deepseek-v4-flash · Released date not recorded
| Provider | DeepSeek |
|---|---|
| Family | DeepSeek V4 |
| Modality | text |
| Context | 1,000,000 tokens |
| Max output | 384,000 tokens |
| Reasoning | Yes |
| Tool calling | Yes |
| Structured output | Yes |
| Open weights | No / not recorded |
| Licence | — |
No verified Cybatar-run benchmark result has been published for this model yet.
Versioned observations tied to the exact deployment and source date.
| Effective | Deployment | Mode | Input / 1M | Cached / 1M | Output / 1M | Source |
|---|---|---|---|---|---|---|
| 23 Aug 2026 | DeepSeek | standard | USD 0.14 | USD 0.0028 | USD 0.28 | Source ↗ |
Cached input represents cache-hit pricing; normal input is cache-miss pricing.
Evidence ↗DeepSeek lists V4 Flash and V4 Pro as current API models with 1M-token context support.
Evidence ↗Reported by independent evaluators or the model provider. These are contextual research observations, not Cybatar-run scores.
| Benchmark | Score | Configuration / harness | Provenance | Source |
|---|---|---|---|---|
| AA-Briefcase 2026-08 | 1285 Elo | Model evaluation · reasoning effort: max · release: 0731 | Independent | Artificial Analysis |
| Artificial Analysis Intelligence Index v4.1.1 | 52 | Model evaluation · reasoning effort: max · release: 0731 | Independent | Artificial Analysis |
| GDPval-AA v2 | 1559 Elo | Model evaluation · reasoning effort: max · release: 0731 | Independent | Artificial Analysis |
| Terminal-Bench 2.1 | 79 % | Model evaluation · reasoning effort: max · release: 0731 | Independent | Artificial Analysis |
| Tau3-Banking 1.0.1 | 31 % | Model evaluation · reasoning effort: max · release: 0731 | Independent | Artificial Analysis |
| SciCode 2026 | 50 % | Model evaluation · reasoning effort: max · release: 0731 | Independent | Artificial Analysis |
| Humanity's Last Exam 2026 | 37 % | Model evaluation · reasoning effort: max · release: 0731 | Independent | Artificial Analysis |
| GPQA Diamond 2026 | 91 % | Model evaluation · reasoning effort: max · release: 0731 | Independent | Artificial Analysis |
| AA-Omniscience Index 2026-08 | -16 | Model evaluation · reasoning effort: max · release: 0731 | Independent | Artificial Analysis |
| AA-Omniscience Hallucination Rate 2026-08 | 84 % | Model evaluation · reasoning effort: max · release: 0731 | Independent | Artificial Analysis |