gpt-5.1 vs claude-sonnet-4-5
Side-by-side comparison of gpt-5.1 and claude-sonnet-4-5 — benchmarks, pricing, context window and capabilities. Both are accessible through Requesty's unified API. gpt-5.1 outperforms claude-sonnet-4-5 on 9 of 9 shared benchmarks.
gpt-5.1
Input / 1M
$1.25
Output / 1M
$10.00
Context
400K
Model ID
openai/gpt-5.1
claude-sonnet-4-5
Input / 1M
$3.00
Output / 1M
$15.00
Context
1M
Model ID
anthropic/claude-sonnet-4-5
Benchmark comparison
MMLU Proknowledge
gpt-5.189.4%
claude-sonnet-4-583.8%
GPQA Diamondreasoning
gpt-5.183.2%
claude-sonnet-4-574.2%
HumanEvalcoding
gpt-5.194.7%
claude-sonnet-4-592.0%
SWE-Bench Verifiedcoding
gpt-5.176.8%
claude-sonnet-4-570.8%
MATHmath
gpt-5.194.8%
claude-sonnet-4-587.5%
AIME 2024math
gpt-5.190.1%
claude-sonnet-4-576.1%
MMMUmultimodal
gpt-5.180.3%
claude-sonnet-4-573.1%
LiveBenchreasoning
gpt-5.176.2%
claude-sonnet-4-569.5%
τ-bench Retailagentic
gpt-5.173.5%
claude-sonnet-4-567.3%
Scores sourced from official model cards, Artificial Analysis, and public leaderboards. Benchmarks measure specific skills and don't capture every aspect of model quality.
Pricing & specifications
| gpt-5.1 | claude-sonnet-4-5 | |
|---|---|---|
| Input price / 1M | $1.25 | $3.00 |
| Output price / 1M | $10.00 | $15.00 |
| Context window | 400K tokens | 1M tokens |
| Max output | 128K tokens | 64K tokens |
| Vision input | Yes | Yes |
| Tool calling | Yes | Yes |
| Reasoning | Yes | Yes |
| Prompt caching | Yes | Yes |
| Computer use | — | Yes |
| Provider | OpenAI Inc. | Anthropic PBC |
Questions people ask
Is gpt-5.1 better than claude-sonnet-4-5?
gpt-5.1 outperforms claude-sonnet-4-5 on 9 of 9 shared benchmarks. See the benchmark comparison above for specifics — gpt-5.1 and claude-sonnet-4-5 have different strengths across reasoning, coding, math and multimodal tasks.
Which is cheaper — gpt-5.1 or claude-sonnet-4-5?
gpt-5.1 is cheaper. gpt-5.1 costs $1.25/$10.00 per 1M input/output tokens, while claude-sonnet-4-5 costs $3.00/$15.00.
Can I use gpt-5.1 and claude-sonnet-4-5 through the same API?
Yes. Requesty provides a single OpenAI-compatible API that routes to both. Change just the "model" parameter to switch — "openai/gpt-5.1" or "anthropic/claude-sonnet-4-5" — no other code changes needed.
What are the context windows?
gpt-5.1 supports up to 400K tokens of context. claude-sonnet-4-5 supports up to 1M tokens. Longer context means you can feed larger documents or codebases in a single prompt, though quality often degrades past 128K for most models.
Switch between gpt-5.1 and claude-sonnet-4-5 with one line of code
Requesty provides a single OpenAI-compatible API for 400+ models. Change the model parameter, not your code.
Get started free