DeepSeek-V4-Pro-0813
- Input price
- $0.66
- Per 1 million tokens (USD)
- Output price
- $1.98
- Per 1 million tokens (USD)
- Effort levels
- 3total
- Default: High
- Benchmark results
- 8total
- Benchmark types: 8
Model information
- API model ID
- deepseek-v4-pro
- release date
- Unknown
- effort
- Low / High (default) / Max
- Effort source
- Based on DeepSeek thinking mode documentation (api-docs.deepseek.com/guides/thinking_mode).
- Claude Code
- unavailable
- Codex
- unavailable
- Availability notes
- DeepSeek official documentation provides connection instructions for Claude Code (Anthropic-compatible API, mapping claude-opus* to deepseek-v4-pro) and Codex (Responses API). These are not official options from Anthropic/OpenAI. The connection instructions are in the model provider documentation, not official model options for Claude Code / Codex, so this is false.
- Availability source
- https://api-docs.deepseek.com/quick_start/agent_integrations/codex
Price (USD per 1 million tokens)
Prices do not vary by effort; token consumption does.
| input | $0.66 |
|---|---|
| output | $1.98 |
| cache read | $0.022 |
| cache write | — |
Off-peak pricing shown. Peak (weekdays 01:00-04:00 / 06:00-10:00 UTC) is 2x: cache hit $0.044 / miss $1.32 / output $3.96. thinking is on by default (default effort high), disabled with none
deepseek-v4-pro cache hit $0.022 / $0.044, cache miss $0.66 / $1.32, output $1.98 / $3.96 (Off-peak / Peak)Benchmark results
| Benchmark | effort | Score | Source cost (metric) | measured/reported by | source | Conditions and extraction method |
|---|---|---|---|---|---|---|
| GPQA DiamondMax | Max | 91.7% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0third-party · Retrieved 2026-11-12 | Run by Epoch AI (third-party measurement). Source label "DeepSeek V4 Pro 0813 (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.transcribed from tableSource excerptgpqa_diamond.csv: Model version=deepseek-v4-pro-0813_max, Best score (across scorers)=0.9166666666666666, stderr=0.015242573629934338, Started at=2026-08-18T21:03:23.000ZLocation gpqa_diamond.csv, data row 71 (file line 124), id=nEJGtXGN588zynPkynZkxz, Model version=deepseek-v4-pro-0813_max |
| FrontierMath Tiers 1-3(v2)Max | Max | 64.6% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tiers_1_3_v2.csv) CC BY 4.0third-party · Retrieved 2026-11-12 | Run by Epoch AI (third-party measurement). Source label "DeepSeek V4 Pro 0813 (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.transcribed from tableSource excerptfrontiermath_tiers_1_3_v2.csv: Model version=deepseek-v4-pro-0813_max, Best score (across scorers)=0.6456140350877193, stderr=0.028383475205435625, Started at=2026-08-19T13:35:48.000ZLocation frontiermath_tiers_1_3_v2.csv, data row 77 (file line 103), id=b6yWmeFgsWeEiG9Qzs3NSf, Model version=deepseek-v4-pro-0813_max |
| FrontierMath Tier 4(v2)Max | Max | 26.8% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0third-party · Retrieved 2026-11-12 | Run by Epoch AI (third-party measurement). Source label "DeepSeek V4 Pro 0813 (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.transcribed from tableSource excerptfrontiermath_tier_4_v2.csv: Model version=deepseek-v4-pro-0813_max, Best score (across scorers)=0.2682926829268293, stderr=0.07005564203095158, Started at=2026-08-19T13:35:48.000ZLocation frontiermath_tier_4_v2.csv, data row 31 (file line 64), id=a4uV8HMMBAcHXLVSmZfBgX, Model version=deepseek-v4-pro-0813_max |
