API ya LLM ya bure kwa LangChain
LangChain inaunganishwa na API zinazooana na OpenAI kupitia ChatOpenAI na OpenAIEmbeddings. Unabadilisha base URL na ufunguo. Mwongozo huu unaelekeza madarasa yote mawili kwenye FreeLLMAPI, ambayo inakusanya ngazi 45 za bure za watoa huduma nyuma ya ufunguo mmoja. Msimbo ulio hapa chini unafanya kazi kwa Python na JavaScript na unashughulikia vikomo vya kiwango.
Msimbo, majina ya modeli na lebo za katalogi ya moja kwa moja zinaonyeshwa kwa Kiingereza.
Sanidi lango na vifurushi
Sakinisha FreeLLMAPI kisha ongeza funguo za bure kutoka watoa huduma wawili au zaidi kwenye ukurasa wa Keys wa dashibodi. Nakili ufunguo wa pamoja. Msimbo wako unatumia ufunguo huu pekee. Funguo za watoa huduma zinabaki ndani ya FreeLLMAPI.
Sakinisha FreeLLMAPI na vifurushi vya LangChain
curl -fsSL https://freellmapi.co/install.sh | bash
# Python
pip install -U langchain langchain-openai
# JavaScript
npm install @langchain/openai @langchain/core zodVigezo vya mazingira
export FREELLMAPI_BASE_URL=http://localhost:3001/v1
export FREELLMAPI_API_KEY=<unified-key>Tumia model="auto" ili kipanga njia kichague modeli. Unaweza pia kutumia mkakati wa uelekezaji, kwa mfano auto:fast au auto:smart. Wasifu wenye jina kama auto:coding na model ID isiyobadilika kutoka katalogi pia zinafanya kazi.
Ili kuona modeli ambazo funguo zako zinaweza kuita sasa, omba GET /v1/models?execution_status=ready. Orodha kamili pia ina modeli zisizo na ufunguo. Modeli yenye hali exhausted ina funguo, lakini zote zimefikia kikomo kwa sasa. Hali hiyo inaisha muda wa kupumzika unapomalizika.
Orodhesha modeli zinazoweza kujibu sasa
curl "http://localhost:3001/v1/models?execution_status=ready" \
-H "Authorization: Bearer <unified-key>"Gumzo kwa ChatOpenAI
Kwenye Python, weka base_url na api_key. Thamani ya max_retries inakwenda kwa mteja wa OpenAI, ambaye anajaribu tena makosa 429 na 5xx kwa kusubiri kwa ongezeko la kielelezo.
Python: gumzo na utiririshaji
import os
from langchain_openai import ChatOpenAI
llm = ChatOpenAI(
model="auto",
base_url=os.environ["FREELLMAPI_BASE_URL"],
api_key=os.environ["FREELLMAPI_API_KEY"],
temperature=0.2,
max_retries=3,
timeout=60,
include_response_headers=True,
)
msg = llm.invoke("Explain retrieval-augmented generation in two sentences.")
print(msg.content)
print("Served by:", msg.response_metadata["headers"].get("x-routed-via"))
for chunk in llm.stream("Write a haiku about SQLite."):
print(chunk.content, end="", flush=True)Kwenye JavaScript, weka base URL kwenye configuration.baseURL. Kitu cha configuration kinakwenda kwa mteja rasmi wa OpenAI SDK.
JavaScript: gumzo na utiririshaji
import { ChatOpenAI } from "@langchain/openai";
const llm = new ChatOpenAI({
model: "auto",
apiKey: process.env.FREELLMAPI_API_KEY,
temperature: 0.2,
maxRetries: 3,
configuration: { baseURL: process.env.FREELLMAPI_BASE_URL },
});
const msg = await llm.invoke("Explain retrieval-augmented generation in two sentences.");
console.log(msg.content);
for await (const chunk of await llm.stream("Write a haiku about SQLite.")) {
process.stdout.write(String(chunk.content));
}Kichwa cha x-routed-via kinaonyesha mtoa huduma na modeli waliojibu. Ikiwa kipanga njia kimebadilisha mtoa huduma, x-fallback-trail inaonyesha kila jaribio lililoshindwa na sababu yake.
