DeepSeek V4 Flash 0423
DeepSeekReleased Apr 24, 2026Open weights · MITdeepseek-v4-flash-0423
- Intelligence (Epoch)
- 146 · 55th of 111
- Reasoning
- yes, with effort levels
- Knowledge cutoff
- March 2026
- Context
- 1M tokens
- Max output
- 393k tokens
- Input
- text
- API features
- tools, structured outputs, JSON mode, seed, logprobs
Read Oct 23, 06:00 UTC from the hosts' published offers and OpenRouter, spec sheet from DeepSeek · cutoff: aiknowledgecutoff.com
Intelligence for the price
2 models score higher for the same price or less; it ranks 3 of the 11 models at its price or below.
Epoch Capabilities Index against the lowest input + output price per M, log scale · prices Oct 23. Score: Epoch AI, CC BY 4.0, 146 with an interval of 144 to 148.
Against its rivals
The best of its price range and the top score
- DeepSeek V4 Flash 0423this model$0.21146
- Claude Opus 5.5top score$24.00169
- DeepSeek V4 Flash 0731same price range$0.21155
- GLM-5.3-Flashsame price range$0.19153
Bars: Epoch Capabilities Index (Epoch AI, CC BY 4.0), drawn from 100, below the lowest score in the catalogue · price: lowest input + output per M.
Speed by provider
Output speed of DeepSeek V4 Flash 0423 at each host, fastest first (the 10 fastest of 12)
- Baidu106 tok/s0.89 s to first token
- Relace96 tok/s0.44 s to first token
- Cloudflare73 tok/s0.89 s to first token
- Parasail70 tok/s0.79 s to first token
- Azure OpenAI64 tok/s1.15 s to first token
- GMICloud62 tok/s1.98 s to first token
- StreamLake40 tok/s1.77 s to first token
- AtlasCloud39 tok/s2.18 s to first token
- Venice29 tok/s1.41 s to first token
- SiliconFlow29 tok/s1.13 s to first token
Speed: OpenRouter, median of the last 30 min, read Oct 23, 06:00 UTC · a snapshot of real traffic before the daily read, not a daily average · bars from zero.
- Parameters
- 284B
- 13B active per token (MoE)
- Memory needed
- 170 GB
- in INT4 · 341 GB in INT8
- Smallest cloud setup
- 4× H100
- 320 GB · $8.60/h, about $6,278 a month
- Worth it above
- 30B tokens
- a month, against the cheapest API at $0.21 per M
| Quantization | Memory | Smallest cloud GPU | Quality |
|---|---|---|---|
| INT4 (Q4) | 170 GB | 4× H100 · $8.60/h | smallest footprint, minor quality loss |
| INT8 (Q8) | 341 GB | 8× H100 · $17.20/h | near-lossless |
| FP16 (full) | 682 GB | multi-node, over 640 GB | reference quality |
At home: in INT4 it fits a Mac Studio M5 Ultra (256 GB unified), about $9,499 once, or $0.3615/h over 3 years, electricity aside; it pays for itself after about 45B tokens against the cheapest API.
Memory ≈ parameters × bytes per parameter × 1.2 · cloud price: on-demand rate, running 24/7 · builds: GGUF, AWQ, MLX, GPTQ, Ollama · break-even calculator
| Provider | Input | Output | Cache ↑ | tok/s | First token | Uptime 24h | Checked |
|---|---|---|---|---|---|---|---|
| StreamLakefp8 · 1000K ctx · 375K out−50% | $0.07 | $0.14 | $0.014 | 40 | 1.77 s | 100% | Oct 23 |
| Cloudflare375K ctx (1M) | $0.44 | $1.32 | $0.014 | 73 | 0.89 s | 98.6% | Oct 23 |
| DeepInfrafp8 · 1M ctx · 64K out | $0.09 | $0.18 | $0.018 | 25 | 1.22 s | 96.8% | Oct 23 |
| GMICloudfp8 · 1.05M ctx−35% | $0.091 | $0.18 | $0.0182 | 62 | 1.98 s | 100% | Oct 23 |
| Veniceprecision not read: host terms · 1M ctx · 32K out−30% | $0.0966 | $0.19 | $0.0196 | 29 | 1.41 s | 100% | Oct 23 |
| DigitalOcean1M ctx · 375K out | $0.098 | $0.20 | $0.0196 | 26 | 0.79 s | 100% | Oct 23 |
| SiliconFlowfp8 · 1M ctx · 384K out | $0.13 | $0.28 | $0.028 | 29 | 1.13 s | 99.9% | Oct 23 |
| Baidufp8 · 1M ctx · 128K out | $0.14 | $0.28 | $0.028 | 106 | 0.89 s | 100% | Oct 23 |
| AtlasCloudfp4 (fp8) · 1M ctx · 384K out | $0.14 | $0.28 | $0.028 | 39 | 2.18 s | 100% | Oct 23 |
| Azure OpenAI1M ctx · 375K out | $0.21 | $0.56 | $0.031 | 64 | 1.15 s | 95.0% | Oct 23 |
| Relacefp4 (fp8) · 1M ctx | $0.05 | $0.45 | $0.05 | 96 | 0.44 s | 100% | Oct 23 |
| Parasailfp8 · 1M ctx | $0.14 | $0.28 | $0.07 | 70 | 0.79 s | 100% | Oct 23 |
