Get started

Qwen3 235B A22B Instruct 2507

Nebius text

nebius/Qwen/Qwen3-235B-A22B-Instruct-2507

Input

$0.2000

per 1M input tokens

Output

$0.6000

per 1M output tokens

Cache read

$0.0500

per 1M cached read tokens

Cache write

n/a

per 1M cache write tokens

Context window

262,144

Max output

262,144

Effective date

Nov 4, 2026

Estimate a workload

Enter token counts to see the cost at this model's rates.

Estimated cost: $0.00

Price history

blended $ per 1M tokens (3:1)
$0.00 $0.49 $0.97 $1.46 Sep 6, 2026: $0.30 Nov 4, 2026: $0.30 Sep 6, 2026 Nov 4, 2026
Effective Input Output Blended
Nov 4, 2026 $0.20 $0.60 $0.30
Sep 6, 2026 $0.20 $0.60 $0.30

Qwen3 235B A22B Instruct 2507 on other providers

Deepinfra · $0.0900 in / $0.5500 out Novita · $0.0900 in / $0.5800 out Wandb · $0.1000 in / $0.1000 out Fireworks Ai · $0.2200 in / $0.8800 out Replicate · $0.2640 in / $1.06 out Scaleway · $0.7500 in / $2.25 out Crusoe · $3.00 in / $3.00 out

Other Nebius models

nebius/Qwen/Qwen3-Embedding-8B · $0.0000/Mtok out nebius/Qwen/Qwen2.5-Coder-7B · $0.0300/Mtok out nebius/BAAI/bge-en-icl · $0.0000/Mtok out nebius/BAAI/bge-multilingual-gemma2 · $0.0000/Mtok out nebius/intfloat/e5-mistral-7b-instruct · $0.0000/Mtok out nebius/meta-llama/Llama-Guard-3-8B · $0.0600/Mtok out

Source: litellm. Confirm against the provider's official pricing before relying on these figures.