deepseek-v4-flash-0731
Fireworks AI/🇺🇸 US/chat
DeepSeek V4 Flash 0731 is the official release of DeepSeek V4 Flash, superseding the preview version, with substantially enhanced agentic capabilities. A 304B parameter open-source Mixture-of-Experts model with speculative decoding, 1M token context, optimized for fast, cost-efficient inference with strong reasoning, coding, and function calling performance.MoreLess
Which id to call
fireworks/deepseek-v4-flash-0731This exact deployment on Fireworks AI, with no routing and no failover. Send it as the model field.
Input /1M
$0.22
$0.0070 cached
Output /1M
$0.66
3.0x input
Context
1M
131K output
Paid /1M
$0.06
measured, cache included
Capabilities 4/8
Provider rates
What deepseek-v4-flash-0731 costs
Provider prices per 1M tokens, updated September 17, 2026.moreless
These are the upstream provider rates. Pay as you go adds 5%, or 0% if you bring your own keys, and there is no per-request fee. Prompt caching and routing change what you pay against these rates, not the rates themselves.
Input /1M
$0.22
Output /1M
$0.66
Cache write /1M
-
Cache read /1M
$0.0070
What a workload costs
- 100K input + 10K output
- $0.0286
- 1M input + 100K output
- $0.29
- 10M input + 1M output
- $2.86
At the rates above, before caching. A cache read costs $0.0070 per 1M, so repeated context lands under these figures.
model=
Which id to call
One base url, https://router.requesty.ai/v1, and one key for every id here.
fireworks/deepseek-v4-flash-0731This exact deployment on Fireworks AI, with no routing and no failover. Send it as the model field.
OpenAI compatible
Call it in three lines
Change the base url, use your Requesty key, set the model to any id on the left. Existing OpenAI SDK code needs no other edit.
123456789101112131415from openai import OpenAI client = OpenAI( api_key="YOUR_REQUESTY_API_KEY", base_url="https://router.requesty.ai/v1", ) response = client.chat.completions.create( model="fireworks/deepseek-v4-flash-0731", messages=[ {"role": "user", "content": "Explain quantum computing in one paragraph."}, ], ) print(response.choices[0].message.content)
Live from production
Fireworks AI on deepseek-v4-flash-0731, measured
What this provider was measured doing on deepseek-v4-flash-0731 across Requesty traffic.moreless
Whole-window figures, because that is the grain published per provider. They cover Fireworks AI serving this model in every region it serves it from, so a region-pinned deployment shares them with its siblings. A figure is absent where no qualifying sample exists.
First token
994ms
median
p95 wait
7.98s
slowest 5%
Output speed
78/s
median tokens
Paid /1M
$0.06
blended, cache included
Cache hit
90.3%
of input tokens
Compare these against the other 8 providers serving deepseek-v4-flash-0731.
Reference
Specs and data terms
What the catalog reports for this deployment, and what the provider does with the traffic.
Released 2026-07-31
Benchmark scores
Benchmarks measure the model, not this endpoint, so they are the same wherever these weights are served.
Artificial Analysis Coding Index: a composite of coding evaluations including LiveCodeBench, SciCode and Terminal-Bench.
Graduate-level physics, chemistry & biology questions designed to resist Googling.
Artificial Analysis Intelligence Index: a composite of multiple evaluations measuring overall model capability.
Scores from official model cards, Artificial Analysis and public leaderboards. They measure specific skills and do not capture every aspect of model quality, so test on your own workload.
Same provider
More from Fireworks AI
Newest first, on the same provider and the same key.
Reference
deepseek-v4-flash-0731 questions
How much does deepseek-v4-flash-0731 cost?
deepseek-v4-flash-0731 is priced at $0.22 per million input tokens and $0.66 per million output tokens when accessed via Requesty. Prompt caching is supported, which can cut effective input cost by up to 90% on repeated context. Those are the upstream provider rates: pay as you go adds 5% on top, or 0% if you bring your own provider keys.
What is the context window of deepseek-v4-flash-0731?
deepseek-v4-flash-0731 has a context window of 1M tokens, with a maximum output of 131K tokens per response. That's roughly 1,333 words of input you can fit in a single prompt.
How does deepseek-v4-flash-0731 perform on benchmarks?
deepseek-v4-flash-0731 scores 90.8% on GPQA Diamond, 69.1% on Coding Index, 50.3% on SciCode. See the full benchmark chart above for results across MMLU Pro, GPQA Diamond, SWE-Bench Verified, HumanEval, MATH, AIME, MMMU, and LiveBench.
What can deepseek-v4-flash-0731 do?
deepseek-v4-flash-0731 supports tool calling, extended reasoning, prompt caching, structured outputs (JSON schema). You can call it through any OpenAI-compatible client by pointing base_url to Requesty.
How do I use deepseek-v4-flash-0731 with the OpenAI SDK?
Install the OpenAI SDK, set base_url to "https://router.requesty.ai/v1", set your API key to your Requesty key, and set the model to "fireworks/deepseek-v4-flash-0731". The Quickstart above shows Python, JavaScript and cURL snippets.
Can I run deepseek-v4-flash-0731 through Requesty?
Yes. deepseek-v4-flash-0731 runs through Requesty's OpenAI-compatible API, served from Fireworks AI. You do not host the model yourself: point base_url at Requesty, set the model to "fireworks/deepseek-v4-flash-0731", and requests are routed to the upstream provider with automatic failover. The same key gives you 600+ other models too.
Call deepseek-v4-flash-0731 through one endpoint
One key for this endpoint and 600+ other models. No markup on provider prices, automatic failover, caching built in.