InferIndex
Language, English, EN
Account

ProvidersAlibaba

Alibaba

The 45 models Alibaba serves, direct and through aggregators, with the price and conditions of each offer.

Prices seen via Kilo Gateway, OpenRouter, Eden AI, LLM Gateway, LLM API, Requesty, Vercel AI Gateway

No training on promptsNumber of this provider's offers whose published policy says prompts are not used for training, out of all its offers.
42 / 80 offers
Cheapest on InferIndexModels for which this provider has the lowest price on InferIndex.
18 / 45 models

Offers

AllAt the lowestAbove the lowest 18 of 80 offers
Alibaba: LLM API prices
Model BlendedA single price that mixes input and output: 3 input tokens for 1 output token, per million tokens. It makes offers easy to rank; your real cost depends on your own mix.$/1M In$/1M Out$/1M ObservationGap to the lowest price we track for this model. CtxThe maximum amount of text, counted in tokens, the model can take in and write in a single request. Past this limit, the request is refused or cut. Offer
Qwen-Plus (qwen/qwen-plus)via AlibabaAlibabaprompt up to 128K tokens: up to 128K: $0.115 / $0.287; up to 256K: $0.345 / $2.87; up to 1M: $0.689 / $6.88 (Input / Output, per million tokens) $0.158 $0.115 $0.287 Cheapest. The lowest price on InferIndex for this model. – See pricing at Alibaba (opens in a new tab)
Qwen3 Coder Flash (qwen/qwen3-coder-flash)via AlibabaAlibabaprompt up to 32K tokens: up to 32K: $0.144 / $0.574; up to 128K: $0.216 / $0.861; up to 256K: $0.359 / $1.43; up to 1M: $0.717 / $3.58 (Input / Output, per million tokens) $0.252 $0.144 $0.574 Cheapest. The lowest price on InferIndex for this model. – See pricing at Alibaba (opens in a new tab)
Qwen3 Coder Plus (qwen/qwen3-coder-plus)via RequestyRequestyFee 5%: Requesty adds a 5% markup (read on requesty.ai/pricing on Oct 31). Offers are ranked with this fee included.+1prompt up to 33K (32,677) tokens: up to 33K (32,677): $1.00 / $5.00; up to 132K (131,071): $1.80 / $9.00; up to 263K (262,143): $3.00 / $15.00; above that: $6.00 / $60.00 (Input / Output, per million tokens) $2.00  $1.00  $5.00  Cheapest. The lowest price on InferIndex for this model. 1M Go to offer at Requesty (opens in a new tab)
Qwen3 Max (qwen/qwen3-max)via RequestyRequestyFee 5%: Requesty adds a 5% markup (read on requesty.ai/pricing on Oct 31). Offers are ranked with this fee included.+1prompt up to 33K (32,677) tokens: up to 33K (32,677): $0.861 / $3.44; up to 132K (131,071): $1.43 / $5.74; above that: $2.15 / $8.60 (Input / Output, per million tokens)
2 routes
 $1.51  $0.861 $3.44  Cheapest. The lowest price on InferIndex for this model. 262k Go to offer at Requesty (opens in a new tab)
LLM APIhttps://www.alibabacloud.com/help/en/model-studio/privacy-noticeUnconfirmed. Last checked 18 October 2026: the last published value, not a confirmed one+1Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest $6.00  $3.00  $15.00  – – See pricing at LLM API (opens in a new tab)
Qwen3 VL Plus (qwen/qwen3-vl-plus)via AlibabaAlibabaprompt up to 32K tokens: up to 32K: $0.143 / $1.43; up to 128K: $0.215 / $2.15; up to 256K: $0.43 / $4.30 (Input / Output, per million tokens) $0.466 $0.143 $1.43  Cheapest. The lowest price on InferIndex for this model. – See pricing at Alibaba (opens in a new tab)
Qwen3.5-122B-A10B (qwen/qwen3.5-122b-a10b)via AlibabaAlibabafp8How finely the model's numbers are stored on the provider's servers. Lower precision (fp8, fp4) is cheaper to run and can slightly change answer quality; "unknown" means the provider doesn't say.prompt up to 128K tokens: up to 128K: $0.115 / $0.917; up to 256K: $0.287 / $2.29 (Input / Output, per million tokens) $0.316 $0.115 $0.917 Cheapest. The lowest price on InferIndex for this model. – See pricing at Alibaba (opens in a new tab)
