Qwen3 235B A22b Instruct 2507
Context
262K
Max output
262K
Serving providers
6
Cheapest input
$0.09 /1M
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
Benchmarks
independent evaluations · source: ARC Prize and Artificial AnalysisSpeed & latency
Output speed
62 t/s
tokens / second
Time to first token
2.36s
latency
Headline indices
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| ARC-AGI-2 | 1% | default | $0.004 | |||||||||||||
| CritPt | 0% | default | — | |||||||||||||
| ||||||||||||||||
| EvalComputeProxy | 292.7 | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| GDPval | 544.4 | reasoning: true | — | |||||||||||||
| GPQA Diamond | 79% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| Humanity's Last Exam | 16% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| IFBench | 51% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| LiveCodeBench | 79% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| Long-Context Reasoning | 71% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| MMLU-Pro | 84% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| Omniscience | -44.0 | default | — | |||||||||||||
| ||||||||||||||||
| Omniscience Accuracy | 0.2 | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| Omniscience Non Hallucination | 0.2 | default | — | |||||||||||||
| ||||||||||||||||
| SciCode | 42% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| TerminalBench Hard | 15% | default | — | |||||||||||||
| ||||||||||||||||
| TerminalBench v2.1 | 12% | reasoning: true | — | |||||||||||||
| τ-bench Banking | 8% | reasoning: true | — | |||||||||||||
| τ²-bench | 53% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
Pricing by serving provider
standard tier · per 1M tokens · click a provider to expandInput pricing runs from $0.09 to $3.00 per 1M tokens across 6 providers, so the dearest route costs 3233% more than the cheapest for the same model.
| Serving provider | Input /1M | Output /1M | Endpoints | ||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| DeepInfraCheapest | $0.09 | $0.55 | 1 | ||||||||||||||||
| |||||||||||||||||||
| NovitaCheapest | $0.09 | $0.58 | 1 | ||||||||||||||||
| |||||||||||||||||||
| Fireworks AI | $0.22 | $0.88 | 1 | ||||||||||||||||
| |||||||||||||||||||
| Replicate | $0.26 | $1.06 | 1 | ||||||||||||||||
| |||||||||||||||||||
| Scaleway | $0.75 | $2.25 | 1 | ||||||||||||||||
| |||||||||||||||||||
| Crusoe | $3.00 | $3.00 | 1 | ||||||||||||||||
| |||||||||||||||||||
Price history
input + output $/1M since we started tracking Input Output
Input down 31% since first tracked
Cost calculator
estimate your monthly spend on this model$62
estimated / month
Model IDs
copy the exact identifier for your platformdeepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507novita/qwen/qwen3-235b-a22b-instruct-2507fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b-instruct-2507replicate/qwen/qwen3-235b-a22b-instruct-2507scaleway/qwen/qwen3-235b-a22b-instruct-2507crusoe/Qwen/Qwen3-235B-A22B-Instruct-2507
Frequently asked questions
Qwen3 235B A22b Instruct 2507 pricing, context and availabilityHow much does Qwen3 235B A22b Instruct 2507 cost?
Qwen3 235B A22b Instruct 2507 costs $0.09 per 1M input tokens and $0.55 per 1M output tokens at its cheapest provider via DeepInfra. Across 6 serving providers, input prices range from $0.09 to $3.00 per 1M tokens.
What is the context window of Qwen3 235B A22b Instruct 2507?
Qwen3 235B A22b Instruct 2507 accepts up to 262K tokens of context and can return up to 262K output tokens.
Which providers serve Qwen3 235B A22b Instruct 2507?
Qwen3 235B A22b Instruct 2507 is available from 6 serving providers, each with its own pricing and model ID. DeepInfra is currently the cheapest.
What can Qwen3 235B A22b Instruct 2507 do?
Qwen3 235B A22b Instruct 2507 supports tool use and structured output.
Other Alibaba models
compare pricing across the Alibaba lineupQwen3 32B$0.08/1M · 8 providersQwen3.6 35B A3B$0.10/1M · 7 providersQwQ 32B$0.15/1M · 7 providersQwen3 Next 80B A3B Instruct$0.09/1M · 6 providersQwen3 Next 80B A3B Thinking$0.14/1M · 6 providersQwen3.6 27B$0.15/1M · 6 providersQwen3 30B A3B$0.09/1M · 5 providersQwen3 235B A22B$0.18/1M · 5 providers
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI