Model

placeholder-medium

placeholder-medium is its own market on OpenFill. A request names placeholder-medium, sets a max price, and pays the level the market is clearing at when it runs.

Open market

Datasheet

Field	Value
Model id	placeholder-medium
Also answers to	No other id
Context length	262,144 tokens
Max output	128,000 tokens
Pricing ratio	1:8:16

The ratio weights a cache-hit, a cache-miss and an output token in the price. max_tokens above the max output is clamped down to it.

The market now

The clearing level, the price of each token kind at that level, and the quote a locked request bids.

Clearing level · placeholder-medium · polling

$0.0722Basis+$0.0231 (+32%)Price lock$0.0953New price in 1s

90% of requests priced above the lock started in time, over the last 10 minutes.

Only requests priced above the lock are counted. At or below it a request bids its own ceiling, so the locked price never sets what it pays.

Set max_price above the lock if you want those odds. Under it, the lock has no bearing on whether the request starts.

Per 1M tokens: $0.0357 cache-hit · $0.2859 cache-miss · $0.5717 output

A price_lock request pays at most the locked price, and cancels with no charge if it has not started within 10 seconds.

The basis is the margin over the level, and a ceiling rather than a charge. See how the lock works.

Uptime, last 24 hours

Each check is a chat completion through the public API, run the way the models board describes.

Uptime

100%

Checks

289

Failures

Latency

259ms

Queue wait

958ms

289 of 289 checks passed in the last 24h.

24h agoNow

All checks passedFailed, drawn in proportionNot available

The first call

Set OPENFILL_API_KEY to a key from API keys before running an example. A key starts with of_live_ and is shown once.

Read docs

import osfrom openai import OpenAI client = OpenAI(    base_url="https://api.openfill.ai/v1",    api_key=os.environ["OPENFILL_API_KEY"],) r = client.chat.completions.create(    model="placeholder-medium",    messages=[        {"role": "user", "content": "hi"}    ],    extra_body={"max_price": 0.10},the max price)print(r.choices[0].message.content)print(r.usage)

import OpenAI from "openai"; const client = new OpenAI({  baseURL: "https://api.openfill.ai/v1",  apiKey: process.env.OPENFILL_API_KEY,}); const r = await client.chat.completions.create(  {    model: "placeholder-medium",    messages: [{ role: "user", content: "hi" }],  },  { headers: { "X-Max-Price": "0.10" } },the max price);console.log(r.choices[0].message.content);console.log(r.usage);

curl https://api.openfill.ai/v1/chat/completions \  -H "Authorization: Bearer $OPENFILL_API_KEY" \  -H "Content-Type: application/json" \  -d '{    "model": "placeholder-medium",    "messages": [      {"role": "user", "content": "hi"}    ],    "max_price": 0.10the max price  }'

# A key from API keys, shown once when madeexport OPENFILL_API_KEY="of_live_..." # Any tool that reads the OpenAI variablesexport OPENAI_BASE_URL="https://api.openfill.ai/v1"the max priceexport OPENAI_API_KEY="$OPENFILL_API_KEY" # The max price comes from the key or the# account default, set on Bidding.curl -s "$OPENAI_BASE_URL/models" \  -H "Authorization: Bearer $OPENAI_API_KEY"

# The base URL without /v1; Claude Code appends /v1/messagesexport ANTHROPIC_BASE_URL="https://api.openfill.ai"export ANTHROPIC_AUTH_TOKEN="$OPENFILL_API_KEY"export ANTHROPIC_API_KEY="" # Every model slot by hand: discovery keeps only ids that name Claudeexport ANTHROPIC_MODEL="placeholder-medium"export ANTHROPIC_DEFAULT_SONNET_MODEL="placeholder-medium"export ANTHROPIC_DEFAULT_HAIKU_MODEL="placeholder-medium"export CLAUDE_CODE_SUBAGENT_MODEL="placeholder-medium" # The max price and the wait, merged into every request bodyexport CLAUDE_CODE_EXTRA_BODY='{"max_price": 0.10, "max_wait": 600}'the max priceexport CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS=1claude

