DeepSeek
·Released on Jul 31, 2026DeepSeek V4 Flash 0731 API Benchmarks, Pricing & Provider Data
Compare DeepSeek V4 Flash 0731 with another model
Choose a model to open its comparison page.
LLM
DeepSeek V4 Flash 0731 benchmark, API pricing, and provider data cover undefined API provider} other undefined API providers}}, with prices starting at $0.000044/M. DeepSeek V4 Flash 0731 free API options are available from undefined provider} other undefined providers}}. The page also shows measured API speed and first-token latency.
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 workfl...
Quality
#55of 112
59.0
LMSpeed score
Speed
74char/s
2.70 s
Cost
$0.000044/ 1M · 8:1 in:out
$0.00000704 in · $0.000037 out
Category Performance
Observed-capability estimates with uncertainty reported separately from independent benchmark families.
- Coverage
- 5 / 8
- Methodology
- V3.0
#1Reasoning58.7RatedGlobal rank #93/4 Measured dimensions
80% interval: 50.3–67.0
abstract logicPrior only
scientific causal60.8
critpt · critpt / gpqa · aa_gpqa_diamond / hle · aa_hle
multistep constraints57.5
mmlu_pro · mmlu_pro
evidence verification57.7
lcr · lcr / mrcr · mrcr1m
#2Math57.9Estimated2/4 Measured dimensions
80% interval: 45.8–70.1
foundational mathPrior only
competition math60.7
hmmt · hmmt_feb2026
proof frontier55.2
imo · imo_answer_bench
applied tool mathPrior only
#3Agents51.3RatedGlobal rank #353/4 Measured dimensions
80% interval: 42.9–59.6
planningPrior only
tool use51
mcp_atlas · mcp_atlas / toolathlon · toolathlon
environment execution47.9
browsecomp · browse_comp / gdpval_aa · benchlm_agentic_gdpval_aa / terminalbench · benchlm_agentic_terminal_bench2
recovery reliability55.1
cyber_gym · cyber_gym
#4Coding50.6RatedGlobal rank #254/4 Measured dimensions
80% interval: 44.3–56.9
code generation56.2
scicode · aa_sci_code
repository engineering50.2
nl2repo · nl2_repo / swe_pro · swe_pro
debugging testing50.7
swe_multilingual · benchlm_coding_swe_multilingual / swe_verified · swe_verified
tooling quality45.1
terminalbench · benchlm_coding_terminal_bench2
#5Knowledge47.5Provisional1/4 Measured dimensions
80% interval: 29.5–65.6
broad knowledgePrior only
professional knowledgePrior only
factuality47.5
simpleqa · simple_qa
retrieval open bookPrior only
No data:MultilingualMultimodalInstruction following
Specifications
Input and output token limits for this model, plus how it ranks on long-context understanding.