Zana na mawakala
FreeLLMAPI inapeleka tools za mtindo wa OpenAI kwa kila mtoa huduma na kurudisha tool_calls katika muundo wa OpenAI. Kwa Gemini, inabadilisha ombi kuwa muundo wa Google na kurudi tena. Tumia bind_tools kwa wito mmoja, au create_agent kwa mzunguko unaoendesha zana.
Python: bind_tools na create_agent
from langchain.agents import create_agent
from langchain_core.tools import tool
@tool
def get_weather(city: str) -> str:
"""Return the current weather for a city."""
return f"It is 18 C and cloudy in {city}."
# One call: the model returns the tool call, your code runs it
msg = llm.bind_tools([get_weather]).invoke("What is the weather in Dublin?")
print(msg.tool_calls)
# Agent loop: LangChain runs the tool and sends the result back
agent = create_agent(
model=llm,
tools=[get_weather],
system_prompt="You answer weather questions. Use the tool.",
)
result = agent.invoke({"messages": [{"role": "user", "content": "Weather in Dublin?"}]})
print(result["messages"][-1].content)JavaScript: bindTools
import { tool } from "@langchain/core/tools";
import { z } from "zod";
const getWeather = tool(
async ({ city }) => `It is 18 C and cloudy in ${city}.`,
{
name: "get_weather",
description: "Return the current weather for a city.",
schema: z.object({ city: z.string() }),
},
);
const reply = await llm.bindTools([getWeather]).invoke("What is the weather in Dublin?");
console.log(reply.tool_calls);Baadhi ya modeli za bure pekee zinaunga mkono wito wa zana. Kwa auto, weka modeli zinazoweza kuita zana kwenye mnyororo wako wa akiba, au tengeneza wasifu wa mawakala. Modeli hizi za bure zinaunga mkono zana kwa sasa:
| Modeli | Bure kwenye | Muktadha | Vikomo vya bure (ofa bora) | Zana | Uoni |
|---|---|---|---|---|---|
| GLM 5.3 | UnoRouter | 1M | 1 maombi/dakika 1 req/min per model | Ndiyo | Hapana |
| GLM 5.3 Flash | NVIDIA NIM, UnoRouter | 1M | 40 maombi/dakika 40 RPM | Ndiyo | Ndiyo |
| Gemini 3.8 Flash | Google AI Studio | 1M | Recurring provider quota | Ndiyo | Ndiyo |
| Qwen3.8 Flash Next | AMD Radeon Cloud | 262K | Recurring daily account allowance | Ndiyo | Hapana |
| Qwen3.8 Flash | ElectronHub | 1M | $0.25/week shared recurring credit | Ndiyo | Ndiyo |
| Gemini 3.7 Flash | Google AI Studio | 1M | 10 maombi/dakika 20 maombi/siku 250,000 tokeni/dakika ~3M | Ndiyo | Ndiyo |
| GPT-5.6 Luna | ElectronHub | 1M | $0.25/week shared recurring credit | Ndiyo | Ndiyo |
| Dots3 Note Preview | Kilo Gateway, OpenRouter | 512K | 20 maombi/dakika 50 maombi/siku 50 req/day account-wide (1,000 after a $10 purchase) | Ndiyo | Ndiyo |
| DeepSeek V4 Flash | AMD Radeon Cloud, BazaarLink, ElectronHub | 1M | 10 maombi/dakika 50 maombi/siku Shared rate limit | Ndiyo | Hapana |
| Qwen3.8 27B | ElectronHub, Groq, OVH AI Endpoints | 262K | 30 maombi/dakika 250 maombi/siku 70,000 tokeni/dakika ~6M | Ndiyo | Ndiyo |
Inaonyesha 10 kati ya 109 modeli za bure zinazolingana. Tazama modeli zote.
Data ya moja kwa moja kutoka katalogi ya FreeLLMAPI (toleo 2026.11.19, imekaguliwa 2026-11-19). Vikomo vya bure hubadilika mara kwa mara. Katalogi hukaguliwa kila siku.
