Qwen3.5 - Baseten

Reasoning Tool calling Long context Agentic

Setup

To get started, sign into Baseten with Truss and then install the OpenAI SDK.

Sign in to Baseten

uvx truss login --browser

Install the OpenAI SDK

uv pip install openai

Pick the model you want to deploy. Each tab is a self-contained recipe.

4B
9B
35B
122B

Qwen/Qwen3.5-4B is a 4B-parameter dense model with up to 256K context.This preset serves Qwen3.5-4B with BF16 weights on a single H100, optimized for low time-to-first-token.

Hardware

H100 × 1

Engine

vLLM 0.18.0

Context

32K

Concurrency

128

Write the config

Create and move into the project directory:

mkdir qwen3.5-4b-latency && cd qwen3.5-4b-latency

Then create a file named config.yaml and paste the following:

config.yaml

model_name: "model:qwen3.5-4b preset:latency"
model_metadata:
  example_model_input:
    model: "Qwen/Qwen3.5-4B"
    messages:
      - role: user
        content: "What is the capital of France?"
    max_tokens: 100
    temperature: 0.7
base_image:
  image: vllm/vllm-openai:v0.18.0
weights:
  - source: "hf://Qwen/Qwen3.5-4B@main"
    mount_location: "/app/checkpoint/qwen3.5-4b"
    auth_secret_name: "hf_access_token"
build_commands: []
docker_server:
  start_command: >-
    sh -c "vllm serve /app/checkpoint/qwen3.5-4b
    --served-model-name Qwen/Qwen3.5-4B
    --host 0.0.0.0
    --port 8000
    --gpu-memory-utilization 0.95
    --max-model-len 32768
    --dtype bfloat16
    --reasoning-parser qwen3
    --enable-auto-tool-choice
    --tool-call-parser qwen3_coder
    --trust-remote-code"
  readiness_endpoint: /health
  liveness_endpoint: /health
  predict_endpoint: /v1/chat/completions
  server_port: 8000
environment_variables:
  HF_HUB_ENABLE_HF_TRANSFER: '1'
  VLLM_LOGGING_LEVEL: WARNING
runtime:
  predict_concurrency: 128
resources:
  accelerator: H100:1
  use_gpu: true
secrets:
  hf_access_token: null

Flags

The start_command passes these flags to the engine. Each one controls a runtime or serving behavior:

Flag	Value	What it does
`--gpu-memory-utilization`	`0.95`	Fraction of GPU memory vLLM may use for weights and KV cache.
`--max-model-len`	`32768`	Maximum context length (tokens) the server accepts per request.
`--dtype`	`bfloat16`	Weight precision loaded at runtime. bfloat16: BF16 weights, no quantization.
`--reasoning-parser`	`qwen3`	Server-side parser that separates reasoning output into `reasoning_content`. qwen3: Qwen3-family thinking format (used by Qwen3, Qwen3.5, and Qwen3.6).
`--enable-auto-tool-choice`	(no value)	Let the model choose when to call tools without requiring `tool_choice: "required"`.
`--tool-call-parser`	`qwen3_coder`	Server-side parser that emits structured `tool_calls` on the response. qwen3_coder: Qwen3-Coder tool format.
`--trust-remote-code`	(no value)	Execute model-specific Python from the checkpoint (required for many Qwen, Phi, and custom architectures).

Deploy

Push the config to Baseten:

uvx truss push

You should see output similar to:

✨ Model qwen3.5-4b-latency was successfully pushed ✨
🪵 View logs for your deployment at https://app.baseten.co/models/abcd1234/logs/wxyz5678

Your model ID is the string after /models/ in the logs URL (abcd1234 in the example). Use it wherever you see {model_id} in the next section.

