Today's price · per 1M tokens
Input
$0.140
per 1M tokens
Output
$0.280
per 1M tokens
Blended
$0.175
blended $/1M — 3:1 weighted input:output
Cached input
$0.003
2% of input — prompt caching
Available on 3 hosts
cheapest blended first · $ per 1M tokensDeepSeek V4 Flash is sold by 3 providers. Prices are per 1M tokens (blended = (3×input + 1×output) ÷ 4). The first-party row is the model maker; “vs first-party” shows each host’s blended price relative to it.
| Host | Input | Output | Blended | vs first-party |
|---|---|---|---|---|
| DeepInfra details → | $0.090 | $0.180 | $0.113 | -36% |
| DeepSeek first-party | $0.140 | $0.280 | $0.175 | — |
| Fireworks details → | $0.140 | $0.280 | $0.175 | 0% |
Overview
DeepSeek's fast, ultra-cheap open-weight (MIT) MoE — 284B parameters (13B active) with a native 1M-token context and aggressive prompt caching. $0.14/$0.28 per 1M tokens.
Capabilities
struck through = not supportedBenchmark performance
accuracy % · higher is better- AA Intelligence Index: 51.8 (Artificial Analysis composite across reasoning, knowledge and coding evals)
- AA Agentic Index: 48.4 (Tool use, planning, autonomy)
- AA-Omniscience Index: -14.3 (−100–100)
- GDPval-AA v2: 1558.4 ELO (Real-world work tasks, human baseline = 1000)
- LMSYS Chatbot Arena: 1435.8 ELO (Human preference)
- Ranks #19 of 67 benchmarked models by average score
- Ranks #32 of 150 comparably-measured models by percentile score, across 11 independent measurements
- Ranks #4 of 150 comparably-tested models by normalized performance per dollar top value
- Strongest at LiveCodeBench — 91.6%, #4 of 23
107.9 tokens/sec output 1.42s latency to first token (TTFT)
Source: Vellum LLM Leaderboard · updated Aug 9, 2026 · See full rankings →
Specifications
- Provider
- DeepSeek
- Context window
- 1M tokens
- Modality
- text
- Parameters
- Proprietary
- Open source
- No — proprietary
- Released
- Apr 24, 2026
- Status
- Current
- Last updated
- Jun 25, 2026
- Tags
Availability verified: Jul 31, 2026 — listed on DeepSeek's own page