---|---|---|
| Older price | |||||||
| 223 | nexapi.techAsk or discussCollected: View 3 plans | gpt pro+plus gpt-pro+plus mixed account pool, stable, high value for money [machine translation]Original: gpt-pro+plus混合号池，稳定高性价比 | 8 | 40 | 0.8 | 16 | Full prices and sources |
| 223 | rqyq6zz.cnAsk or discussCollected: View 1 plans | GPT general [machine translation]Group on site: GPT通用 General, all models, 0.8 rate multiplier [machine translation]Original: 通用所有模型0.8倍率 | 8 | 40 | 0.8 | 16 | Full prices and sources |
| 223 | cn.gptapi.asiaAsk or discussCollected: View 2 plans 2 more sites of the same company
Basis: identical homepage assets, identical quotes, same status-page name, logo or server address. Counted as one company in the ranking; this is not a legal finding. | default Default channel [machine translation]Original: 默认通道 | 8 | 40 | — | 16 | Full prices and sources |
| 223 | yutoapi.comAsk or discussCollected: View 2 plans 2 more sites of the same company
Basis: identical homepage assets, identical quotes, same status-page name, logo or server address. Counted as one company in the ranking; this is not a legal finding. | default Default channel [machine translation]Original: 默认通道 | 8 | 40 | — | 16 | Full prices and sources |
| 230 | aitokenyes.comAsk or discussCollected: View 4 plans | Official direct-connection pro pool [machine translation]Group on site: 官方直连pro池 pro pool 0.3x [machine translation]Original: pro池0.3x | 9 | 45 | 0.9 | 18 | Full prices and sources |
| 231 | 2api.cloudAsk or discussCollected: View 3 plans | default Default group [machine translation]Original: 默认分组 | 10 | 50 | 1 | 20 | Full prices and sources |
| 231 | ai-one.vipAsk or discussCollected: View 6 plans | codex_vip Made of gpt-pro account pool-not dumbed down [machine translation]Original: gpt-pro号池组成-不降智 | 10 | 50 | 1 | 20 | Full prices and sources |
| 231 | api.2slk.comAsk or discussCollected: View 1 plans | Official relay [machine translation]Group on site: 官转 Official API forwarding [machine translation]Original: 官方API转发 | 10 | 50 | 1 | 20 | Full prices and sources |
| 231 | api.aimodelserver.comAsk or discussCollected: View 1 plans | default Default group, supports openai, grok, claude models [machine translation]Original: 默认分组，支持openai，grok，claude模型 | 10 | 50 | 1 | 20 | Full prices and sources |
| 231 | api.clawsocket.comAsk or discussCollected: View 1 plans | default Default group [machine translation]Original: 默认分组 | 10 | 50 | 1 | 20 | Full prices and sources |
| 231 | api.onefaka.comAsk or discussCollected: View 6 plans | c15 Claude Channel 15 Only | 10 | 50 | 1 | 20 | Full prices and sources |
| 231 | api.onefaka.comAsk or discussCollected: View 6 plans | default ???? | 10 | 50 | 1 | 20 | Full prices and sources |
| 231 | api.onefaka.comAsk or discussCollected: View 6 plans | ssvip SSVIP?? | 10 | 50 | 1 | 20 | Full prices and sources |
| 231 | api.onefaka.comAsk or discussCollected: View 6 plans | svip svip?? | 10 | 50 | 1 | 20 | Full prices and sources |
| 231 | api.onefaka.comAsk or discussCollected: View 6 plans | vip vip?? | 10 | 50 | 1 | 20 | Full prices and sources |
| 231 | api.pezayo.comAsk or discussCollected: View 3 plans | coding openai coding openai group, can call kimi-latest, deepseek-flash models via the openai chat completion format and the openai response format [machine translation]Original: coding openai 分组，能通过 openai chat completion格式和 openai response 格式调用 kimi-latest，deepseek-flash 模型 | 10 | 50 | 1 | 20 | Full prices and sources |
| 231 | api.pezayo.comAsk or discussCollected: View 3 plans | default Default group, use all models via the openai chat completion format [machine translation]Original: 默认分组，通过 openai chat completion 格式使用全部模型 | 10 | 50 | 1 | 20 | Full prices and sources |
| 231 | api.pezayo.comAsk or discussCollected: View 3 plans | official Official group, gpt, claude gemini official models [machine translation]Original: 官方 分组，gpt, claude gemini 官方模型 | 10 | 50 | 1 | 20 | Full prices and sources |
| 231 | api.wlapi.topAsk or discussCollected: View 2 plans | default Default group [machine translation]Original: 默认分组 | 10 | 50 | 1 | 20 | Full prices and sources |
| 231 | api.wlapi.topAsk or discussCollected: View 2 plans | svip svip group [machine translation]Original: svip分组 | 10 | 50 | 1 | 20 | Full prices and sources |
| 231 | cn.chrouter.comAsk or discussCollected: View 2 plans | gpt gpt full-series group [machine translation]Original: gpt全系列组 | 10 | 50 | 1 | 20 | Full prices and sources |
| 231 | codexcs.ysaikeji.cnAsk or discussCollected: View 2 plans | codex codex | 10 | 50 | — | 20 | Full prices and sources |
| 231 | codexcs.ysaikeji.cnAsk or discussCollected: View 2 plans | default Default group [machine translation]Original: 默认分组 | 10 | 50 | — | 20 | Full prices and sources |
| 231 | dahlo.liveAsk or discussCollected: View 5 plans | Special group [machine translation]Group on site: 特殊分组 | 10 | 50 | 1 | 20 | Full prices and sources |
| 231 | devinone.comAsk or discussCollected: View 1 plans | default Default group [machine translation]Original: 默认分组 | 10 | 50 | 1 | 20 | Full prices and sources |
Special groups · 23 rows · not ranked
These plans are marked as test, internal, disabled, gated by top-up or membership, or have a near-zero ratio. They may not be purchasable or stable, so they are listed separately and left out of the ranking and statistics.
