Qwen3 32B
Qwen3-32B is a world-class model with comparable quality to DeepSeek R1 while outperforming GPT-4.1 and Claude Sonnet 3.7.
text → text · made by Alibaba
$0.05→$0.1per Mtok in / out
Lambda · 17 sellers
Sold by 25 ways
| Seller | Lane | Rate |
|---|---|---|
| AWS Bedrock cloud | standard | $0.15per Mtok in$0.6per Mtok outmodels.dev · read 2026-09-16 |
| DigitalOcean cloud | standard | $0.25per Mtok in$0.55per Mtok outmodels.dev · read 2026-09-16 |
| Lambda aggregator | standard | $0.05per Mtok in$0.1per Mtok outraw.githubusercontent.com · read 2026-09-16 |
| Requesty 2 ways | $0.058per Mtok in$0.2per Mtok out | |
| Requesty aggregatornot on the seller's list today | deepinfra flex | $0.058per Mtok in$0.2per Mtok outrouter.requesty.ai · read 2026-08-25 |
| Requesty aggregator | deepinfra | $0.1per Mtok in$0.3per Mtok out$0.1per Mtok cachedrouter.requesty.ai · read 2026-09-15 |
| Requesty aggregator | nebius | $0.1per Mtok in$0.3per Mtok out$0.1per Mtok cachedrouter.requesty.ai · read 2026-08-28 |
| DeepInfra aggregator | standard | $0.08per Mtok in$0.28per Mtok outapi.deepinfra.com · read 2026-08-25 |
| Hugging Face Inference Providers 3 ways | $0.29per Mtok in$0.59per Mtok out | |
| Hugging Face Inference Providers aggregator | deepinfra | $0.08per Mtok in$0.28per Mtok outrouter.huggingface.co · read 2026-08-25 |
| Hugging Face Inference Providers aggregator | nscale | $0.08per Mtok in$0.25per Mtok outrouter.huggingface.co · read 2026-08-25 |
| Hugging Face Inference Providers aggregator | standard | $0.29per Mtok in$0.59per Mtok outmodels.dev · read 2026-09-16 |
| Nous Research aggregator | standard | $0.08per Mtok in$0.28per Mtok outinference-api.nousresearch.com · read 2026-09-12 |
| OpenRouter 2 ways | $0.08per Mtok in$0.28per Mtok out | |
| OpenRouter aggregator | standard | $0.08per Mtok in$0.28per Mtok outopenrouter.ai · read 2026-08-24 |
| OpenRouter aggregatornot on the seller's list today | nebius/base | $0.1per Mtok in$0.3per Mtok outopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | siliconflow/fp8 | $0.14per Mtok in$0.57per Mtok outopenrouter.ai · read 2026-08-28 |
| OpenRouter aggregatornot on the seller's list today | groq | $0.29per Mtok in$0.59per Mtok out$0.14per Mtok cachedopenrouter.ai · read 2026-08-25 |
| Nebius Token Factory 0 ways | $0.1per Mtok in$0.3per Mtok out | |
| Nebius Token Factory aggregatornot on the seller's list today | standard | $0.1per Mtok in$0.3per Mtok outtokenfactory.nebius.com · read 2026-08-25 |
| Novita AI aggregator | standard | $0.1per Mtok in$0.45per Mtok outapi.novita.ai · read 2026-08-25 |
| ElectronHub aggregator | standard | $0.12per Mtok in$0.36per Mtok outapi.electronhub.ai · read 2026-09-16 |
| SiliconFlow aggregator | standard | $0.14per Mtok in$0.57per Mtok outmodels.dev · read 2026-09-16 |
| Vercel AI Gateway aggregator | standard | $0.16per Mtok in$0.64per Mtok outai-gateway.vercel.sh · read 2026-08-25 |
| Groq aggregator | standard | $0.29per Mtok in$0.59per Mtok outraw.githubusercontent.com · read 2026-09-16 |
| Cerebras aggregator | standard | $0.4per Mtok in$0.8per Mtok outraw.githubusercontent.com · read 2026-09-16 |
| SambaNova Cloud aggregator | standard | $0.4per Mtok in$0.8per Mtok outraw.githubusercontent.com · read 2026-09-16 |
| PPIO aggregator | standard | $0.72per Mtok in$3.26per Mtok outapi.ppinfra.com · read 2026-09-10 |
| Fireworks AI aggregator | standard | $0.9per Mtok in$0.9per Mtok outraw.githubusercontent.com · read 2026-09-16 |
Measured 13 standings
| Place | Board | Metric | Score |
|---|---|---|---|
| 24thof 105 | Vectara Hallucination Leaderboard | Hallucination Rate | 5.9 |
| 44thof 69 | Aider polyglot coding leaderboard | Percent correct | 40 |
| 48thof 72 | Aider polyglot — Epoch AI | Percent correct | 40 |
| 94thof 161 | Dtbench — Epoch AI | Accuracy | 67.47 |
| 94thof 123 | Lmca — Epoch AI | Score | 17.28 |
| 127thof 177 | Critpt — Epoch AI | Accuracy | 0.286 |
| 133rdof 143 | Artificial Analysis · Agentic Index | Index | 0.9 |
| 141stof 168 | Scicode — Epoch AI | Score | 35.417 |
| 142ndof 290 | OTIS Mock AIME 2024-2025 | mean_score | 66.944 |
| 156thof 222 | Chess puzzles — Epoch AI | mean_score | 5 |
| 162ndof 184 | Artificial Analysis · Coding Index | Index | 15.3 |
| 191stof 313 | GPQA Diamond | mean_score | 65.72 |
| 464thof 656 | Epoch capabilities index — Epoch AI | ECI Score (none) | 138.53 |
About
Qwen3 32B — a text model from Alibaba, sold by 17 companies from $0.05 in and $0.1 out per million tokens, placed 24th of 105 on Vectara Hallucination Leaderboard.
It takes text and returns text, with a context window of 128,000 tokens. It was published in April 2025, trained on material up to April 2025. Its sellers say it can reason step by step and call a tool. The catalogue files it under reasoning and code. Seventeen companies sell it. The cheapest is $0.05 in and $0.1 out per million tokens at Lambda. Beside the standard rate there are separately routed and regional lanes. It has been measured on 13 boards, and stands best at 24th of 105 on Vectara Hallucination Leaderboard.
Every current figure
- Maker
- Alibaba
- Register
- model
- Takes
- text
- Returns
- text
- Context
- 128,000 tokens
- Published
- April 2025
- Knowledge to
- April 2025
- Parameters
- 33 billion
- Licence
- not read
- Sellers
- 17
- Maker's own price
- not read
- Price
- $0.05 in and $0.1 out per million tokens — Lambda
- Boards
- 13
- Best place
- 24th of 105 — Vectara Hallucination Leaderboard
Known as 7 names
Qwen 3 32BQwen/Qwen3-32Bqwen/qwen3-32b-fp8deepinfra/Qwen/Qwen3-32Bdeepinfra/Qwen/Qwen3-32B:flexnebius/qwen/qwen3-32balibaba/qwen-3-32b