Embeddings kwa OpenAIEmbeddings
Kwa chaguo-msingi, OpenAIEmbeddings kwenye Python inagawanya maandishi kwa kitenganishi cha tokeni cha OpenAI na kutuma tokeni. Watoa huduma wengi wengine wanahitaji maandishi ghafi. Weka check_embedding_ctx_length=False ili kutuma maandishi.
Python: embeddings
from langchain_openai import OpenAIEmbeddings
emb = OpenAIEmbeddings(
model="bge-m3", # one embedding family, 1024 dimensions
base_url=os.environ["FREELLMAPI_BASE_URL"],
api_key=os.environ["FREELLMAPI_API_KEY"],
check_embedding_ctx_length=False,
)
vectors = emb.embed_documents(["FreeLLMAPI pools free tiers.", "LangChain builds LLM apps."])
print(len(vectors), len(vectors[0]))JavaScript: embeddings
import { OpenAIEmbeddings } from "@langchain/openai";
const emb = new OpenAIEmbeddings({
model: "bge-m3",
apiKey: process.env.FREELLMAPI_API_KEY,
configuration: { baseURL: process.env.FREELLMAPI_BASE_URL },
});
const vector = await emb.embedQuery("What does FreeLLMAPI do?");
console.log(vector.length);Mbadala wa embedding kwenye FreeLLMAPI haubadilishi modeli kamwe. Unahamia tu kati ya watoa huduma wanaotoa familia ile ile. Hii inaweka vekta zote kwenye hifadhi moja ya vekta zikiwa sambamba. Chagua familia moja kisha ibaki nayo. Modeli za bure za embedding za leo ni:
| Modeli | Mtoa huduma | Vipimo | Ingizo la juu zaidi | Kikomo cha bure |
|---|---|---|---|---|
Gemini Embeddinggemini-embedding-001 | Google AI Studio | 3072 | 2048 | 100 rpm · 1K req/day |
Nemotron Embed VL 1Bnvidia/llama-nemotron-embed-vl-1b-v2 | NVIDIA NIM | 2048 | 8192 | ~40 rpm |
Nemotron 3 Embed 1B (OR free)nvidia/nemotron-3-embed-1b:free | OpenRouter | 2048 | 32768 | 20 rpm · shared free daily cap |
SEA-LION E5 Embedding 600Maisingapore/SEA-LION-E5-Embedding-600M | SEA-LION | 1024 | 8192 | free · 10 rpm |
SEA-LION ModernBERT Embedding 300Maisingapore/SEA-LION-ModernBERT-Embedding-300M | SEA-LION | 1024 | 8192 | free · 10 rpm |
SEA-LION ModernBERT Embedding 600Maisingapore/SEA-LION-ModernBERT-Embedding-600M | SEA-LION | 1024 | 8192 | free · 10 rpm |
BGE-M3@cf/baai/bge-m3 | Cloudflare Workers AI | 1024 | 8192 | 10K neurons/day (shared) |
EmbeddingGemma 300M@cf/google/embeddinggemma-300m | Cloudflare Workers AI | 768 | 2048 | 10K neurons/day (shared) |
Qwen3 Embedding 0.6B@cf/qwen/qwen3-embedding-0.6b | Cloudflare Workers AI | 1024 | 8192 | 10K neurons/day (shared) |
Cohere Embed v4embed-v4.0 | Cohere | 1536 | 128000 | 1K calls/mo (shared w/ chat) |
Gemini Embedding 2gemini-embedding-2 | Google AI Studio | 3072 | 8192 | free-tier rate limited |
Nemotron 3 Embed 1Bnvidia/nemotron-3-embed-1b | NVIDIA NIM | 2048 | 4096 | ~40 rpm |
PLaMo Embedding 1B (CF)@cf/pfnet/plamo-embedding-1b | Cloudflare Workers AI | 2048 | 4096 | 10K neurons/day (shared) |
BGE Small EN v1.5 (CF)@cf/baai/bge-small-en-v1.5 | Cloudflare Workers AI | 384 | 512 | 10K neurons/day (shared) |
BGE Base EN v1.5 (CF)@cf/baai/bge-base-en-v1.5 | Cloudflare Workers AI | 768 | 512 | 10K neurons/day (shared) |
BGE Large EN v1.5 (CF)@cf/baai/bge-large-en-v1.5 | Cloudflare Workers AI | 1024 | 512 | 10K neurons/day (shared) |