- test or debug group: 12 rows
- near-zero-ratio group: 10 rows
- marked display-only or do-not-select: 8 rows
- top-up or membership gated: 1 rows
- api.pezayo.com · codex anthropic · gpt-6-astra · Input 0.03 / Output 0.15 USD credits / 1M
- nty-hk.zhouyang168.top · Codex11 · gpt-6-astra · Input 0.1 / Output 0.5 USD credits / 1M
- yfy.zhouyang168.top · Codex11 · gpt-6-astra · Input 0.1 / Output 0.5 USD credits / 1M
- apiroute.top · gpt-plus · gpt-6-astra · Input 0.135 / Output 0.675 USD credits / 1M
- apiroute.top · gpt-pro · gpt-6-astra · Input 0.22 / Output 1.1 USD credits / 1M
- ainzy.net · codex-plus · gpt-6-astra · Input 0.3 / Output 1.5 USD credits / 1M
- api.pezayo.com · codex · gpt-6-astra · Input 0.3 / Output 1.5 USD credits / 1M
- bmodels.top · default · gpt-6-astra · Input 0.32 / Output 1.6 USD credits / 1M
- newtonrouter.com · Gpt Pro 20x · gpt-6-astra · Input 0.35 / Output 1.75 USD credits / 1M
- nty-hk.zhouyang168.top · Test · gpt-6-astra · Input 1 / Output 5 USD credits / 1M
Related variants · 4 rows · not ranked
These are special editions of the model (thinking, max, search, batch, long context, free, etc.). They are priced differently from the base model, so they are listed separately and not ranked. Names that only add an effort level such as low, high or nothinking are compared with the base model.
- gpt-6-astra[1m] ([1m] · context or size tier (e.g. 128k, 1M, 4K)): 4 rows
- api.bddevlab.online · CLAUDE-FABLE · gpt-6-astra[1m] · Input 3.99996288 / Output 3.99996288 USD credits / 1M
- api.bddevlab.online · CodexDeepSeek · gpt-6-astra[1m] · Input 5.8744 / Output 5.8744 USD credits / 1M
- api.bddevlab.online · default · gpt-6-astra[1m] · Input 6.7136 / Output 6.7136 USD credits / 1M
- api.bddevlab.online · CLAUDE-HIGH-UPTIME · gpt-6-astra[1m] · Input 11.41312 / Output 11.41312 USD credits / 1M
How this ranking works
All per-token prices: 96,427 prices from 839 sites (about 733 companies). 88,950 are ranked, from 826 sites (about 720 companies); 7,477 more are listed separately and not ranked. Prices collected up to 2026-10-10.
This model has 3661 recorded prices; 594 can be compared directly (557 ranked, 37 listed separately). Not comparable yet: tiered by rules (see Tiered prices) 2091, price not parsed yet 590, new price under review; showing the previous one 194, ratio looks unset 72, display unit not confirmed 71, scope of the official doc price not confirmed 34, billed per request or another unit 15
0 recent · 416 stale (older than 7 days, or not updated by this refresh) · 0 unverified timestamps. Only older prices are available, so the statistics are for reference only. 0 zero-valued pairs are separately unverified, without proof of free eligibility. Timing does not verify payment, upstream identity or quality.
Prices are converted to site credits using each site’s published ratio. What you actually pay depends on its top-up rate. Input, output and cache prices in each row come from the same plan. Several sites run by the same company take one place in the ranking: its cheapest plan, with the other sites listed under it. We judge “same company” by identical prices, status pages or homepage code; this is not a legal finding. To see every site’s prices, choose “All plans” or filter by provider.
“Self-declared unofficial channel” means the plan name itself says “reverse-engineered” or similar. We have not verified their source or quality. Minimum and median only count regular plans.