AI Rate CardBase model
Qwen3 235B A22B Instruct 2507 FP8 Throughput
from $0.20 at 1 provider
alibaba/qwen3-235b-a22b-instruct-2507-fp8-throughput · 235B parameters (22B active) · 1 provider · Text models ·
Price alerts
Found 1
Simple Full
Ranges in one field: "from-to" - "0.5-3", "-3" (up to), "128k-" (from); a colon works too. Several ticked values of one column are ORed, columns are ANDed.
Input price history, $/1M
Latest: minimum $0.20, median $0.20 (Nov 4, 2026)
The QWEN family - base models: 231
- qwen
- Qwen 1.5 (0.5B) 1
- Qwen 1.5 (1.8B) 1
- Qwen 1.5 (4B) 1
- Qwen 1.5 (7B) 1
- Qwen 1.5 (14B) 1
- Qwen 1.5 (72B) 1
- Qwen 1.5 Chat (0.5B) 1
- Qwen 1.5 Chat (1.8B) 1
- Qwen 1.5 Chat (4B) 1
- Qwen 1.5 Chat (7B) 1
- Qwen 1.5 Chat (14B) 1
- Qwen 1.5 Chat (72B) 1
- qwen2-1-5b-instruct 1
- qwen2.5-3b-instruct 1
- Qwen2.5 14B Instruct 1
- Qwen2.5 32B Instruct 1
- Qwen2.5-72B-Instruct-128K 1
- qwen2-5-coder-1-5b-instruct 1
- qwen2-5-coder-3b-instruct 2
- qwen2-5-coder-7b 1
- Qwen2.5-Coder 7B Instruct 3
- qwen2.5-math-1.5b-instruct 1
- Qwen2.5-Math 7B Instruct 1
- Qwen2.5-Math 72B Instruct 1
- Qwen2.5-VL 72B Instruct 13
- qwen2-7b-instruct 4
- Qwen2-57B-A14B-Instruct 1
- qwen2-72b-instruct 2
- Qwen 2 Instruct (72B) 1
- qwen2-vl-7b-instruct 1
- qwen2-vl-72b-instruct 1
- Qwen2.5 7B Instruct 12
- Qwen 2.5 72B Instruct 14
- Qwen2.5 Coder 7B fast 1
- Qwen2.5-Coder-32B-Instruct 11
- Qwen 2.5 VL 7B Instruct 1
- Qwen 2.5 VL 32B Instruct 5
- qwen3-0-6b 2
- qwen3-1-7b 1
- qwen3-4b 5
- Qwen3 4B Instruct 2
- qwen3.5-4b-el 1
- qwen3.5-9b-el 1
- qwen3.5-flash-el 1
- qwen3.5-ocr 1
- Qwen3.5 Omni Flash Realtime 1
- Qwen3.5 Omni Plus Realtime 1
- qwen3.5-plus-el 1
- qwen3.6-plus-t 1
- qwen3.7-flash-el 1
- qwen3.7-max-el 1
- qwen3.7-max-t 1
- qwen3.8 2
- qwen3.8-2.4t-a95b-alibaba 1
- qwen3.8-2.4t-a95b-n 1
- qwen3.8-27b-alibaba 1
- qwen3.8-27b-el 1
- Qwen3.8 27B Free cached input until Oct 31, 2026, 11:59 PM UTC 1
- qwen3.8-flash-el 1
- Qwen3.8 Flash Next FP4 1
- Qwen3.8 LiveTranslate Flash Realtime 1
- qwen3.8-max-0902-el 1
- qwen3.8-max-el 1
- qwen3-8-omni-flash-realtime 1
- Qwen3 8B 12
- Qwen3 14B 14
- Qwen3 14B Instruct 1
- Qwen3 30B A3B 18
- Qwen3 30B-A3B Instruct 2507 14
- Qwen3 30B A3B Thinking 2507 8