Mistral Embedmistral-embed | Mistral | 1024 | 8192 | free mode · monthly cap (shared) |
Codestral Embedcodestral-embed | Mistral | 1536 | 8192 | free mode · monthly cap (shared) |
Llama Text Embed v2 (Pinecone)llama-text-embed-v2 | Pinecone | 1024 | 2048 | 5M tokens/mo per model |
Multilingual E5 Large (Pinecone)multilingual-e5-large | Pinecone | 1024 | 507 | 5M tokens/mo per model |
Nemotron 3 Embed 1B (Speka)nvidia/nemotron-3-embed-1b | Speka | 2048 | 8192 | $1/month shared across Speka models |
OpenAI: Text Embedding 3 Small (ElectronHub)text-embedding-3-small | ElectronHub | 1536 | 8192 | $0.25/week shared free credits |
OpenAI: Text Embedding 3 Large (ElectronHub)text-embedding-3-large | ElectronHub | 3072 | 8192 | $0.25/week shared free credits |
Nemotron 3 Embed 8B (Inferbase)nvidia-nemotron-3-embed-8b | Inferbase | 4096 | 8192 | 5,000 requests/month; 100 requests and $0.50 usage/day shared |
Qwen 3 Embedding 0.6B (Inferbase)qwen3-embedding-0-6b | Inferbase | 1024 | 8192 | 5,000 requests/month; 100 requests and $0.50 usage/day shared |
Qwen 3 Embedding 4B (Inferbase)qwen3-embedding-4b | Inferbase | 2560 | 8192 | 5,000 requests/month; 100 requests and $0.50 usage/day shared |
Qwen 3 Embedding 8B (Inferbase)qwen3-embedding-8b | Inferbase | 4096 | 8192 | 5,000 requests/month; 100 requests and $0.50 usage/day shared |
LFM2.5 Embedding 350M (LLMTR)liquid/lfm-2.5-embedding-350m-free | LLMTR | 1024 | 512 | Ongoing zero-price route; provider terms apply |
BGE-M3 (SEA-LION)BAAI/bge-m3 | SEA-LION | 1024 | 8192 | free · 10 rpm |
Cohere Embed English v3embed-english-v3.0 | Cohere | 1024 | 512 | 1K calls/mo (shared w/ chat) |
Qwen3 Embedding 8B (OVH)Qwen3-Embedding-8B | OVH AI Endpoints | 4096 | 32768 | free · anonymous 2 req/min per IP |
BGE-M3 (OVH)bge-m3 | OVH AI Endpoints | 1024 | 8192 | free · anonymous 2 req/min per IP |
BGE Multilingual Gemma2 (OVH)bge-multilingual-gemma2 | OVH AI Endpoints | 3584 | 8192 | free · anonymous 2 req/min per IP |
Mistral: Codestral Embed (ElectronHub)codestral-embed | ElectronHub | 1536 | 8192 | $0.25/week shared free credits |
Mistral: Mistral Embed (ElectronHub)mistral-embed | ElectronHub | 1024 | 8192 | $0.25/week shared free credits |
Google: Gemini Embedding 2 (ElectronHub)gemini-embedding-2 | ElectronHub | 3072 | 8192 | $0.25/week shared free credits |
Google: Gemini Embedding 001 (ElectronHub)gemini-embedding-001 | ElectronHub | 3072 | 2048 | $0.25/week shared free credits |
OpenAI: Text Embedding Ada 002 (ElectronHub)text-embedding-ada-002 | ElectronHub | 1536 | 8192 | $0.25/week shared free credits |
Cohere Embed English Light v3embed-english-light-v3.0 | Cohere | 384 | 512 | 1K calls/mo (shared w/ chat) |
Cohere Embed Multilingual v3embed-multilingual-v3.0 | Cohere | 1024 | 512 | 1K calls/mo (shared w/ chat) |
Cohere Embed Multilingual Light v3embed-multilingual-light-v3.0 | Cohere | 384 | 512 | 1K calls/mo (shared w/ chat) |
Data ya moja kwa moja kutoka katalogi ya FreeLLMAPI (toleo 2026.11.19, imekaguliwa 2026-11-19). Vikomo vya bure hubadilika mara kwa mara. Katalogi hukaguliwa kila siku.