INPUT
1.3Mtokens
≈ 1.6K pages of text
OUTPUT
943.7Ktokens
8K128K1M4M
1.3M
Features
Technical Details
- Input
- Output
- Released
- Jul 2026
- Tokenizer
- DeepSeek
- Architecture
- text->text
- Moderated
- No
- Supported parameters
- frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_pparallel_tool_callspresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_atop_ktop_logprobstop_p
Rankings
Excels at
Falls behind in
Detailed scores
Updated: Aug 20, 2026Overall
undefined metric} other undefined metrics}}
Overall score59.0#55 / 112DeepSWE54.4#16 / 21
Overall
undefined metric} other undefined metrics}}
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Agents
V3.0undefined metric} other undefined metrics}} · Rated
Score51.3#3580% interval42.9–59.63/4 Measured dimensionsAgentic score49.3#57 / 77Terminal-Bench 2.056.9#37 / 53
Agents
V3.0undefined metric} other undefined metrics}} · Rated
Dimensions and evidence
Planning & decompositionPrior only
Tool use51
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
mcp_atlas · mcp_atlas · z -0.40 · q 1.00
toolathlon · toolathlon · z -0.02 · q 1.00
Environment & long-horizon execution47.9
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
browsecomp · browse_comp · z -0.68 · q 1.00
gdpval_aa · benchlm_agentic_gdpval_aa · z 0.06 · q 1.00
terminalbench · benchlm_agentic_terminal_bench2 · z -0.43 · q 1.00
Recovery & completion reliability55.1
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
cyber_gym · cyber_gym · z -0.06 · q 1.00
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Coding
V3.0undefined metric} other undefined metrics}} · Rated
Score50.6#2580% interval44.3–56.94/4 Measured dimensionsCoding score53.4#43 / 87Codeforces3052.0#2 / 4
Coding
V3.0undefined metric} other undefined metrics}} · Rated
Dimensions and evidence
Code generation56.2
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
scicode · aa_sci_code · z 0.65 · q 1.00
Repository engineering50.2
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
nl2repo · nl2_repo · z 1.18 · q 1.00
swe_pro · swe_pro · z -0.78 · q 1.00
Debugging & testing50.7
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
swe_multilingual · benchlm_coding_swe_multilingual · z -0.58 · q 1.00
swe_verified · swe_verified · z 0.45 · q 1.00
Tool-assisted development & quality45.1
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
terminalbench · benchlm_coding_terminal_bench2 · z -0.63 · q 1.00
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Reasoning
V3.0undefined metric} other undefined metrics}} · Rated
Score58.7#980% interval50.3–67.03/4 Measured dimensionsMMLU-Pro86.2%#18 / 129GPQA88.1%#49 / 218
Reasoning
V3.0undefined metric} other undefined metrics}} · Rated
Dimensions and evidence
Abstract logicPrior only
Scientific & causal reasoning60.8
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
critpt · critpt · z 0.70 · q 1.00
gpqa · aa_gpqa_diamond · z 0.97 · q 1.00
hle · aa_hle · z 0.83 · q 1.00
Multi-step constraints57.5
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
mmlu_pro · mmlu_pro · z 0.80 · q 1.00
Evidence integration & verification57.7
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
lcr · lcr · z 0.05 · q 1.00
mrcr · mrcr1m · z 1.23 · q 0.75
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Knowledge
V3.0undefined metric} other undefined metrics}} · Provisional
Score47.580% interval29.5–65.61/4 Measured dimensionsKnowledge score61.1#57 / 83SimpleQA34.1#3 / 4
Knowledge
V3.0undefined metric} other undefined metrics}} · Provisional
Dimensions and evidence
Broad knowledgePrior only
Professional knowledgePrior only
Factuality47.5
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
simpleqa · simple_qa · z -0.43 · q 0.17
Retrieval & open-book usePrior only
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Artificial Analysis Intelligence Index
LMSpeed rank#8
Score51.8
Sourcebenchlm.ai
UpdatedAug 20, 2026
Confidence2
AA-Omniscience Hallucination Rate
LMSpeed rank#13
Score91.7
Sourcebenchlm.ai
UpdatedAug 20, 2026
Confidence2
Math
V3.0undefined metric} other undefined metrics}} · Estimated
Score57.980% interval45.8–70.12/4 Measured dimensionsHMMT Feb 202694.8#3 / 18IMOAnswerBench88.4#3 / 7
Math
V3.0undefined metric} other undefined metrics}} · Estimated
Dimensions and evidence
Foundational mathPrior only
Competition math60.7
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
hmmt · hmmt_feb2026 · z 1.55 · q 1.00
Advanced proofs55.2
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
imo · imo_answer_bench · z 0.20 · q 0.88
Applied & tool-assisted mathPrior only
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Multilingual
V3.0undefined metric} other undefined metrics}} · No data
No data80% interval30.8–69.20/4 Measured dimensions
Multilingual
V3.0undefined metric} other undefined metrics}} · No data
Dimensions and evidence
Cross-language understandingPrior only
Multilingual generationPrior only
Reasoning transferPrior only
Low-resource robustnessPrior only
Multimodal
V3.0undefined metric} other undefined metrics}} · No data
80% interval30.8–69.20/4 Measured dimensionsDesign Arena Website1219.0#45 / 78
Multimodal
V3.0undefined metric} other undefined metrics}} · No data
Dimensions and evidence
Perception & OCRPrior only
Document & spatial understandingPrior only
Visual reasoningPrior only
Video & grounded actionPrior only
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Instruction following
V3.0undefined metric} other undefined metrics}} · No data
No data80% interval30.8–69.20/4 Measured dimensions
Instruction following
V3.0undefined metric} other undefined metrics}} · No data
Dimensions and evidence
Constraint followingPrior only
Structured outputPrior only
Novel-instruction generalizationPrior only
Multi-turn & long instructionsPrior only
OpenRouter endpoints
26 endpointsThird-party OpenRouter endpoint data, shown separately from LMSpeed measurements. Some 30-minute live performance fields only appear after syncing with an OpenRouter API key.
