Text model
microsoft/WizardLM-2-8x22B pricing
DeepInfra charges $0.48 per million input tokens and $0.48 per million output tokens for microsoft/WizardLM-2-8x22B. Below: every rate that applies, what common workloads cost, and cheaper options.
- Input
- $0.48/ 1M
- Output
- $0.48/ 1M
- Context
- 65.5Ktokens
All rates
| Tier | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
| Standard | $0.48 | $0.48 | — | — |
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 | $0.000912 | 100,000 | $91.20 |
| RAG answer, cached context | 2,000 fresh + 4,000 cached input, 500 output | $0.00312 | 100,000 | $312.00 |
| Agent step | 4,000 fresh + 8,000 cached input, 800 output | $0.00614 | 250,000 | $1,536.00 |
| 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 microsoft/WizardLM-2-8x22B, 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 |
|---|---|---|
| deepinfra/MiniMaxAI/MiniMax-M2.7 | $0.000775 | 15% |
| deepinfra/Qwen/Qwen3-Next-80B-A3B-Thinking | $0.00077 | 16% |
| azure-ai/Llama-4-Maverick-17B-128E-Instruct-FP8 | $0.000775 | 15% |
| nebius/reflection/beam | $0.000775 | 15% |
Price history
No price changes since Veqen started tracking this model.
Compare
Last verified with price book 2026-10-22. Sources: DeepInfra pricing and LiteLLM's MIT-licensed price file. Track every call to this model, per customer or project: install the SDK.