Coder‑Large is a 32 B‑parameter offspring of Qwen 2.5‑Instruct that has been further trained on permissively‑licensed GitHub, CodeSearchNet and synthetic bug‑fix corpora. It supports a 32k context window, enabling multi‑file refactoring or …
Model details →Arcee AI: Coder Large vs WizardLM-2 8x22B
WizardLM-2 8x22B wins on 2 of 6 axes — pricing and capability skew in its favour for most workloads.
WizardLM-2 8x22B is Microsoft AI's most advanced Wizard model. It demonstrates highly competitive performance compared to leading proprietary models, and it consistently outperforms all existing state-of-the-art opensource models. It is an…
Model details →Side-by-side comparison
| Capability | Arcee AI: Coder Large | WizardLM-2 8x22B | Winner |
|---|---|---|---|
| Context window Maximum number of input tokens the model can attend to in a single request. | 33K | 66K | 🏆 WizardLM-2 8x22B |
| Input price (per 1M) Cost per million input tokens billed by the provider. | $0.50 | $0.62 | 🏆 Arcee AI: Coder Large |
| Output price (per 1M) Cost per million output tokens billed by the provider. | $0.80 | $0.62 | 🏆 WizardLM-2 8x22B |
| Tool / function calling First-class support for emitting structured tool calls. | — | — | Tie |
| Vision input Accepts image inputs alongside text. | — | — | Tie |
| Reasoning mode Internal chain-of-thought / extended-thinking support. | — | — | Tie |
Frequently asked questions
Is Arcee AI: Coder Large better than WizardLM-2 8x22B?
WizardLM-2 8x22B wins on 2 of 6 axes — pricing and capability skew in its favour for most workloads.
What's the price difference between Arcee AI: Coder Large and WizardLM-2 8x22B?
Input: $0.50 vs $0.62 per 1M tokens. Output: $0.80 vs $0.62 per 1M tokens.
What context windows do Arcee AI: Coder Large and WizardLM-2 8x22B support?
Arcee AI: Coder Large supports up to 33K tokens. WizardLM-2 8x22B supports up to 66K tokens.
Do both Arcee AI: Coder Large and WizardLM-2 8x22B support tool calling?
Arcee AI: Coder Large: not advertised. WizardLM-2 8x22B: not advertised.