DeepSeek V4 Flash 0731
Azure AI Foundry chat Deprecates in 29d (Dec 3, 2026)model fallback routing to swap models without code changes.
DeepSeek V4 Flash 0731 is an Azure AI Foundry chat model.It supports a 1,000,000-token context windowwith up to 384,000 output tokens.Input is priced at $0.440/M tokens and output at $1.32/M tokens. Capabilities include function calling, reasoning, prompt caching. Route DeepSeek V4 Flash 0731 via Future AGI's Agent Command Center for unified observability, caching, and 15 routing strategies including cost-optimized fallback.
Estimate DeepSeek V4 Flash 0731 spend
Pick a workload, fine-tune the sliders, and see the monthly bill.
Estimate uses $0.4400/M input · $1.32/M output. Provider pricing changes. Production costs vary with retries, streaming overhead, and tool-call rounds.
Want this for free? Cache + route via Agent Command Center — first 100K requests and 100K cache hits free every month.
Pricing
Per-token rates, expressed in USD per 1M tokens. Verified Oct 22, 2026.
| Input | $0.440/M | |
| Output | $1.32/M | |
| Blended (3:1 in:out) | $0.660/M Cross-model comparable price | |
| Cached input | $0.0140/M |
Context & limits
- Context window
- 1,000,000 tokens
- Max input
- 1,000,000 tokens
- Max output
- 384,000 tokens
- Modalities
- text
Capabilities
- Function calling ✓ supported
- Parallel tool calls — not advertised
- Vision input — not advertised
- Audio input — not advertised
- Audio output — not advertised
- PDF input — not advertised
- Streaming ✓ supported
- Structured output — not advertised
- Prompt caching ✓ supported
- Reasoning ✓ supported
Strengths & caveats — when to pick DeepSeek V4 Flash 0731
Data-driven from DeepSeek V4 Flash 0731's percentile within chat peers.
Where it's strong
- +long-context tasks — context window in the top 11% of peers
- +long-form generation — 384,000-token max output, top-4% of peers
Watch out for
- !strict structured output — no JSON-schema enforcement, expect retry loops
- !scheduled deprecation on Dec 3, 2026 (29 days)
Benchmarks pending
We haven't logged public benchmark scores for DeepSeek V4 Flash 0731 yet. Have one to contribute? Submit a source — citations help us prioritise.
Call DeepSeek V4 Flash 0731 via Agent Command Center
One OpenAI-compatible endpoint. Routing, fallback, semantic caching, guardrails, and cost tracking come along for the ride. First 100K requests + 100K cache hits free every month.
agentcc / @agentcc/client). Per-call metadata — provider, cost, latency, cache hit, request id — is returned on x-agentcc-* response headers, so any HTTP client can read it.# DeepSeek V4 Flash 0731 via the Agent Command Center Python SDK
# pip install agentcc
import os
from agentcc import AgentCC
client = AgentCC(
api_key=os.environ["AGENTCC_API_KEY"], # from app.futureagi.com → Settings → API Keys
base_url="https://gateway.futureagi.com/v1",
)
resp = client.chat.completions.create(
model="azure-ai-foundry/deepseek-v4-flash-0731",
messages=[{"role": "user", "content": "Hello, DeepSeek V4 Flash 0731!"}],
)
print(resp.choices[0].message.content)
print(f"Tokens: {resp.usage.total_tokens}")
# Per-call gateway metadata is returned on x-agentcc-* response headers.
# When you need it programmatically, use .with_raw_response to get them:
raw = client.chat.completions.with_raw_response.create(
model="azure-ai-foundry/deepseek-v4-flash-0731",
messages=[{"role": "user", "content": "Same call, but I want the headers."}],
)
print("Provider:", raw.headers.get("x-agentcc-provider"))
print("Latency:", raw.headers.get("x-agentcc-latency-ms"), "ms")
print("Cost: ", raw.headers.get("x-agentcc-cost"), "USD")
print("Cache: ", raw.headers.get("x-agentcc-cache"))AGENTCC_API_KEY with a key fromapp.futureagi.com.Gateway docs ↗Same model on other providers
deepseek-v4-flash-0731 is also available via 2 other routes. Pricing, regions, and capabilities can differ — compare before routing production traffic.
| Provider | Input / 1M | Output / 1M | Verified |
|---|---|---|---|
| Alibaba DashScope | $0.200/M | $0.400/M | Oct 22, 2026 |
| Fireworks AI | $0.220/M | $0.660/M | Oct 22, 2026 |
Explore similar models
DeepSeek V4 Flash 0731 doesn't have a public Arena ELO score yet, so we group by provider only — quality-tier comparisons need a benchmark. Side-by-side links appear where a comparison page exists; otherwise, open the model profile.
- GPT-5.4Azure AI Foundry · $2.50/M in · $15.00/M out · 922,000 ctxCompare side-by-side →
- GPT-5.5 (2026-04-23)Azure AI Foundry · $5.00/M in · $30.00/M out · 922,000 ctxCompare side-by-side →
- Claude Opus 4.7Azure AI Foundry · $5.00/M in · $25.00/M out · 1,000,000 ctxView model →
- Claude Opus 4.6Azure AI Foundry · $5.00/M in · $25.00/M out · 1,000,000 ctxView model →
FAQ
How much does DeepSeek V4 Flash 0731 cost?
Input is priced at $0.440 per 1M tokens and output at $1.32 per 1M tokens (Azure AI Foundry, last verified Oct 22, 2026).
What is the context window of DeepSeek V4 Flash 0731?
DeepSeek V4 Flash 0731 supports a 1,000,000-token context window with up to 384,000 output tokens.
Does DeepSeek V4 Flash 0731 support function calling?
Yes — DeepSeek V4 Flash 0731 supports function (tool) calling.
Is DeepSeek V4 Flash 0731 good for production?
DeepSeek V4 Flash 0731 is well-suited for long-context tasks — context window in the top 11% of peers and long-form generation — 384,000-token max output, top-4% of peers. Consider alternatives if you need strict structured output — no JSON-schema enforcement, expect retry loops.
How can I route to DeepSeek V4 Flash 0731 with fallback?
Use Agent Command Center: a single OpenAI-compatible endpoint that supports cost-optimized routing, latency-aware retries, model fallback, and shadow traffic. Configure once, swap models without app changes.
Useful links for DeepSeek V4 Flash 0731
Official sources, independent benchmarks, and pricing aggregators — no random search-engine guesses.
Third-party evals — verify the marketing.
Cross-check our number against the rest of the ecosystem.