Matokeo yaliyopangwa, vikao na uchaguzi wa modeli
with_structured_output inarudisha kitu cha Pydantic badala ya maandishi. Kwa chaguo-msingi, LangChain inatumia wito wa kazi kwa hili. Mbinu hiyo inafanya kazi kwenye kila modeli ya bure inayounga mkono zana.
Python: matokeo yaliyopangwa
from pydantic import BaseModel, Field
class Ticket(BaseModel):
category: str = Field(description="billing, bug or other")
urgent: bool
classifier = llm.with_structured_output(Ticket)
ticket = classifier.invoke("The app crashes when I pay. Please fix it today.")
print(ticket.category, ticket.urgent)Usitumie method="json_schema" na auto. Si kila mtoa huduma wa bure anaunga mkono matokeo madhubuti ya JSON schema, na kipanga njia kinaweza kuchagua mtoa huduma tofauti kwa kila ombi.
FreeLLMAPI inaweka mazungumzo kwenye modeli moja kwa dakika 30. Inatambua mazungumzo kutoka kwenye kichwa cha X-Session-Id. Ikiwa hakuna kichwa, inatumia hash ya ujumbe wa kwanza wa mtumiaji. Kwa programu ya gumzo yenye watumiaji wengi, tuma kitambulisho kimoja cha kikao kwa kila mtumiaji:
Python: kikao kimoja kwa kila mtumiaji
def llm_for(user_id: str) -> ChatOpenAI:
return ChatOpenAI(
model="auto",
base_url=os.environ["FREELLMAPI_BASE_URL"],
api_key=os.environ["FREELLMAPI_API_KEY"],
default_headers={"X-Session-Id": f"user-{user_id}"},
max_retries=3,
)Chagua mfuatano wa modeli kwa kila sehemu ya programu yako:
| Kazi kwenye programu yako | Mfuatano wa modeli | Sababu |
|---|---|---|
| Majibu ya gumzo kwa watumiaji | auto | Inafuata mnyororo ulioweka kwenye dashibodi |
| Wakala mwenye zana | auto:<profile> | Wasifu wenye modeli za wito wa zana pekee |
| Uainishaji, uelekezaji, muhtasari mfupi | auto:fast | Inapanga modeli kwa kasi iliyopimwa |
| Hatua ngumu za kufikiri | auto:smart | Inapanga modeli kwa uwezo wa akili |
| Majaribio yanayopaswa kurudiwa kwa matokeo yaleyale | Model ID isiyobadilika | Modeli ile ile kila wakati, lakini inasimama kwenye kikomo cha modeli hiyo |
Ngazi za bure hazina SLA. Muda wa kujibu hubadilika wakati wa siku, na modeli zenye nguvu zaidi hufikia vikomo vyao vya kila siku kwanza. Jaribu minyororo yako kwa modeli ambazo mnyororo wako utazitumia kweli.
Vikomo vya kiwango na majaribio upya
FreeLLMAPI inajaribu mtoa huduma anayefuata mtoa huduma mmoja anaporudisha 429. Msimbo wako unaona 429 pale tu funguo zote kwenye mnyororo zinapofikia kikomo chake. Kisha jibu lina kichwa cha Retry-After. Vikomo vingi vya kila siku huwekwa upya saa sita usiku UTC.
Kwa kazi za makundi, ongeza tabaka la pili la majaribio upya kwa with_retry. Inajaribu upya runnable nzima kwa kusubiri kwa ongezeko la kielelezo na jitter.
