Very long inputs
Choose Grok 4.3
Grok 4.3 reads up to 1M tokens per request, against 200k for Claude Haiku 3.5.
Claude Haiku 3.5 vs Grok 4.3: price, context and capabilities
Choose Grok 4.3 for very long inputs and the latest release; on the other points the two are level or the data is missing.
In short
- Claude Haiku 3.5 has been retired; Grok 4.3 is the one you can still call.
- A price comparison is not possible: one of them has no comparable published price.
- Grok 4.3 reads more per request: 1M tokens against 200k.
- Grok 4.3 is the newer model (Apr 30, 2026, against October 2024).
- Only Grok 4.3 offers reasoning.
Which should you choose?
Each answer below comes straight from the published prices, specifications and independent benchmark results.
Latest release
Choose Grok 4.3
Grok 4.3 is the newer release (Apr 30, 2026, against October 2024 for Claude Haiku 3.5).
Specifications side by side
| Claude Haiku 3.5 | Grok 4.3 | |
|---|---|---|
| Provider | Anthropic | xAI |
| Category | Language models | Language models |
| Status | Retired | Generally available |
| Headline price | $1.60 / 1M tokens | $1.56 / 1M tokens |
| Input | $0.80 / 1M tokens | $1.25 / 1M tokens |
| Output | $4.00 / 1M tokens | $2.50 / 1M tokens |
| Cached input | $0.08 / 1M tokens | $0.20 / 1M tokens |
| Context window | 200k | 1M |
| Max output | No data | No data |
| Released | October 2024 | Apr 30, 2026 |
| Knowledge cutoff | No data | No data |
| Licence | Proprietary | Proprietary |
| Capabilities | Vision, Tool calling, Structured output, Prompt caching, Batch API | Vision, Reasoning, Tool calling, Structured output, Prompt caching, Batch API |
| API model id | claude-3-5-haiku-20241022 | grok-4.3 |
Benchmarks side by side
Leader in bold.
| Benchmark | Claude Haiku 3.5 | Grok 4.3 |
|---|---|---|
| Intelligence Index | No data | 24.9 |
| Terminal-Bench Hard | No data | 37.9% |
| SciCode | No data | 48.3% |
| GPQA Diamond | No data | 90.1% |
| Humanity's Last Exam | No data | 37.2% |
| IFBench (instruction following) | No data | 81.3% |
| τ²-Bench (agentic tool use) | No data | 97.7% |
| MMMU-Pro (visual reasoning) | No data | 78.1% |
| Long-context reasoning (AA-LCR) | No data | 73% |
Independent evaluations by Artificial Analysis, run the same way for every model, at the reasoning setting shown. Percentages unless marked as an index.
Frequently asked questions
Should I choose Claude Haiku 3.5 or Grok 4.3?
Choose Grok 4.3 for very long inputs and the latest release; on the other points the two are level or the data is missing.
Which is cheaper, Claude Haiku 3.5 or Grok 4.3?
A price comparison is not possible: one of them has no comparable published price.
Which has the larger context window, Claude Haiku 3.5 or Grok 4.3?
Grok 4.3 reads more per request: 1M tokens against 200k.
What is the difference between Claude Haiku 3.5 and Grok 4.3?
Claude Haiku 3.5 is made by Anthropic and Grok 4.3 by xAI. Claude Haiku 3.5 has been retired; Grok 4.3 is the one you can still call. A price comparison is not possible: one of them has no comparable published price. Grok 4.3 reads more per request: 1M tokens against 200k. Grok 4.3 is the newer model (Apr 30, 2026, against October 2024). Only Grok 4.3 offers reasoning.
Which is newer, Claude Haiku 3.5 or Grok 4.3?
Grok 4.3 was released on Apr 30, 2026 and Claude Haiku 3.5 on October 2024.