Loading...
Loading...
Side-by-side comparison of API pricing, context window, latency, and benchmark performance. Data refreshed daily from provider APIs and ModelStop's own latency probes.
Price (lower is better), Speed/Latency (lower is better), Performance (higher is better)
| Spec | Qwen3 235B A22B | Claude 3.5 Haiku |
|---|---|---|
| Provider | alibaba | anthropic |
| Input price / 1M tokens | Free | Free |
| Output price / 1M tokens | — | — |
| Context window | 128k tokens | — |
| Latency (p50) | — | — |
| Best benchmark score | — | — |
| Open source | Yes | No |
Qwen3 235B A22B is Alibaba's flagship mixture-of-experts model with 235B total parameters and 22B active per token. Delivers frontier-level performance on coding, reasoning, and multilingual tasks at significantly lower inference cost.
Claude 3.5 Haiku — available via AWS Bedrock (us-east-1).
Want to swap in a different model or estimate monthly costs?
Help my team choose the right model
Not sure which model fits your workload, budget, and latency requirements? Get a tailored recommendation.