Python: jaribu upya mnyororo kwenye vikomo vya kiwango
import openai
from langchain_core.prompts import ChatPromptTemplate
prompt = ChatPromptTemplate.from_messages([
("system", "Summarize the text in one sentence."),
("user", "{text}"),
])
chain = (prompt | llm).with_retry(
retry_if_exception_type=(openai.RateLimitError, openai.APITimeoutError),
wait_exponential_jitter=True,
stop_after_attempt=5,
)
# batch() runs requests in parallel; max_concurrency keeps the rate low
results = chain.batch(
[{"text": t} for t in ["First document.", "Second document."]],
config={"max_concurrency": 4},
)| Tatizo | Chanzo | Suluhisho |
|---|---|---|
openai.AuthenticationError | Ufunguo wa pamoja si sahihi | Nakili tena ufunguo kutoka ukurasa wa Keys |
openai.NotFoundError kwa kila wito | Base URL haina /v1 | Tumia http://localhost:3001/v1 |
openai.RateLimitError | Funguo zote kwenye mnyororo zimefikia kikomo chake | Ongeza watoa huduma, punguza max_concurrency au subiri Retry-After |
| Hitilafu ya embedding kuhusu tokeni au aina ya ingizo | LangChain inatuma tokeni, si maandishi | Weka check_embedding_ctx_length=False |
tool_calls ni tupu | Modeli haiungi mkono zana | Tumia modeli kutoka jedwali la zana au wasifu wa zana |
| Maandishi ya kufikiri hayapo | ChatOpenAI inahifadhi sehemu za kawaida za OpenAI pekee | Soma jibu kwenye content; sehemu za ziada za mtoa huduma hazihifadhiwi |
Maswali yanayoulizwa mara kwa mara
Je, ninaweza kutumia API ya LLM ya bure na LangChain?
Ndiyo. API yoyote inayooana na OpenAI inafanya kazi na ChatOpenAI. Weka base_url kuwa http://localhost:3001/v1 na api_key kuwa ufunguo wako wa pamoja wa FreeLLMAPI. Kipanga njia kinatumia ngazi za bure za watoa huduma.
Ninawekaje base URL maalum kwenye LangChain ChatOpenAI?
Kwenye Python, pitisha base_url kwa ChatOpenAI. Kwenye JavaScript, pitisha configuration: { baseURL } kwa constructor. Kigezo cha mazingira cha OPENAI_BASE_URL pia kinafanya kazi kwenye Python.
Je, mawakala wa LangChain wanafanya kazi na modeli za bure?
Ndiyo, ikiwa modeli inaunga mkono wito wa zana. Tumia create_agent na modeli ya ChatOpenAI, kisha weka modeli zinazoweza kuita zana kwenye mnyororo wako wa FreeLLMAPI.
Kwa nini OpenAIEmbeddings inashindwa na mtoa huduma asiye wa OpenAI?
Kwa chaguo-msingi inatuma vitambulisho vya tokeni. Watoa huduma wengi wengine wanahitaji maandishi ghafi. Weka check_embedding_ctx_length=False kwenye Python.
Ninashughulikiaje hitilafu za 429 kwenye LangChain?
Weka max_retries kwenye ChatOpenAI na ongeza with_retry kwenye mnyororo kwa kazi za makundi. FreeLLMAPI tayari inahamia kwa mtoa huduma anayefuata kabla msimbo wako haujaona 429.
Miongozo inayohusiana
- LLM ya bure kwa LlamaIndex
- LLM API ya bure kwa Python
- API ya LLM bure kwa RAG
- API ya bure ya embeddings
- Free LLM API yenye function calling
- API ya LLM bure kwa wakala wa AI
Vyanzo
- LangChain docs: ChatOpenAI integration (Python) (imekaguliwa 20 November 2026)
- LangChain docs: ChatOpenAI integration (JavaScript) (imekaguliwa 20 November 2026)
- LangChain docs: agents and create_agent (imekaguliwa 20 November 2026)
- LangChain source: OpenAIEmbeddings note on OpenAI-compatible APIs (imekaguliwa 20 November 2026)
- OpenAI Python SDK: retries and errors (imekaguliwa 20 November 2026)
- FreeLLMAPI docs: REST API (tool calling, embeddings, response headers) (imekaguliwa 20 November 2026)