DeepSeek
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....
Cost / 1M tokens
Very low usage$0.119
input
$0.024
cached input
$0.238
output
Context Window
1M
Up to 944K max output
Modalities
text → text
DeepSeek tokenizer
Quickstart & API
deepseek/deepseek-v4-flash-0731Best for & Strengths
Key Strengths
Recommended Workloads in ChatOSS
- Coding assistants
- Fast development
- Self-hosted AI
Verified Evaluations
Benchmarks & Frontier Comparison
How DeepSeek V4 Flash 0731 compares against leading open-weight and proprietary frontier models across independent agentic coding and reasoning suites.
| Benchmark (Metric) | DeepSeek V4 Flash 0731 | DeepSeek V4.1 Flash | GLM 5.3 | Kimi K3.1 Pro | Claude Opus 5.5 |
|---|---|---|---|---|---|
| Agentic & Software Engineering | |||||
| ChatOSS Agentic Coding Index (%) | 44.2% | 63.2% | 58.3% | 65% | 74.1% |
| SWE-Bench Verified (%) | 88.8% | 91.5% | 95.4% | 94.8% | 97% |
| DeepSWE v1.1 (Pass@1 %) | 54.4% | 77% | 69% | 73.5% | 74.2% |
| Vibe Code Bench v1.1 (%) | 74.7% | 87.7% | 78.1% | 88.4% | 90.3% |
| Terminal-Bench 4.0 (%) | 9.09% | 42.3% | 42% | 46.2% | 65.2% |
| Code Migration (%) | 38.6% | 45.6% | 44.2% | 52% | 66.7% |
| Intelligence & Token Economics | |||||
| Artificial Analysis Intelligence Index (0–100) | 34.3 | 39.5 | 44.8 | 55.1 | 57.6 |
| Input Price (/ 1M tokens) | $0.119 | $0.15 | $1.40 | $2.00 | $4.00 |
| Output Price (/ 1M tokens) | $0.238 | $0.60 | $4.40 | $10.00 | $20.00 |
ChatOSS Agentic Coding Index
ChatOSS Benchmark Audit · 4-benchmark composite mean
SWE-Bench Verified
Vals AI · Terminus 2
DeepSWE v1.1
DeepSWE / Official Audit · Mini-SWE-Agent
Vibe Code Bench v1.1
Vals.ai · OpenHands
Terminal-Bench 4.0
Vals.ai / Artificial Analysis · Terminus 2
Terminal-Bench 2.1
Vals.ai · Terminus 2
Code Migration
Vals.ai · Vals evaluation harness
Artificial Analysis Intelligence Index
Artificial Analysis
Design Arena: 3D
Design Arena · Rank #46 (48.7% win)
Design Arena: ASCIIART
Design Arena · Rank #64 (33.3% win)
Design Arena: Code Generation
Design Arena · Rank #53 (46.4% win)
Design Arena: Data Visualization
Design Arena · Rank #66 (41.1% win)
Active Provider Endpoints (25)
Upstream inference providers serving DeepSeek V4 Flash 0731, with per-provider pricing, context limits, quantization, and 24-hour uptime.
| Provider | Input / 1M | Output / 1M | Cache Read / 1M | Context | Max Output | Quantization | Uptime (24h) |
|---|---|---|---|---|---|---|---|
Relacecache relace/fp4 | $0.042 | $0.169 | $0.028 | 1M | 944K | fp4 | 100.0% |
Baiducache baidu/fp8 | $0.044 | $0.133 | $0.0014 | 1M | 131K | fp8 | 99.7% |
Rekacache reka | $0.05 | $0.28 | $0.04 | 262K | 131K | — | 100.0% |
DeepInfracache deepinfra/fp8 | $0.06 | $0.18 | $0.015 | 1M | 384K | fp8 | 100.0% |
Wafercache wafer/fast | $0.10 | $0.23 | $0.095 | 1M | 944K | nvfp4 | 100.0% |
DigitalOceancache digitalocean | $0.119 | $0.238 | $0.024 | 1M | 944K | — | 100.0% |
BaseTencache baseten/fp8 | $0.13 | $0.26 | $0.028 | 1M | 384K | fp8 | 100.0% |
BaseTencache baseten/fp32 | $0.13 | $0.26 | $0.028 | 1M | 384K | fp32 | 100.0% |
Venicecache venice | $0.13 | $0.26 | $0.028 | 1M | 33K | — | 100.0% |
CoreWeavecache coreweave/fp8 | $0.13 | $0.28 | $0.07 | 262K | 236K | fp8 | 99.9% |
Inceptroncache inceptron/fp4 | $0.13 | $0.367 | $0.027 | 1M | 944K | fp4 | 100.0% |
StreamLakecache streamlake/fp8 | $0.132 | $0.396 | $0.0042 | 1M | 384K | fp8 | 100.0% |
Coherecache cohere | $0.14 | $0.28 | $0.07 | 1M | 384K | — | 98.4% |
Parasailcache parasail/fp8 | $0.14 | $0.28 | $0.05 | 1M | 944K | fp8 | 100.0% |
Sail Researchcache sail-research/us | $0.15 | $0.30 | $0.042 | 1M | 944K | fp4 | 100.0% |
Sail Researchcache sail-research/fp4 | $0.15 | $0.30 | $0.042 | 1M | 944K | fp4 | 100.0% |
Alibabacache alibaba | $0.176 | $0.528 | $0.018 | 1M | 393K | — | 97.4% |
Alibabacache alibaba/us-east-1 | $0.187 | $0.561 | $0.019 | 1M | 393K | — | 99.8% |
Mancer 2 mancer/fp8 | $0.20 | $0.60 | — | 1M | 944K | fp8 | 99.1% |
SiliconFlowcache siliconflow/fp8 | $0.22 | $0.66 | $0.028 | 1M | 393K | fp8 | 99.9% |
GMICloudcache gmicloud/fp8 | $0.286 | $0.858 | $0.0091 | 1M | 944K | fp8 | 100.0% |
Phalacache phala | $0.308 | $0.924 | $0.02 | 1M | 393K | — | 100.0% |
Novitacache novita/fp8 | $0.409 | $1.23 | $0.026 | 1M | 393K | fp8 | 100.0% |
AtlasCloudcache atlas-cloud/fp4 | $0.44 | $1.32 | $0.028 | 1M | 393K | fp4 | 99.9% |
Cloudflarecache cloudflare | $0.44 | $1.32 | $0.014 | 1M | 944K | — | 100.0% |
Supported API Parameters
Parameters accepted by this model when called through ChatOSS or OpenRouter.
Compare Similar Models
Browse all models →DeepSeek
DeepSeek V4.1 Flash 1017
DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the `deepseek-flash` API model name. V4.1 Flash is a sparse mixture-of-experts model...
DeepSeek
DeepSeek V4.1 Flash
DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...
DeepSeek
DeepSeek V4 Flash Vision Exp
DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of DeepSeek V4 Flash 0731 from DeepSeek, adding image understanding while matching the base model on text capabilities including agents,...
DeepSeek
DeepSeek V4 Pro 0813
DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.
Anthropic
Claude Opus 5.5
Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code...
Moonshot AI
Kimi K3.1 Pro
Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, 3D...