| Provider endpoint | Input | Output | 1d uptime | 30m latency | 30m throughput | Context / output |
|---|---|---|---|---|---|---|
Novita novita/fp8 | $0.409/M | $1.23/M | 100.0% | — | — | undefined tokens / undefined tokens |
Alibaba alibaba | $0.352/M | $1.06/M | 100.0% | — | — | undefined tokens / undefined tokens |
Cloudflare cloudflare | $0.440/M | $1.32/M | 100.0% | — | — | undefined tokens / undefined tokens |
CoreWeave coreweave/fp8 | $0.130/M | $0.280/M | 100.0% | — | — | undefined tokens / undefined tokens |
BaseTen baseten/fp8 | $0.130/M | $0.260/M | 100.0% | — | — | undefined tokens / undefined tokens |
Morph morph/bf16 | $0.123/M | $0.348/M | 99.9% | — | — | undefined tokens / undefined tokens |
AtlasCloud atlas-cloud/fp4 | $0.440/M | $1.32/M | 99.9% | — | — | undefined tokens / undefined tokens |
GMICloud gmicloud/fp8 | $0.286/M | $0.858/M | 99.9% | — | — | undefined tokens / undefined tokens |
DigitalOcean digitalocean | $0.119/M | $0.238/M | 99.8% | — | — | undefined tokens / undefined tokens |
Phala phala | $0.440/M | $1.32/M | 99.8% | — | — | undefined tokens / undefined tokens |
NextBit nextbit/fp8 | $0.352/M | $1.06/M | 99.8% | — | — | undefined tokens / undefined tokens |
Inceptron inceptron/fp4 | $0.064/M | $0.173/M | 99.8% | — | — | undefined tokens / undefined tokens |
Relace relace/fp4 | $0.060/M | $0.120/M | 99.7% | — | — | undefined tokens / undefined tokens |
DeepInfra deepinfra/fp8 | $0.060/M | $0.180/M | 99.7% | — | — | undefined tokens / undefined tokens |
Reka reka/fp4 | $0.110/M | $0.660/M | 99.6% | — | — | undefined tokens / undefined tokens |
Baidu baidu/fp8 | $0.440/M | $1.32/M | 99.6% | — | — | undefined tokens / undefined tokens |
Venice venice | $0.175/M | $0.350/M | 99.4% | — | — | undefined tokens / undefined tokens |
Wafer wafer/fast | $0.100/M | $0.250/M | 99.1% | — | — | undefined tokens / undefined tokens |
Sail Research sail-research/fp4 | $0.074/M | $0.342/M | 99.0% | — | — | undefined tokens / undefined tokens |
OpenInference open-inference/fp8 | $0.040/M | $0.100/M | 98.9% | — | — | undefined tokens / undefined tokens |
Fireworks fireworks | $0.220/M | $0.660/M | 98.2% | — | — | undefined tokens / undefined tokens |
Makora makora | $0.090/M | $0.195/M | 98.2% | — | — | undefined tokens / undefined tokens |
Mancer 2 mancer/fp8 | $0.200/M | $0.600/M | 98.1% | — | — | undefined tokens / undefined tokens |
Together together | $0.140/M | $0.280/M | 97.8% | — | — | undefined tokens / undefined tokens |
StreamLake streamlake/fp8 | $0.057/M | $0.172/M | 97.1% | — | — | undefined tokens / undefined tokens |
SiliconFlow siliconflow/fp8 | $0.220/M | $0.660/M | 91.6% | — | — | undefined tokens / undefined tokens |
Pricing Comparison
Compare DeepSeek V4 Flash 0731 API pricing across 97 providers. Prices range from $0.000044/M to $10273.97/M. OAI2API offers the lowest rate at $0.000044/M. 4 providers offer free API credits or a free tier.
