DeepSeek-V4-Flash-0731
DeepSeek
Open weights, served by a provider reached through SayGM. The provider receives the prompt under its API terms.
- Tool calling: yes
- Image input: no
Released
Jul 2026Modalities
Text · Tool callingBest price on SayGM
-75.4%In
Cached
Out
per Mtok*
SayGM vs. list price
SayGM's best available rate for deepseek-v4-flash-0731 next to the published list price — 75.4% off.
| Dimension | SayGM price | List price |
|---|---|---|
| Input | $0.107888per Mtok | $0.44 |
| Output | $0.323664per Mtok | $1.32 |
| Cache read | $0.0034328per Mtok | $0.014 |
Recent effective price
What buyers have actually paid on this model recently, across every provider and cache hits.
Input
$0.11
$0.44Cached input
$0.003
$0.014Output
$0.32
$1.32How the effective price is calculated
Requests are load balanced across every provider serving this model, each offering its own rate, so what you pay is a blend rather than a single number. These are the blended rates actually paid — priced at what a provider offered, capped at list.
Measured over 4 windows: 668 requests and 2,424,191 input-side tokens. Most recent window closed 2026-08-26 14:17 UTC.
Who's serving this model
Every provider currently serving this model, ranked by discount.
| Provider | Discount | In | Out |
|---|---|---|---|
| Provider 1 | 75.4% off | $0.11 | $0.32 |
| Provider 2 | 75.4% off | $0.11 | $0.32 |
Performance
Measured on the requests SayGM routed to this model.
- Throughput
- 82.6 tok/sover 314 requests
- Time to first token
- 16.2 sover 312 requests
- Request success rate
- 100.0% over 129 requests
Benchmarks
Fixed-seed suites SayGM runs against this model.
Frequently asked questions
How much does deepseek-v4-flash-0731 cost on SayGM?
The best available rate for deepseek-v4-flash-0731 on SayGM right now is $0.11 per million input tokens and $0.32 per million output tokens.
How much cheaper is SayGM than list price?
SayGM's best available rate for deepseek-v4-flash-0731 is 75.4% off list price.
Is deepseek-v4-flash-0731 OpenAI-compatible on SayGM?
Yes. deepseek-v4-flash-0731 is served on SayGM's OpenAI-compatible chat/completions surface, so an unmodified OpenAI SDK pointed at SayGM's base URL works with it.