# ~/.codex/config.tomlmodel_provider = "openfill"model = "placeholder-medium"model_context_window = <context_length from GET /v1/models>web_search = "disabled"show_raw_agent_reasoning = true [model_providers.openfill]name = "OpenFill"base_url = "https://api.openfill.ai/v1"env_key = "OPENFILL_API_KEY"wire_api = "responses"http_headers = { "X-Max-Price" = "0.10" }the max price

import { createOpenAICompatible } from "@ai-sdk/openai-compatible";import { generateText } from "ai"; const openfill = createOpenAICompatible({  name: "openfill",  baseURL: "https://api.openfill.ai/v1",  apiKey: process.env.OPENFILL_API_KEY,  headers: { "X-Max-Price": "0.10" },the max price}); const { text } = await generateText({  model: openfill.chatModel("placeholder-medium"),  prompt: "hi",});console.log(text);

import osfrom langchain_openai import ChatOpenAI llm = ChatOpenAI(    model="placeholder-medium",    base_url="https://api.openfill.ai/v1",    api_key=os.environ["OPENFILL_API_KEY"],    default_headers={"X-Max-Price": "0.10"},the max price)print(llm.invoke("hi").content)

import osfrom litellm import completion r = completion(    model="openai/placeholder-medium",    api_base="https://api.openfill.ai/v1",    api_key=os.environ["OPENFILL_API_KEY"],    messages=[        {"role": "user", "content": "hi"}    ],    extra_headers={"X-Max-Price": "0.10"},the max price)print(r.choices[0].message.content)

import osfrom openai import AsyncOpenAIfrom agents import (    Agent, Runner,    set_default_openai_api,    set_default_openai_client,    set_tracing_disabled,) set_default_openai_client(AsyncOpenAI(    base_url="https://api.openfill.ai/v1",    api_key=os.environ["OPENFILL_API_KEY"],    default_headers={"X-Max-Price": "0.10"},the max price))set_default_openai_api("chat_completions")set_tracing_disabled(True) agent = Agent(name="assistant", model="placeholder-medium")print(Runner.run_sync(agent, "hi").final_output)

// opencode.json{  "$schema": "https://opencode.ai/config.json",  "provider": {    "openfill": {      "npm": "@ai-sdk/openai-compatible",      "name": "OpenFill",      "options": {        "baseURL": "https://api.openfill.ai/v1",        "apiKey": "{env:OPENFILL_API_KEY}",        "headers": { "X-Max-Price": "0.10" }the max price      },      "models": {        "placeholder-medium": { "name": "placeholder-medium" }      }    }  }}

# Cline, Roo Code and Kilo Code# Settings > API Provider: OpenAI Compatible Base URL   https://api.openfill.ai/v1the max priceAPI Key    (your OPENFILL_API_KEY)Model ID   placeholder-medium # These tools send no max price of their# own. Set one on the key, on Bidding.

Questions

What does placeholder-medium cost on OpenFill?

The clearing level when the request runs, up to the max price you set, shared across the three token kinds by the ratio 1:8:16.

How pricing works

What happens while the level is above my max price?

The request waits in the book while capacity is short and runs when there is room, for up to max_wait (10 seconds to 30 days). Past that it expires with 408 and no charge.

Waiting and timeouts

How do I know the price before I send?

With price_lock: true the request bids the published quote, or your max price if lower, and starts within 10 seconds or cancels with 429 and no charge.

Price lock

What are the limits?

1,200 inference requests a minute per key, 2,000 queued orders per account, and a request body of up to 8 MB. Every limit is on GET /v1/limits.

Limits

What is stored?

Storage is off by default: a prompt and its response exist only while the request runs. With it on, results are kept up to 30 days; store: false keeps less.

Data storage