Showing 20 model IDs of 55.
Alternatives & Similar Models
DeepSeek V4 Flash
deepseek-v4-flash
DeepSeek V4 Flash is a fast, cost-efficient language model in the DeepSeek V4 family, optimized for low-latency chat, coding assistance, and high-throughput API workloads while retaining strong reasoning quality.
50 shared providers
DeepSeek V4 Pro
deepseek-v4-pro
DeepSeek V4 Pro is the professional-tier DeepSeek V4 model, targeting frontier reasoning, coding, and agent workflows with maximum capability.
50 shared providers
GLM-5.2
glm-5-2
Zhipu GLM-5.2 is Zhipu latest flagship coding and agentic model with a 1M-token context window, enhanced reasoning modes, and long-horizon software engineering capabilities.
48 shared providers
GPT-5.4
gpt-5-4
OpenAI GPT-5.4 extends the GPT-5 family with stronger instruction following, deeper tool use, and improved performance on coding, math, and long-document analysis.
46 shared providers
GLM-5.1
glm-5-1
Zhipu GLM-5.1 is a next-generation GLM model aimed at frontier reasoning, coding, and bilingual agent applications.
45 shared providers
Claude Opus 4.6
claude-opus-4-6
Anthropic Claude Opus 4.6 is the most capable Claude Opus tier, optimized for complex analysis, long-horizon coding, and high-stakes enterprise reasoning workloads.
44 shared providers
Frequently Asked Questions
- What benchmark data does DeepSeek V4 Flash 0731 include?
- LMSpeed shows DeepSeek V4 Flash 0731 benchmark context, API price, output speed, first-token latency, and provider data across 101 providers when those signals are available.
- What is the DeepSeek V4 Flash 0731 API price?
- DeepSeek V4 Flash 0731 has pricing from undefined provider} other undefined providers}}, ranging from $0.000044/M to $10273.97/M. OAI2API has the lowest listed price.
- What does the DeepSeek V4 Flash 0731 API pricing table include?
- The DeepSeek V4 Flash 0731 API pricing table compares 101 providers by input price, output price, free tier status, speed, first-token latency, and recent health data when available.
- Which provider has the cheapest DeepSeek V4 Flash 0731 API pricing?
- OAI2API currently has the lowest listed DeepSeek V4 Flash 0731 price at $0.000044/M across undefined provider} other undefined providers}}.
- Can I compare DeepSeek V4 Flash 0731 API price and speed together?
- Yes. LMSpeed shows DeepSeek V4 Flash 0731 API price, output speed, first-token latency, and provider health on the same page so you can compare cost and performance together.
- Is DeepSeek V4 Flash 0731 API free?
- Yes, DeepSeek V4 Flash 0731 free API options are available through 4 providerundefined other undefined} on LMSpeed, including Dext API, 初叶🍂Furry API, 初叶🍂Furry API, 初叶🍂Furry API. These providers offer free API credits or a free tier with no per-token charges.
- Where can I get DeepSeek V4 Flash 0731 free API access?
- LMSpeed currently lists 4 free API providerundefined other undefined} for DeepSeek V4 Flash 0731: Dext API, 初叶🍂Furry API, 初叶🍂Furry API, 初叶🍂Furry API. Check each provider row before using it because free tier limits can change.