- Qwen3 32B 26
- Qwen3 235B-A22B 16
- qwen3-235b-a22b-di 1
- Qwen3-235B-A22B-Instruct 1
- Qwen3 235B-A22B Instruct 2507 23
- Qwen3 235B A22B Instruct 2507 FP8 Throughput 1
- qwen3-235b-a22b-n 1
- Qwen3 235B-A22B Thinking 2507 17
- Qwen3 ASR 0.6B 1
- Qwen3 ASR 1.7B 1
- Qwen3-ASR Flash 1
- Qwen3-Coder 30B-A3B Instruct 19
- Qwen3-Coder 480B-A35B Instruct 28
- qwen3-coder-480b-n 1
- Qwen3 Coder Flash 10
- Qwen3 Coder Next 21
- qwen3-coder-next-n 1
- Qwen3 Coder Plus 15
- Qwen3-Embedding-0.6B-batch 1
- Qwen3 Embedding 0.6B 7
- Qwen3 Embedding 4B 6
- Qwen3-Embedding-4B-batch 1
- Qwen3 Embedding 8B 17
- Qwen3-Embedding-8B-batch 1
- Qwen3 Max 18
- qwen3-max-el 1
- qwen3-max-n 1
- Qwen3 Max Preview 6
- qwen3-max-preview-el 1
- Qwen: Qwen3 Max Thinking 8
- qwen3-max-thinking-el 1
- Qwen3-Next 80B-A3B Instruct 20
- Qwen3-Next 80B-A3B (Thinking) 14
- qwen3-next-80b-think 1
- Qwen3 Omni 30B A3B Instruct 2
- Qwen3 Omni 30B A3B Thinking 2
- Qwen3 Rerank 3
- Qwen3 Reranker 0.6B 5
- Qwen3 Reranker 4B 4
- Qwen3 Reranker 8B 5
- Qwen3 Thinking 2507 1
- Qwen3-TTS 1.7B 4
- qwen3-tts-12hz-1.7b-base 1
- Qwen3-TTS-Flash Realtime 1
- Qwen3 TTS VoiceDesign 2
- qwen3-vl-2b-instruct 1
- Qwen3-VL-4B-Instruct 2
- Qwen: Qwen3 VL 8B Instruct 9
- Qwen: Qwen3 VL 8B Thinking 7
- Qwen3 VL 30B A3B Instruct 14
- Qwen: Qwen3 VL 30B A3B Thinking 11
- Qwen: Qwen3 VL 32B Instruct 8
- Qwen/Qwen3-VL-32B-Thinking 5
- qwen3-vl-235b-a22b-i 1
- Qwen3 VL 235B A22B Instruct 17
- qwen3-vl-235b-a22b-t 1
- Qwen3 VL 235B A22B Thinking 11
- Qwen: Qwen3 VL Embedding 1
- Qwen3-VL-Embedding-2B 1
- Qwen3-VL Embedding 8B 2
- Qwen3 VL Flash (Alibaba Cloud) 4
- Qwen3 VL Instruct 1
- Qwen3-VL Plus 7
- Qwen: Qwen3 VL Rerank 1
- Qwen3-VL-Reranker-2B 1
- Qwen3-VL-Reranker-8B 1
- Qwen3 VL Thinking 1
- Qwen3.5 0.8B 1
- Qwen3.5 2B 3
- Qwen3.5 4B 6
- Qwen3.5 9B 19
- Qwen3.5 27B 19
- Qwen3.5 35B-A3B 20
- Qwen3.5 122B-A10B 23
- qwen3.5:397b 1
- Qwen3.5 397B-A17B 33
- Qwen3.5 Flash 13
- Qwen3.5 Plus 21
- Qwen3.6 27B 30
- Qwen3.6 35B-A3B 30
- Qwen3.6 Max Preview 10
- Qwen3.6 Plus 23
- Qwen3.7 Flash 14
- Qwen3.7 Max 28
- Qwen3.7 Plus 26
- Qwen3.8 2.4T A95B 28
- Qwen3.8 27B 52
- Qwen3.8 27B Abliterated 1
- Qwen 3.8 27B Uncensored 2
