Claude Haiku 4.5 vs Cogito v2.1 671B
Side-by-side API pricing and Artificial Analysis performance for Claude Haiku 4.5 (Anthropic) and Cogito v2.1 671B (Deepcogito). Green cells mark the better value in each row.
Prices updated Jul 22, 2026, 1:32 AM UTC · refreshed hourly
| Claude Haiku 4.5 Anthropic | Cogito v2.1 671B Deepcogito | |
|---|---|---|
| Pricing | ||
| Input $/1M | $1.00 | $1.25 |
| Output $/1M | $5.00 | $1.25 |
| Blended $/1M (3:1) | $2.00 | $1.25 |
| RAG example (30K in / 2K out) | $0.04 | $0.04 |
| Quality & speed | ||
| Intelligence Index | 29.6 | — |
| Coding Index | 43.9 | — |
| Agentic Index | 16.4 | — |
| Output speed (tok/s) | — | — |
| Time to first token | — | — |
| Specs | ||
| Context window | 200K | 128K |
| Input modalities | text, image, file | text |
FAQ
Which is cheaper, Claude Haiku 4.5 or Cogito v2.1 671B?
Cogito v2.1 671B has the lower blended API price at $1.25 per 1M tokens (3:1 input:output mix), versus $2.00 for the other model. Prices are live from OpenRouter and refresh about hourly.
Which is better for RAG workloads?
Both models cost about $0.04 for a 30K/2K RAG request at current rates. Context windows are 200K (Claude Haiku 4.5) and 128K (Cogito v2.1 671B).
Which scores higher on Artificial Analysis benchmarks?
Claude Haiku 4.5 leads on the Artificial Analysis Intelligence Index (29.6 vs —). Check coding and agentic indices on this page for workload-specific tradeoffs.