Speka
Start free
All models
codeOpenAI

GPT-OSS 20B

The small GPT-OSS tier — quick code completion, refactors and shell/tool calls at a fraction of the price.

openai/gpt-oss-20b
Running· verified 10 min ago · 365ms

What is GPT-OSS 20B?

GPT-OSS 20B is OpenAI's code model. The small GPT-OSS tier — quick code completion, refactors and shell/tool calls at a fraction of the price. It runs on Speka's OpenAI-compatible /v1/chat/completions endpoint at $0.07 / 1M input and $0.30 / 1M output tokens, using the model ID openai/gpt-oss-20b.

Test it live

Live playgroundGPT-OSS 20Bin-browser demo

Test GPT-OSS 20B live

Send a message and watch the model respond. Multi-turn — it remembers the conversation.

How to call GPT-OSS 20B via the API

Speka exposes GPT-OSS 20B on an OpenAI-compatible /v1/chat/completions endpoint. Point any OpenAI SDK at https://speka.me/v1, set model to openai/gpt-oss-20b, and your existing code runs unchanged.

quickstart.py
from openai import OpenAI

client = OpenAI(
    base_url="https://speka.me/v1",
    api_key="sk-speka-live-...",  # your Speka key
)

resp = client.chat.completions.create(
    model="openai/gpt-oss-20b",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)
FAQ

Frequently asked questions

GPT-OSS 20B is OpenAI's code model. The small GPT-OSS tier — quick code completion, refactors and shell/tool calls at a fraction of the price. It is available on Speka's OpenAI-compatible API using the model ID openai/gpt-oss-20b.
On Speka, GPT-OSS 20B is priced at $0.07 / 1M input and $0.30 / 1M output tokens. Pricing is per-token with no subscription or seat fee — usage is billed against your plan's monthly allowance, then at the same rate with no overage penalty. Rates are current as of June 2026; check the pricing page for updates.
Speka exposes GPT-OSS 20B on an OpenAI-compatible /v1/chat/completions endpoint. Set base_url to https://speka.me/v1, supply your Speka key, and set model to "openai/gpt-oss-20b" in any OpenAI SDK — no other code changes are required.
GPT-OSS 20B supports a 128,000-token context window — roughly 96,000 words of input, suitable for long documents, multi-turn agents, and large-context tasks.
Yes. GPT-OSS 20B is served through Speka's OpenAI-compatible endpoint, so any application built on the OpenAI Python or Node.js SDK, LangChain, or LlamaIndex can call it by changing only the base URL and model ID.

More code models

O

GPT-OSS 120B

OpenAI
code

Open-weight 120B model with strong code generation, refactoring and tool-use. Built for coding agents and automation.

openai/gpt-oss-120b
Input / 1M
$0.15
Output / 1M
$0.60
Open model
P

Laguna XS 2.1

Poolside
code

Poolside's compact software-engineering model, tuned for repository-aware code completion and edits with very low latency.

poolside/laguna-xs-2.1
Input / 1M
$0.20
Output / 1M
$0.60
Open model