Llama 3.3 70B Instruct
AvailableMeta Llama 3.3 70B Instruct: dynamic FP8 quantization. Text quality close to the 405B class, as a dense model on a single GPU.
CHAT
Context window
32K
32,768 tokens
Input price
$0.99 / 1M tokens
Output price
$1.99 / 1M tokens
Quickstart
OpenAI-compatible API. Point base_url at the gateway and pass the Model ID in the model field.
curl https://llm.fixcloud.ai/v1/chat/completions \
-H "Authorization: Bearer $FXC_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "llama-3.3-70b-instruct",
"messages": [{"role": "user", "content": "Hello!"}]
}'from openai import OpenAI
client = OpenAI(base_url="https://llm.fixcloud.ai/v1", api_key="FXC_API_KEY")
response = client.chat.completions.create(
model="llama-3.3-70b-instruct",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)import OpenAI from 'openai';
const client = new OpenAI({ baseURL: 'https://llm.fixcloud.ai/v1', apiKey: process.env.FXC_API_KEY });
const response = await client.chat.completions.create({
model: 'llama-3.3-70b-instruct',
messages: [{ role: 'user', content: 'Hello!' }],
});
console.log(response.choices[0].message.content);curl https://llm.fixcloud.ai/v1/chat/completions -N \
-H "Authorization: Bearer $FXC_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "llama-3.3-70b-instruct",
"messages": [{"role": "user", "content": "Hello!"}],
"stream": true
}'from openai import OpenAI
client = OpenAI(base_url="https://llm.fixcloud.ai/v1", api_key="FXC_API_KEY")
stream = client.chat.completions.create(
model="llama-3.3-70b-instruct",
messages=[{"role": "user", "content": "Write a haiku about GPUs."}],
stream=True,
)
for chunk in stream:
delta = chunk.choices[0].delta.content
if delta:
print(delta, end="", flush=True)import OpenAI from 'openai';
const client = new OpenAI({ baseURL: 'https://llm.fixcloud.ai/v1', apiKey: process.env.FXC_API_KEY });
const stream = await client.chat.completions.create({
model: 'llama-3.3-70b-instruct',
messages: [{ role: 'user', content: 'Write a haiku about GPUs.' }],
stream: true,
});
for await (const chunk of stream) {
process.stdout.write(chunk.choices[0]?.delta?.content ?? '');
}curl https://llm.fixcloud.ai/v1/chat/completions \
-H "Authorization: Bearer $FXC_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "llama-3.3-70b-instruct",
"tools": [{
"type": "function",
"function": {
"name": "get_weather",
"description": "Get the current weather for a city",
"parameters": {
"type": "object",
"properties": {"city": {"type": "string"}},
"required": ["city"]
}
}
}],
"tool_choice": "auto",
"messages": [{"role": "user", "content": "What is the weather in Istanbul?"}]
}'from openai import OpenAI
client = OpenAI(base_url="https://llm.fixcloud.ai/v1", api_key="FXC_API_KEY")
tools = [{
"type": "function",
"function": {
"name": "get_weather",
"description": "Get the current weather for a city",
"parameters": {
"type": "object",
"properties": {"city": {"type": "string"}},
"required": ["city"],
},
},
}]
response = client.chat.completions.create(
model="llama-3.3-70b-instruct",
messages=[{"role": "user", "content": "What is the weather in Istanbul?"}],
tools=tools,
tool_choice="auto",
)
print(response.choices[0].message.tool_calls)import OpenAI from 'openai';
const client = new OpenAI({ baseURL: 'https://llm.fixcloud.ai/v1', apiKey: process.env.FXC_API_KEY });
const tools = [{
type: 'function',
function: {
name: 'get_weather',
description: 'Get the current weather for a city',
parameters: {
type: 'object',
properties: { city: { type: 'string' } },
required: ['city'],
},
},
}];
const response = await client.chat.completions.create({
model: 'llama-3.3-70b-instruct',
messages: [{ role: 'user', content: 'What is the weather in Istanbul?' }],
tools,
tool_choice: 'auto',
});
console.log(response.choices[0].message.tool_calls);curl https://llm.fixcloud.ai/v1/chat/completions \
-H "Authorization: Bearer $FXC_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "llama-3.3-70b-instruct",
"response_format": {
"type": "json_schema",
"json_schema": {
"name": "city_info",
"schema": {
"type": "object",
"properties": {"city": {"type": "string"}, "country": {"type": "string"}},
"required": ["city", "country"]
}
}
},
"messages": [{"role": "user", "content": "Where is the Bosphorus?"}]
}'from openai import OpenAI
client = OpenAI(base_url="https://llm.fixcloud.ai/v1", api_key="FXC_API_KEY")
response = client.chat.completions.create(
model="llama-3.3-70b-instruct",
messages=[{"role": "user", "content": "Where is the Bosphorus?"}],
response_format={
"type": "json_schema",
"json_schema": {
"name": "city_info",
"schema": {
"type": "object",
"properties": {"city": {"type": "string"}, "country": {"type": "string"}},
"required": ["city", "country"],
},
},
},
)
print(response.choices[0].message.content) # valid JSONimport OpenAI from 'openai';
const client = new OpenAI({ baseURL: 'https://llm.fixcloud.ai/v1', apiKey: process.env.FXC_API_KEY });
const response = await client.chat.completions.create({
model: 'llama-3.3-70b-instruct',
messages: [{ role: 'user', content: 'Where is the Bosphorus?' }],
response_format: {
type: 'json_schema',
json_schema: {
name: 'city_info',
schema: {
type: 'object',
properties: { city: { type: 'string' }, country: { type: 'string' } },
required: ['city', 'country'],
},
},
},
});
console.log(JSON.parse(response.choices[0].message.content));Capabilities
The features this model offers through the API.
- ChatMulti-turn chat via /v1/chat/completions.
- Tool callingCalls the tools you define in the OpenAI tools format.
- Function callingSupports function-calling schemas.
- JSON schemaOutput constrained to a JSON schema via response_format.
- Structured outputProduces structured, machine-parseable output.
- StreamingToken-level streaming (stream: true).
- Batch inferenceAsynchronous bulk jobs (Batch API).
Pricing
Prices are per 1 million tokens. Once the monthly token quota of your plan is used up, usage is billed at these prices.
Input price
$0.99/ 1M tokens
Output price
$1.99/ 1M tokens
Cost estimator
- Per request
- —
- Per day
- —
- Per month (30 days)
- —
Enter your expected usage; actual billing follows the token counts measured by the gateway.
View plansSpecifications
Transparency details about the infrastructure serving this model.
- Family
- llama
- Publisher
- Meta
- License
- llama-3.3
- Model ID
- llama-3.3-70b-instruct
- Context (tokens)
- 32,768
- Quantization
- None (native)
- GPUs per replica
- 1 × GPU
32K-token serving window.