API PRICES
OpenAI · gpt-3.5-turbo-instruct
Provider prices, cheapest first
Price comparison
- Official (cash)
- Input 1.5 / output 2 USD/million tokensOpenAI ·
- Lowest inference provider (cash)
- Input 1.5 / output 2 USD/million tokensOpenRouter · Aggregator ·
- Lowest relay (credit)
- 0.28125 CNY credit/million total tokenszhangsan.yun "image-2分组" ·
Official and inference-provider prices are cash; relay prices are site credit (USD credit or CNY credit), a different unit, compared separately. Relay prices are per million total tokens at 75% input and 25% output.
All official and inference price observations
OpenAI · gpt-3.5-turbo-instruct official price: input 1.5, output 2 USD per million tokens (OpenAI, observed 2026-10-17). Cheapest inference provider: OpenRouter, input 1.5, output 2 USD per million tokens. Cheapest relay: zhangsan.yun, group "image-2 group [machine translation] (on site: image-2分组)" 0.28125 CNY_CREDIT per million total tokens (credit price, not cash, observed 2026-10-23). 44 sites have comparable prices; 72 sites list this model.Relay blended price uses 75% input and 25% output. Conditions: Standard processing · documentSection: Flagship models · processingMode: standard
Price ranges per million tokens
Official cash prices · Lowest 1.625 · median 1.625 · highest 1.625 · 1 quotes USD / per million tokens
Inference provider cash prices · Lowest 1.625 · median 1.625 · highest 1.625 · 1 quotes USD / per million tokens
Relay USD credit prices · Lowest 0.9 · median 1.875 · highest 11.366 · 22 quotes USD / per million tokens, site credit
Relay CNY credit prices · Lowest 0.28125 · median 2.8125 · highest 18.25 · 5 quotes CNY / per million tokens, site credit
Official price
| Provider | Tariff | Input | Output | Cache read | Cache write | Unit | Observed | Conditions and source |
|---|---|---|---|---|---|---|---|---|
| OpenAI | Standard | 1.5 | 2 | — | — | USD / 1M tokens | Standard processing · documentSection: Flagship models · processingMode: standardFull price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [],
"contextTier": null,
"processingMode": "standard",
"conditionNotes": [
"documentSection: Flagship models",
"processingMode: standard"
],
"effectiveFrom": null,
"effectiveUntil": null
}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 | Tariff | Input | Output | Cache read | Cache write | Unit | Observed | Conditions and source | vs official |
|---|---|---|---|---|---|---|---|---|---|
| OpenRouter · Aggregator | Standard | 1.5 | 2 | — | — | USD / 1M tokens | Full price conditions{
"sourceUnit": "USD_PER_TOKEN",
"sourceAmounts": {
"input": "0.0000015",
"output": "0.000002"
},
"conditions": [],
"contextTier": null,
"processingMode": null,
"conditionNotes": [],
"effectiveFrom": null,
"effectiveUntil": null
}Official source |
Older official and inference provider prices
Earlier price observations and their original conditions
Official price
| Provider | Tariff | Input | Output | Cache read | Cache write | Unit | Observed | Conditions and source |
|---|---|---|---|---|---|---|---|---|
| OpenAI | Standard | 1.5 | 2 | — | — | USD / 1M tokens | Standard processing · documentSection: Flagship models · processingMode: standardFull price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [],
"contextTier": null,
"processingMode": "standard",
"conditionNotes": [
"documentSection: Flagship models",
"processingMode: standard"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source |
Inference providers
| Provider | Tariff | Input | Output | Cache read | Cache write | Unit | Observed | Conditions and source |
|---|---|---|---|---|---|---|---|---|
| OpenRouter · Aggregator | Standard | 1.5 | 2 | — | — | USD / 1M tokens | Full price conditions{
"sourceUnit": "USD_PER_TOKEN",
"sourceAmounts": {
"input": "0.0000015",
"output": "0.000002"
},
"conditions": [],
"contextTier": null,
"processingMode": null,
"conditionNotes": [],
"effectiveFrom": null,
"effectiveUntil": null
}Official source |
Unit: CNY credits per 1M tokens. These are site-credit prices; actual cost depends on each site’s top-up rate.
Price range: lowest 0.28125 · median 2.8125 · highest 18.25 (5 quotes, CNY credits per million total tokens)
Relays
Prices below are in site credit, not cash.
| # | Provider | Plan / conditions | Input ↑CNY credits / 1M | Output CNY credits / 1M | Cache readCNY credits / 1M | BlendedCNY credits / 1M | Details |
|---|---|---|---|---|---|---|---|
| Recent price | |||||||
| 01 | zhangsan.yunAsk or discussCollected: Collected this cycle View 1 plans | image-2 group [machine translation]Group on site: image-2分组 image-2 image generation [machine translation]Original: image-2生图 Operator pending verification | 0.225 | 0.45 | — | 0.28125Median price ÷ this price: 10× | Full prices and sources |
| 02 | ai.soruxgpt.comAsk or discussCollected: Collected this cycle View 1 plans | default General channel [machine translation]Original: 通用渠道 Operator pending verification | 1.5 | 3 | — | 1.875Median price ÷ this price: 1.5× | Full prices and sources |
| 03 | vakv.cnAsk or discussCollected: Collected this cycle View 1 plans 1 more site of the same companyBasis: identical quotes, same status-page name, logo or server address. Counted as one company in the ranking; this is not a legal finding. | az-gpt-亚力桑那 (Not yet translated) 地区-亚力桑那 (Not yet translated) Operator pending verification | 2.25 | 4.5 | — | 2.8125Median price ÷ this price: 1× | Full prices and sources |
| 04 | hy88.myAsk or discussCollected: Collected this cycle View 1 plans | gpt_azure GPT premium quality group [machine translation]Original: GPT高质量分组 Operator pending verification | 6.75 | 9 | — | 7.3125Median price ÷ this price: 0.4× | Full prices and sources |
| 05 | api.tacklekey.comAsk or discussCollected: Collected this cycle View 1 plans | default Name on site: openai/gpt-3.5-turbo-instruct Default group Operator pending verification | 16.846 | 22.462 | — | 18.25Median price ÷ this price: 0.2× | Full prices and sources |
How this ranking works
All per-token prices: 93,968 prices from 854 sites (about 751 companies). 84,786 are ranked, from 838 sites (about 736 companies); 9,182 more are listed separately and not ranked. Prices collected up to 2026-10-24.
This model has 192 recorded prices; 100 can be compared directly. Not comparable yet: price not parsed yet 56, scope of the official doc price not confirmed 16, new price under review; showing the previous one 10, ratio looks unset 4, tiered by rules (see Tiered prices) 1
6 recent · 0 stale (older than 10 days, or not updated by this refresh) · 0 unverified timestamps. Minimum and median only count recent paid prices; older prices stay in the table. 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.
Sources not accepted this cycle and reasons
FAQ
Which API is cheapest for OpenAI · gpt-3.5-turbo-instruct?
zhangsan.yun, group "image-2分组 (image-2 group)", 0.28125 CNY credit per million total tokens, observed 2026-10-23. 44 sites have comparable prices.
What is the official price for OpenAI · gpt-3.5-turbo-instruct?
Input 1.5, output 2 USD per million tokens, checked 2026-10-17. Lowest inference provider: OpenRouter, input 1.5, output 2 USD per million tokens.
How do I use OpenAI · gpt-3.5-turbo-instruct in Claude Code or Codex?
Install Grandet Skill, then say "Connect the cheapest OpenAI · gpt-3.5-turbo-instruct API to Claude Code for me". Install Skill →