10 of 12 providers · prices per million tokens, read Oct 23, 06:00 UTC · speed: OpenRouter, median of the last 30 min, read Oct 23, 06:00 UTC · uptime: OpenRouter, last 24 h · −N%: a discount off the host's list price · under each host: weights precision, context and max output as served, the maker's value in brackets when the host's differs
| Provider | Weights | Context | Max output | Tools | Structured outputs | Reasoning |
|---|---|---|---|---|---|---|
| StreamLake | fp8 | 1000K | 375K | yes | yes | yes |
| DeepInfra | fp8 | 1M | 64K | yes | yes | yes |
| GMICloud | fp8 | 1.05M | not read: host terms | yes | no | yes |
| Venice | not read: host terms | 1M | 32K | yes | yes | yes |
| DigitalOcean | not checked yet | 1M | 375K | yes | yes | yes |
| SiliconFlow | fp8 | 1M | 384K | yes | no | yes |
| Baidu | fp8 | 1M | 128K | yes | yes | yes |
| AtlasCloud | fp4 | 1M | 384K | yes | yes | yes |
| Parasail | fp8 | 1M | not read: host terms | yes | yes | yes |
| Relace | fp4 | 1M | not stated by the host | yes | no | yes |
| Azure OpenAI | not checked yet | 1M | 375K | yes | no | yes |
| Cloudflare | not checked yet | 375K | not checked yet | yes | yes | yes |
Weights, context and max output: read at each host's own catalogue or docs where its terms allow, otherwise as the host declares to OpenRouter; hover a cell for its source and date · tools, structured outputs, reasoning: as declared to OpenRouter · not verified by us
DeepSeek V4 Flash 0423 spec sheet, field by field, with sources
DeepSeek V4 Flash 0423 spec sheetmaker-declared
What DeepSeek declares about the model itself — read from its own weights repository and documentation, not from any host. What each endpoint actually serves is in the pricing above: the two can differ, and both are true.
- Context window
- 1,048,576 tokens
- Parameters
- 290,944,616,402≈ 290.9B
- Active experts
- 6 of 256 active per token
- Weight precision
- fp8
- License
- MIT — open weights, permissivecurated · read 2026-10-21Scope: the licence on the published weights, and nothing else. It is not the maker's acceptable-use policy, which is a separate document, and it is not the contract you sign with whichever host you call — hosts set their own terms, which this index does not read.
- Knowledge cutoff
- not published by the maker≈ March 2026 third-party estimate — not the maker's figurecurated
- Modalities
- text
- Max output (official)
- to verify
- Release date
- April 24, 2026maker's docs · read 2026-10-21
- Maker lifecycle status
- Previewmaker's docs · read 2026-10-21
Also declared in the weights
- Architecture class
- DeepseekV4ForCausalLM
- Layers
- 43
- Vocabulary
- 129,280 tokens
- Weights first published
- April 22, 2026
- Weights last updated
- June 22, 2026
- Paper
- arXiv:2606.19348
deepseek-ai/DeepSeek-V4-Flash · config.json @ 60d8d70 · read 2026-10-21 · 8 of 10 fields published by the maker
| Date | Provider | Input | Output | Change |
|---|---|---|---|---|
| Oct 23 | Baidu | $0.0909 → $0.14 | $0.18 → $0.28 | +54% |
Every published change of input or output price, newest first · change on input + output · full series: pricing-history.csv.
| Provider | Chatbot 1,000 in / 500 out | RAG / long context 8,000 in / 500 out | Batch summarize 4,000 in / 1,000 out |
|---|---|---|---|
| StreamLake | $0.14 | $0.63 | $0.42 |
| DeepInfra | $0.18 | $0.81 | $0.54 |
| GMICloud | $0.18 | $0.82 | $0.55 |
| Venice | $0.19 | $0.87 | $0.58 |
| DigitalOcean | $0.20 | $0.88 | $0.59 |
| SiliconFlow | $0.27 | $1.18 | $0.80 |
| Baidu | $0.28 | $1.26 | $0.84 |
| AtlasCloud | $0.28 | $1.26 | $0.84 |
| Parasail | $0.28 | $1.26 | $0.84 |
| Relace | $0.28 | $0.62 | $0.65 |
| Azure OpenAI | $0.49 | $1.96 | $1.40 |
| Cloudflare | $1.10 | $4.18 | $3.08 |
What each host bills for 1,000 requests of a representative job
Your own workload
Also serving DeepSeek V4 Flash 0423, without a published price
No price we can verify, so no rank.
Other DeepSeek models · all its models, hosts and history ›
- DeepSeek V4.1 Flash29 providers · from $0.47
- DeepSeek V4 Flash 073125 providers · from $0.21
- DeepSeek V4 Pro 081323 providers · from $2.50
- DeepSeek V4.1 Flash 101722 providers · from $0.39
- DeepSeek V4 Pro 042315 providers · from $2.40
- DeepSeek V3.214 providers · from $0.52