Qwen3.5-27B (qwen/qwen3.5-27b)via AlibabaAlibabafp8prompt up to 128K tokens: up to 128K: $0.086 / $0.688; up to 256K: $0.258 / $2.06 (Input / Output, per million tokens) $0.237 $0.086 $0.688 Cheapest. The lowest price on InferIndex for this model. – See pricing at Alibaba (opens in a new tab)
Qwen3.5-35B-A3B (qwen/qwen3.5-35b-a3b)via AlibabaAlibabafp8prompt up to 128K tokens: up to 128K: $0.057 / $0.459; up to 256K: $0.229 / $1.84 (Input / Output, per million tokens) $0.158 $0.057 $0.459 Cheapest. The lowest price on InferIndex for this model. – See pricing at Alibaba (opens in a new tab)
Qwen3.5 397B A17B (qwen/qwen3.5-397b-a17b)via AlibabaAlibabafp8prompt up to 128K tokens: up to 128K: $0.172 / $1.03; up to 256K: $0.43 / $2.58 (Input / Output, per million tokens) $0.387 $0.172 $1.03  Cheapest. The lowest price on InferIndex for this model. – See pricing at Alibaba (opens in a new tab)
Qwen3.5 Flash (qwen/qwen3.5-flash)via AlibabaAlibabaprompt up to 128K tokens: up to 128K: $0.029 / $0.287; up to 256K: $0.115 / $1.15; up to 1M: $0.172 / $1.72 (Input / Output, per million tokens) $0.094 $0.029 $0.287 Cheapest. The lowest price on InferIndex for this model. – See pricing at Alibaba (opens in a new tab)
Qwen3.5 Plus (qwen/qwen3.5-plus)via AlibabaAlibabaprompt up to 128K tokens: up to 128K: $0.115 / $0.688; up to 256K: $0.287 / $1.72; up to 1M: $0.573 / $3.44 (Input / Output, per million tokens) $0.258 $0.115 $0.688 Cheapest. The lowest price on InferIndex for this model. – See pricing at Alibaba (opens in a new tab)
Qwen3.6 Flash (qwen/qwen3.6-flash)via AlibabaAlibabaprompt up to 256K tokens: up to 256K: $0.165 / $0.99; up to 1M: $0.66 / $3.96 (Input / Output, per million tokens) $0.371 $0.165 $0.99  Cheapest. The lowest price on InferIndex for this model. – See pricing at Alibaba (opens in a new tab)
Qwen3.6 Plus (qwen/qwen3.6-plus)via AlibabaAlibabaprompt up to 256K tokens: up to 256K: $0.276 / $1.65; up to 1M: $1.10 / $6.60 (Input / Output, per million tokens) $0.62  $0.276 $1.65  Cheapest. The lowest price on InferIndex for this model. – See pricing at Alibaba (opens in a new tab)
Qwen3.7 Flash (qwen/qwen3.7-flash)via AlibabaAlibabaprompt up to 32K tokens: up to 32K: $0.028 / $0.11; up to 256K: $0.083 / $0.33; up to 1M: $0.165 / $0.66 (Input / Output, per million tokens) $0.049 $0.028 $0.11  Cheapest. The lowest price on InferIndex for this model. – See pricing at Alibaba (opens in a new tab)
Qwen3.7 Plus (qwen/qwen3.7-plus)via AlibabaAlibabaprompt up to 256K tokens: up to 256K: $0.276 / $1.10; up to 1M: $0.826 / $3.30 (Input / Output, per million tokens) $0.482 $0.276 $1.10  Cheapest. The lowest price on InferIndex for this model. – See pricing at Alibaba (opens in a new tab)
Qwen3.8 Flash (qwen/qwen3.8-flash)via AlibabaAlibabafp8 $0.18  $0.113 $0.382 Cheapest. The lowest price on InferIndex for this model. – See pricing at Alibaba (opens in a new tab)
Qwen3.8 Max (0902) (qwen/qwen3.8-max-0902)via AlibabaAlibaba $2.48  $1.65  $4.95  Cheapest. The lowest price on InferIndex for this model. – See pricing at Alibaba (opens in a new tab)
Qwen3.8 Omni Flash (qwen/qwen3.8-omni-flash)via AlibabaAlibabafp8 $0.18  $0.113 $0.382 Cheapest. The lowest price on InferIndex for this model. – See pricing at Alibaba (opens in a new tab)

No training on promptsPrompts may be used for trainingTraining terms not published

One row per offer, at its cheapest route at this provider; the other routes (hosted API, aggregators) open on the row. Blended = (3 × input + output) / 4, per million tokens. Prices in USD, converted at the ECB rate when the provider bills in another currency.