DeepSeek V3
Azure AI Foundry chatDeepSeek V3 is an Azure AI Foundry chat model.It supports a 128,000-token context windowwith up to 8,192 output tokens.Input is priced at $1.14/M tokens and output at $4.56/M tokens. Route DeepSeek V3 via Future AGI's Agent Command Center for unified observability, caching, and 15 routing strategies including cost-optimized fallback.
Estimate DeepSeek V3 spend
Pick a workload, fine-tune the sliders, and see the monthly bill.
Estimate uses $1.14/M input · $4.56/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 May 12, 2026.
| Input | $1.14/M | |
| Output | $4.56/M |
Limits
- Context window
- 128,000 tokens
- Max input
- 128,000 tokens
- Max output
- 8,192 tokens
- Modalities
- text
Capabilities
- Function calling — not advertised
- 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 — not advertised
- Reasoning — not advertised
Where it's strong
Watch out for
- !agentic workflows — no advertised function-calling; use a tool-capable model and route via Agent Command Center for fallback
- !strict structured output — no JSON-schema enforcement, expect retry loops
Benchmark scores
Reported public benchmark numbers. Each row links to the source. Faded bar shows 6-peer average for context.
Call DeepSeek V3 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 V3 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-v3",
messages=[{"role": "user", "content": "Hello, DeepSeek V3!"}],
)
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-v3",
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 ↗Advanced: fallback + cache config (YAML) ▸
strategy: cost-optimized
targets:
- model: deepseek-v3
provider: azure-ai-foundry
weight: 80
fallbacks:
- model: deepseek-r1
provider: deepseek
- model: gemini-2-5-flash
provider: vertex-ai
guardrails: [pii, prompt-injection, secrets]
cache: { exact: true, semantic: true }Same model on other providers
deepseek-v3 is also available via 1 other route. Pricing, regions, and capabilities can differ — compare before routing production traffic.
| Provider | Input / 1M | Output / 1M | Verified |
|---|---|---|---|
| DeepSeek | $0.270/M | $1.10/M | May 12, 2026 |
Compare with similar models
Grouped by Chatbot Arena tier (DeepSeek V3 sits at 1310 ELO).
- Claude Opus 4.7Azure AI Foundry · $5.00/M in · $25.00/M out · 200,000 ctx
- Claude Opus 4.6Azure AI Foundry · $5.00/M in · $25.00/M out · 200,000 ctx
- Claude Sonnet 4.6Azure AI Foundry · $3.00/M in · $15.00/M out · 1,000,000 ctx
- Claude Opus 4.5Azure AI Foundry · $5.00/M in · $25.00/M out · 200,000 ctx
≥30 ELO higher
- Claude Opus 4.6Azure AI Foundry · $5.00/M in · $25.00/M out · 200,000 ctx
- Claude Opus 4.6 (2026-02-05)Anthropic · $5.00/M in · $25.00/M out · 1,000,000 ctx
- Gemini 3.1 Pro previewGoogle Vertex AI · $2.00/M in · $12.00/M out · 1,048,576 ctx
- Claude Opus 4.7Azure AI Foundry · $5.00/M in · $25.00/M out · 200,000 ctx
25–100 ELO lower, ≤50% of price
FAQ
How much does DeepSeek V3 cost?
Input is priced at $1.14 per 1M tokens and output at $4.56 per 1M tokens (Azure AI Foundry, last verified May 12, 2026).
What is the context window of DeepSeek V3?
DeepSeek V3 supports a 128,000-token context window with up to 8,192 output tokens.
Does DeepSeek V3 support function calling?
DeepSeek V3 does not currently advertise function-calling support. For agentic workloads, prefer a tool-calling-capable model and route via Agent Command Center for fallback.
Is DeepSeek V3 good for production?
DeepSeek V3 is best evaluated against your own production traces. Pipe traffic through Agent Command Center to compare it head-to-head against alternatives in shadow mode.
How can I route to DeepSeek V3 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 V3
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.