- Qwen3.8 Flash 29
- Qwen3.8 Flash Next 9
- Qwen3.8 Max 32
- Qwen3.8 Max 0902 13
- Qwen3.8 Max Preview 2
- Qwen3.8 Omni Flash 12
- qwen3guard-gen-0.6b 5
- Qwen3Guard-Gen-4B 1
- qwen3guard-gen-8b 5
- Qwen (7B) 1
- qwen38-27b 1
- qwen38-27b-turbo-v2 1
- qwen-2-1-5b-instruct 2
- qwen-2.5-7b-t 1
- qwen-agentworld-35b-a3b 1
- Qwen Audio 3.0 ASR 1
- Qwen Audio 3.0 ASR Stream 1
- Qwen Audio 3.0 Realtime Flash 1
- Qwen Audio 3.0 Realtime Plus 1
- Qwen Audio 3.0 TTS 2
- qwen-audio-3-1-asr 1
- qwen-audio-3.1-asr-flash 1
- qwen-audio-3-1-asr-message 1
- qwen-audio-3-1-asr-stream 1
- Qwen Audio 3.1 Realtime Flash 1
- qwen-audio-3-1-realtime-plus 1
- Qwen Audio 3.1 TTS 1
- Qwen Audio 3.1 TTS Next 1
- qwen-audio-3-1-tts-plus 1
- Qwen-Audio-3.0-TTS Flash 1
- Qwen-Audio-3.0-TTS Plus 2
- Qwen Chat (7B) 1
- Qwen Chat (14B) 1
- qwen-edit 1
- qwen-embedding-0.6b 1
- Qwen Flash 5
- qwen-flash-character 1
- Qwen Image 7
- qwen-image-2 4
- qwen-image-2.1-viggle-turbo 1
- qwen-image-2-pro 1
- Qwen Image 2.0 Pro 3
- Qwen-Image-2.1 1
- Qwen-Image-2.1-Pro 1
- Qwen-Image-2.1-Turbo 1
- qwen-image-3.0-el 1
- Qwen-Image-3.0 5
- Qwen-Image-3.0-Pro 4
- Qwen Image Edit 6
- Qwen-Image-Edit-Max 1
- Qwen-Image-Max 2
- Qwen Long 1
- Qwen Max 8
- qwen-max-longcontext 1
- Qwen-Mt-Flash 3
- qwen-mt-lite 3
- Qwen MT Plus 6
- Qwen-MT Turbo 3
- Qwen Plus 10
- Qwen Plus Character 2
- Qwen Plus Character (Japanese) 1
- qwen-qwq-32b 1
- Qwen-SEA-LION-v4.5-27B-IT 1
- qwen-sea-lion-v4-32b-it 1
- Qwen Text Embedding v3 1
- Qwen Text Embedding v4 1
- Qwen Turbo 5
- Qwen-VL Max 3
- Qwen-VL OCR 2
- Qwen-VL Plus 1
- QwQ 32B 6
- QwQ Plus 1
About the model: cost of your workload, questions, comparisons, citation
Cost of my workload → in the Tools tab: every provider of this model, cheapest first
Frequently asked questions
How much does Qwen3 235B A22B Instruct 2507 FP8 Throughput API cost?
From $0.20 input and $0.60 output per 1M tokens, at togetherai.
Which provider offers Qwen3 235B A22B Instruct 2507 FP8 Throughput cheapest?
togetherai offers the lowest price, $0.20 per 1M tokens, among 1 provider.
Source: AI Rate Card, https://airatecard.com/en/model/alibaba/qwen3-235b-a22b-instruct-2507-fp8-throughput, prices checked 2026-11-04