Code Bison32k

Google Vertex AI completion

Code Bison32k is a Google Vertex AI text completion model.It supports a 6,144-token context windowwith up to 1,024 output tokens.Input is priced at $0.125/M tokens and output at $0.125/M tokens. Route Code Bison32k via Future AGI's Agent Command Center for unified observability, caching, and 15 routing strategies including cost-optimized fallback.

Pricing source: litellm Last verified: May 7, 2026 View source ↗
Cost calculator

Estimate Code Bison32k spend

Pick a workload, fine-tune the sliders, and see the monthly bill.

~3K in / ~400 out · 5K req/day
3,000
08,000
400
01,024
5,000
01,000,000
Per request
$0.000425
in $0.000375 · out $0.000050
Per day
$2.13
5,000 requests
Per month
$64.68
152,188 requests

Estimate uses $0.1250/M input · $0.1250/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 7, 2026.

Input $0.125/M
Output $0.125/M

Limits

Context window
6,144 tokens
Max input
6,144 tokens
Max output
1,024 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

  • !small context (under 16K tokens)

Benchmarks pending

We haven't logged public benchmark scores for Code Bison32k yet. Have one to contribute? Submit a source — citations help us prioritise.

Try it

Call Code Bison32k 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.

SDK
Native Future AGI client (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.
# Code Bison32k 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="vertex-ai/code-bison32k",
    messages=[{"role": "user", "content": "Hello, Code Bison32k!"}],
)

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="vertex-ai/code-bison32k",
    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"))
Set AGENTCC_API_KEY with a key fromapp.futureagi.com.Gateway docs ↗

Compare with similar models

Code Bison32k doesn't have a public Arena ELO score yet, so we group by provider only — quality-tier comparisons need a benchmark.

FAQ

How much does Code Bison32k cost?

Input is priced at $0.125 per 1M tokens and output at $0.125 per 1M tokens (Google Vertex AI, last verified May 7, 2026).

What is the context window of Code Bison32k?

Code Bison32k supports a 6,144-token context window with up to 1,024 output tokens.

Does Code Bison32k support function calling?

Code Bison32k 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 Code Bison32k good for production?

Code Bison32k 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 Code Bison32k 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 Code Bison32k

Official sources, independent benchmarks, and pricing aggregators — no random search-engine guesses.