GPT Oss 20B

Replicate chat

GPT Oss 20B is a Replicate chat model.Input is priced at $0.0900/M tokens and output at $0.360/M tokens. Capabilities include function calling. Route GPT Oss 20B 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 12, 2026 View source ↗
Cost calculator

Estimate GPT Oss 20B spend

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

~3K in / ~400 out · 5K req/day
3,000
0200,000
400
016,000
5,000
01,000,000
Per request
$0.000414
in $0.000270 · out $0.000144
Per day
$2.07
5,000 requests
Per month
$63.01
152,188 requests

Estimate uses $0.0900/M input · $0.3600/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 $0.0900/M
Output $0.360/M

Limits

Context window
Max input
Max output
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 — not advertised
  • Reasoning — not advertised

Where it's strong

  • +agentic workflows that depend on reliable tool calls

Watch out for

  • !strict structured output — no JSON-schema enforcement, expect retry loops

Benchmarks pending

We haven't logged public benchmark scores for GPT Oss 20B yet. Have one to contribute? Submit a source — citations help us prioritise.

Try it

Call GPT Oss 20B 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.
# GPT Oss 20B 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="replicate/gpt-oss-20b",
    messages=[{"role": "user", "content": "Hello, GPT Oss 20B!"}],
)

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="replicate/gpt-oss-20b",
    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 ↗

Same model on other providers

gpt-oss-20b is also available via 1 other route. Pricing, regions, and capabilities can differ — compare before routing production traffic.

ProviderInput / 1MOutput / 1MVerified
OVHcloud AI$0.0400/M$0.150/MMay 12, 2026

Compare with similar models

GPT Oss 20B 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 GPT Oss 20B cost?

Input is priced at $0.0900 per 1M tokens and output at $0.360 per 1M tokens (Replicate, last verified May 12, 2026).

What is the context window of GPT Oss 20B?

Context window for GPT Oss 20B is not currently public.

Does GPT Oss 20B support function calling?

Yes — GPT Oss 20B supports function (tool) calling.

Is GPT Oss 20B good for production?

GPT Oss 20B is well-suited for agentic workflows that depend on reliable tool calls. Consider alternatives if you need strict structured output — no JSON-schema enforcement, expect retry loops.

How can I route to GPT Oss 20B 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 GPT Oss 20B

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