TokenSpend
All models

OpenAI (open weights)

gpt-oss 120B

open weights

Model id

openai/gpt-oss-120b
Try in playgroundGet API key
Input
$0.037
per M tokens
Output
$0.17
per M tokens
Cache read
—
not offered on this model
Context
131K
tokens

Registry contract

Capabilities

Protocols
3
Chat · Responses · Messages · streaming
Tools
None
Not supported
JSON Schema
None
Not supported
Vision
No
Not supported
Reasoning
1
Messages
Output limit
Provider
No narrower TokenSpend limit

canonical openai/gpt-oss-120b · revision openai/gpt-oss-120b · aliases gpt-oss-120b, openai.gpt-oss-120b-1:0

Provider list price

Pricing

Input$0.037 / M tokens
Output$0.17 / M tokens
RoutingFree

Provider list price. BYOK bills your provider; managed credits draw down at these rates. No markup or request fee. Every request is metered per engineer and joined to shipped work.

Registry 2026-09-17.3 · effective 9/17/2026 · Private rate card. Source withheld.

First request

Run it

Python · TokenSpend SDK

from tokenspend import TokenSpend

client = TokenSpend()
resp = client.chat.completions.create(
    model="openai/gpt-oss-120b",
    messages=[{"role": "user", "content": "hello"}],
)

TypeScript · TokenSpend SDK

import { TokenSpend } from "@tokenspend/sdk";

const client = new TokenSpend();
const resp = await client.chat.completions.create({
  model: "openai/gpt-oss-120b",
  messages: [{ role: "user", content: "hello" }]
});

curl

curl https://api.tokenspend.dev/v1/chat/completions \
  -H "content-type: application/json" \
  -H "Authorization: Bearer $TOKENSPEND_API_KEY" \
  -d '{"model":"openai/gpt-oss-120b","messages":[{"role":"user","content":"hello"}]}'

Claude Code integration

export ANTHROPIC_BASE_URL=https://api.tokenspend.dev
export ANTHROPIC_API_KEY=$TOKENSPEND_API_KEY
export ANTHROPIC_MODEL=openai/gpt-oss-120b

One request shape reaches every model. Claude Code connects as an integration with two environment variables. Prompts are not stored unless you enable request logging.