Imagen 3.0 Generate 002
Google AI image generation Deprecated 184d agomodel fallback routing to swap models without code changes.
Imagen 3.0 Generate 002 is a Google AI image generation model. Route Imagen 3.0 Generate 002 via Future AGI's Agent Command Center for unified observability, caching, and 15 routing strategies including cost-optimized fallback.
Estimate Imagen 3.0 Generate 002 spend
Pick a workload, fine-tune the sliders, and see the monthly bill.
Estimate uses $0.000000/M input · $0.000000/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 | — | |
| Output | — | |
| Per image | $0.0400 |
Limits
- Context window
- —
- Max input
- —
- Max output
- —
- Modalities
- image, 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
- !already deprecated — provider stopped accepting new traffic 184 days ago
Benchmarks pending
We haven't logged public benchmark scores for Imagen 3.0 Generate 002 yet. Have one to contribute? Submit a source — citations help us prioritise.
Call Imagen 3.0 Generate 002 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.# Imagen 3.0 Generate 002 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="google/imagen-3-0-generate-002",
messages=[{"role": "user", "content": "Hello, Imagen 3.0 Generate 002!"}],
)
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="google/imagen-3-0-generate-002",
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
imagen-3-0-generate-002 is also available via 1 other route. Pricing, regions, and capabilities can differ — compare before routing production traffic.
| Provider | Input / 1M | Output / 1M | Verified |
|---|---|---|---|
| Google Vertex AI | — | — | May 12, 2026 |
Compare with similar models
Imagen 3.0 Generate 002 doesn't have a public Arena ELO score yet, so we group by provider only — quality-tier comparisons need a benchmark.
- Gemini 2.5 Flash ImageGoogle AI · $0.300/M in · $2.50/M out · 32,768 ctx
- Deep Research Pro preview 12.2025Google AI · $2.00/M in · $12.00/M out · 65,536 ctx
- Gemini 3.1 Flash Image previewGoogle AI · $0.250/M in · $1.50/M out · 65,536 ctx
- Gemini 3 Pro Image previewGoogle AI · $2.00/M in · $12.00/M out · 65,536 ctx
FAQ
How much does Imagen 3.0 Generate 002 cost?
Input is priced at $0.000000 per 1M tokens and output at $0.000000 per 1M tokens (Google AI, last verified May 12, 2026).
What is the context window of Imagen 3.0 Generate 002?
Context window for Imagen 3.0 Generate 002 is not currently public.
Does Imagen 3.0 Generate 002 support function calling?
Imagen 3.0 Generate 002 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 Imagen 3.0 Generate 002 good for production?
Imagen 3.0 Generate 002 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 Imagen 3.0 Generate 002 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 Imagen 3.0 Generate 002
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.