DeepSeek V3
Language Retired Full comparison ↗ deepseek/deepseek-v3 · by DeepSeek
· mixture-of-experts
Pricing — 1 offering(s)
Input tokens
Deprecated — pricing unavailable
- $0.20 / 1M tokens (input) Historical 2025-03-24 → 2025-11-30
Output tokens
Deprecated — pricing unavailable
- $0.77 / 1M tokens (output) Historical 2025-03-24 → 2025-11-30
Showing the active price and any recorded history. Full pricing history is available via the paid API — see API docs.
See how DeepSeek V3 fits into a cost-aware routing setup
See how →Capability profile
reasoning strong
coding moderate
tool use moderate
instruction following strong
context window strong
multilingual moderate
speed moderate
cost efficiency strong
Coding benchmarks
View full leaderboard →| Benchmark | Score | Harness | Source |
|---|---|---|---|
| livecodebench ↗ | 49.2% 2024-12 | — | 📊 leaderboard ↗ |
| aider-polyglot ↗ | 55.1% 2025-03 | aider | 📊 leaderboard ↗ |
| swe-bench-verified ↗ | 42.0% 2024-12 | agentless | 📄 paper ↗ |
| bigcodebench ↗ | 34.5% 2024-12 | — | 📊 leaderboard ↗ |
| bigcodebench ↗ | 31.8% 2025-03 | — | 📊 leaderboard ↗ |
Operator guidance
Exceptional price-to-performance ratio — one of the cheapest frontier-class models available. Route here when cost is the primary constraint and capability is still required. Available directly via DeepSeek API or on Replicate, Together AI.
Use cases
- Cost-optimised code generation and general reasoning
- RAG and retrieval pipelines where cost is primary constraint
- Open-weights deployment on own infrastructure
Limitations
- Chinese lab; some organisations have data-residency or compliance constraints
- Open weights means self-hosting cost must be factored for on-prem use
- Capability ratings are qualitative, not a single cited benchmark run
Citations
Compare models
ComparingDeepSeek V3with
Pick a model above to see the comparison.