ModelRefs / DeepSeek R1 vs Claude Sonnet 4 — Benchmarks, Pricing & Codi…
DeepSeek R1 vs Claude Sonnet 4 — Benchmarks, Pricing & Codi…
DeepSeek R1 vs Claude Sonnet 4: side-by-side benchmarks, pricing, context windows, coding ability and deployment. Pick the right model for your stack.
Overview
Claude Sonnet 4: Claude Sonnet 4 is Anthropic's May 2025 hybrid-reasoning model for coding, visual reasoning, tool use, and agent workflows. The dated claude-sonnet-4-20250514 snapshot was retired on Anthropic-operated platforms on June 15, 2026 and is retained as a historical evaluation and migration reference.
DeepSeek R1: DeepSeek R1 is DeepSeek's open-source reasoning model, trained with reinforcement learning to produce chain-of-thought reasoning before answering. Released in January 2025 under the MIT license, it matched or exceeded closed reasoning models on several math and coding benchmarks.
Context window: Claude Sonnet 4 accepts up to 200,000 tokens, DeepSeek R1 up to 128,000. Confirm the limit for your specific deployment channel before relying on it.
Claude Sonnet 4 vs DeepSeek R1 at a glance
| Attribute | Claude Sonnet 4 | DeepSeek R1 |
|---|---|---|
| Provider | Anthropic | DeepSeek |
| Released | 2025-05-22 | 2025-01-20 |
| Context window | 200,000 tokens | 128,000 tokens |
| Input price | $3/M tokens | $0.55/M tokens |
| Output price | $15/M tokens | $2.19/M tokens |
| Licence | Proprietary | MIT |
| Self-hostable | No, hosted only | Yes, open weights |
| Modalities | text, vision | text |
Benchmarks reported for both
| Benchmark | Claude Sonnet 4 | DeepSeek R1 | Reported |
|---|---|---|---|
| gpqa | 75.4 | 71.5 | 2025-05-22 / 2025-01-20 |
Scores are as published by their cited sources on the dates shown. Different runs use different harnesses, prompts, and dates, so treat these as directional evidence rather than a head-to-head result.
Where they differ most
- Cost Efficiency: Claude Sonnet 4 37%, DeepSeek R1 75%. DeepSeek R1 leads on this dimension.
- Coding: Claude Sonnet 4 57%, DeepSeek R1 66%. DeepSeek R1 leads on this dimension.
- Reasoning: Claude Sonnet 4 73%, DeepSeek R1 76%. DeepSeek R1 leads on this dimension.
Capability scores are ModelRefs' own derived signals, not vendor claims or benchmark results. Validate against your own workload before relying on them.
Continue your research
Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to DeepSeek R1 vs Claude Sonnet 4 — Benchmarks, Pricing & Codi….
Frequently asked questions
Which is better, DeepSeek R1 or Claude Sonnet 4?
DeepSeek R1 and Claude Sonnet 4 target different workloads — see the benchmark and pricing tables for a side-by-side answer.
Is DeepSeek R1 cheaper than Claude Sonnet 4?
Compare $0.00055 vs $0.00300 on this page.