Text model
qwen/qwen3-235b-a22b-instruct-2507 pricing
Replicate charges $0.264 per million input tokens and $1.06 per million output tokens for qwen/qwen3-235b-a22b-instruct-2507. Below: every rate that applies, what common workloads cost, and cheaper options.
- Input
- $0.264/ 1M
- Output
- $1.06/ 1M
All rates
| Tier | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
| Standard | $0.264 | $1.06 | — | — |
USD per million tokens. Long-context tiers apply when the whole prompt, cached tokens included, passes the threshold.
Work it out
What common workloads cost
| Workload | Per call | Cost per call | Calls a month | Per month |
|---|---|---|---|---|
| Chat reply | 1,500 input and 400 output tokens | $0.00082 | 100,000 | $82.00 |
| RAG answer, cached context | 2,000 fresh + 4,000 cached input, 500 output | $0.00211 | 100,000 | $211.40 |
| Agent step | 4,000 fresh + 8,000 cached input, 800 output | $0.00402 | 250,000 | $1,004.00 |
| Batch summary | 3,000 input and 300 output tokens via the Batch API | — | 1,000,000 | — |
Planning a mix of models? Simulate a workload with qwen/qwen3-235b-a22b-instruct-2507, alongside anything else you run.
Cheaper options
Current models that cost at least 15% less for a typical chat reply. Cheaper isn't always equivalent: test quality on your own prompts, then use veqen diff to see the impact at your volume.
| Model | Chat reply | Saving |
|---|---|---|
| replicate/openai/gpt-oss-120b | $0.000558 | 32% |
| replicate/openai/gpt-4o-mini | $0.000465 | 43% |
| bedrock/cohere.command-light-text-v14 | $0.00069 | 16% |
| bedrock/qwen.qwen3-235b-a22b-2507-v1:0 | $0.000682 | 17% |
Price history
No price changes since Veqen started tracking this model.
Compare
Last verified with price book 2026-10-22. Sources: Replicate pricing and LiteLLM's MIT-licensed price file. Track every call to this model, per customer or project: install the SDK.