| OTIS Mock AIME 2024-2025Max | Max | 98.6% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, otis_mock_aime_2024_2025.csv) CC BY 4.0third-party · Retrieved 2026-11-12 | Run by Epoch AI (third-party measurement). Source label "DeepSeek V4 Pro 0813 (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.transcribed from tableSource excerptotis_mock_aime_2024_2025.csv: Model version=deepseek-v4-pro-0813_max, Best score (across scorers)=0.9861111111111112, stderr=0.00990980650017605, Started at=2026-08-18T21:03:23.000ZLocation otis_mock_aime_2024_2025.csv, data row 79 (file line 139), id=4HVvM9ZWKKPLQPcC8WYYMT, Model version=deepseek-v4-pro-0813_max |
| SimpleQA VerifiedMax | Max | 52.9% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, simpleqa_verified.csv) CC BY 4.0third-party · Retrieved 2026-11-12 | Run by Epoch AI (third-party measurement). Source label "DeepSeek V4 Pro 0813 (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.transcribed from tableSource excerptsimpleqa_verified.csv: Model version=deepseek-v4-pro-0813_max, Best score (across scorers)=0.5290581162324649, stderr=0.015808394665706597, Started at=2026-08-27T19:30:20.000ZLocation simpleqa_verified.csv, data row 59 (file line 104), id=2xfFf6KZAp2gUWYhHGkFgs, Model version=deepseek-v4-pro-0813_max |
| Chess Puzzles(Epoch AI)Max | Max | 46.0% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, chess_puzzles.csv) CC BY 4.0third-party · Retrieved 2026-11-12 | Run by Epoch AI (third-party measurement). Source label "DeepSeek V4 Pro 0813 (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.transcribed from tableSource excerptchess_puzzles.csv: Model version=deepseek-v4-pro-0813_max, Best score (across scorers)=0.46, stderr=0.05009082659620331, Started at=2026-10-13T13:13:34.000ZLocation chess_puzzles.csv, data row 144 (file line 200), id=C56VHYLMeww2wXebeJh3gg, Model version=deepseek-v4-pro-0813_max |
| MirrorCodeMax | Max | 33.3% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, mirrorcode.csv) CC BY 4.0third-party · Retrieved 2026-11-12 | Run by Epoch AI (third-party measurement). Source label "DeepSeek V4 Pro 0813 (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.transcribed from tableSource excerptmirrorcode.csv: Model version=deepseek-v4-pro-0813_max, Best score (across scorers)=0.3333333333333333, stderr=0.10026420125303973, Started at=2026-10-20T20:32:20.000ZLocation mirrorcode.csv, data row 29 (file line 47), id=4sSMLxWLPihKZSUFVUjwTh, Model version=deepseek-v4-pro-0813_max |
| Epoch Capabilities Index(ECI)not stated | not stated | 155.94 | — | Epoch AI | Epoch AI, epoch_capabilities_index/eci_scores.csv (CC BY 4.0)third-party · Retrieved 2026-11-12 | A per-model metric that combines results across multiple benchmarks and multiple efforts (not per effort). Calculated by Epoch AI.transcribed from tableSource excerpteci_scores.csv: Model=DeepSeek V4 Pro 0813, eci=155.94, eci_ci_low=154.06, eci_ci_high=158.01Location epoch_capabilities_index/eci_scores.csv, data row 41 (file line 42), Model=DeepSeek V4 Pro 0813 |
Related rankings
- Overall ranking (all models, records)
- GPQA Diamond ranking by metric (all models, records)
- FrontierMath Tiers 1-3(v2) ranking by metric (all models, records)
- FrontierMath Tier 4(v2) ranking by metric (all models, records)
- OTIS Mock AIME 2024-2025 ranking by metric (all models, records)
- SimpleQA Verified ranking by metric (all models, records)
- Chess Puzzles(Epoch AI) ranking by metric (all models, records)
- MirrorCode ranking by metric (all models, records)
- Epoch Capabilities Index(ECI) ranking by metric (all models, records)
- Recommendations by role