DeepSeek V4 Flash (Reasoning, Max Effort)
DeepSeekDeepSeek
Release Date
2026-04-24
Parameters
—
Context Length
1.0M
Modalities
text
Capability Radar
39
general
54
coding
89
reasoning
62
scienceest.
79
agents
0
multimodal
Science uses a reasoning proxy when dedicated science benchmarks are unavailable.
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Code Ranking | 101 | 70.0 | AA |
| General Ranking | 39 | 81.0 | AA |
| Science | 61 | 76.0 | AA |
Benchmark Scores (LLM Stats)
No benchmark data available
AA Evaluation Indices
Coding Index56.2
Intelligence Index40.3
Tau21.0
Gpqa0.9
Ifbench0.8
Lcr0.6
Terminalbench V2 10.6
Scicode0.4
Terminalbench Hard0.4
Hle0.3
Tau Banking0.2
LLM Stats Category Scores
No category score data available
Pricing
Input Price$0.14 / 1M tokens
Output Price$0.28 / 1M tokens
Blended Price (3:1)$0.175 / 1M tokens
Cache Read Price$0.0028 / 1M tokens
Speed
Tokens/sec102.3
Time to First Token0.89s
Time to Answer55.76s
Provider Price Ranking
Provider Price Ranking
15 providers
Cheapest: UnoRouterMost Expensive: Charm Hyper
ProviderInputOutput
1UnoRouterCheapest
$0.0625
$0.125
2LLM Gateway
$0.076
$0.153
3Neuralwatt
$0.104
$0.207
4routing.run
$0.112
$0.224
5CrofAI
$0.12
$0.21
6Cortecs
$0.133
$0.266
7Venice AI
$0.138
$0.275
8DeepSeekPRIMARY
$0.14
$0.28
9OpenCode Go
$0.14
$0.28
10Alibaba (China)
$0.14
$0.28
11OpenCode Zen
$0.14
$0.28
12Auriko
$0.14
$0.28
13EmpirioLabs AI
$0.14
$0.28
14Azure
$0.19
$0.51
15Charm Hyper
$0.2
$0.4
Compare pricing across different API providers for this model.