Call the model

Your deployment serves an OpenAI-compatible API. Replace {model_id} with your model ID and make sure BASETEN_API_KEY is set.Now call your deployment to run inference:

Python
cURL

main.py

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["BASETEN_API_KEY"],
    base_url="https://model-{model_id}.api.baseten.co/environments/production/sync/v1",
)

response = client.chat.completions.create(
    model="Qwen/Qwen3.5-4B",
    messages=[
        {"role": "user", "content": "What is machine learning?"}
    ],
)

print(response.choices[0].message.content)

curl -s https://model-{model_id}.api.baseten.co/environments/production/sync/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $BASETEN_API_KEY" \
  -d '{
    "model": "Qwen/Qwen3.5-4B",
    "messages": [
      {"role": "user", "content": "What is machine learning?"}
    ]
  }'

To access the model’s chain of thought, enable thinking mode. The server parses the reasoning output into a separate reasoning_content field on the response:

response = client.chat.completions.create(
    model="Qwen/Qwen3.5-4B",
    messages=[
        {"role": "user", "content": "How many r's in strawberry?"}
    ],
    extra_body={"chat_template_kwargs": {"enable_thinking": True}},
)
print(response.choices[0].message.reasoning_content)  # chain of thought
print(response.choices[0].message.content)            # final answer

To let the model call tools, pass a tools array. The server returns structured tool_calls on the response:

tools = [{
    "type": "function",
    "function": {
        "name": "get_weather",
        "parameters": {
            "type": "object",
            "properties": {"location": {"type": "string"}},
            "required": ["location"],
        },
    },
}]

response = client.chat.completions.create(
    model="Qwen/Qwen3.5-4B",
    messages=[
        {"role": "user", "content": "What's the weather in Paris?"}
    ],
    tools=tools,
)
print(response.choices[0].message.tool_calls)

Qwen/Qwen3.5-9B is a 9B-parameter dense model with up to 256K context.This preset serves Qwen3.5-9B with BF16 weights on a single H100. It’s the smallest dense Qwen3.5 deployment that keeps reasoning and tool calling enabled.

Hardware

H100 × 1

Engine

vLLM 0.18.0

Context

32K

Concurrency

128

Write the config

Create and move into the project directory:

mkdir qwen3.5-9b-latency && cd qwen3.5-9b-latency

Then create a file named config.yaml and paste the following:

config.yaml

model_name: "model:qwen3.5-9b preset:latency"
model_metadata:
  example_model_input:
    model: "Qwen/Qwen3.5-9B"
    messages:
      - role: user
        content: "What is the capital of France?"
    max_tokens: 100
    temperature: 0.7
base_image:
  image: vllm/vllm-openai:v0.18.0
weights:
  - source: "hf://Qwen/Qwen3.5-9B@main"
    mount_location: "/app/checkpoint/qwen3.5-9b"
    auth_secret_name: "hf_access_token"
build_commands: []
docker_server:
  start_command: >-
    sh -c "vllm serve /app/checkpoint/qwen3.5-9b
    --served-model-name Qwen/Qwen3.5-9B
    --host 0.0.0.0
    --port 8000
    --gpu-memory-utilization 0.95
    --max-model-len 32768
    --dtype bfloat16
    --reasoning-parser qwen3
    --enable-auto-tool-choice
    --tool-call-parser qwen3_coder
    --trust-remote-code"
  readiness_endpoint: /health
  liveness_endpoint: /health
  predict_endpoint: /v1/chat/completions
  server_port: 8000
environment_variables:
  HF_HUB_ENABLE_HF_TRANSFER: '1'
  VLLM_LOGGING_LEVEL: WARNING
runtime:
  predict_concurrency: 128
resources:
  accelerator: H100:1
  use_gpu: true
secrets:
  hf_access_token: null

Flags

The start_command passes these flags to the engine. Each one controls a runtime or serving behavior:

Flag	Value	What it does
`--gpu-memory-utilization`	`0.95`	Fraction of GPU memory vLLM may use for weights and KV cache.
`--max-model-len`	`32768`	Maximum context length (tokens) the server accepts per request.
`--dtype`	`bfloat16`	Weight precision loaded at runtime. bfloat16: BF16 weights, no quantization.
`--reasoning-parser`	`qwen3`	Server-side parser that separates reasoning output into `reasoning_content`. qwen3: Qwen3-family thinking format (used by Qwen3, Qwen3.5, and Qwen3.6).
`--enable-auto-tool-choice`	(no value)	Let the model choose when to call tools without requiring `tool_choice: "required"`.
`--tool-call-parser`	`qwen3_coder`	Server-side parser that emits structured `tool_calls` on the response. qwen3_coder: Qwen3-Coder tool format.
`--trust-remote-code`	(no value)	Execute model-specific Python from the checkpoint (required for many Qwen, Phi, and custom architectures).

Deploy

Push the config to Baseten:

uvx truss push

You should see output similar to:

✨ Model qwen3.5-9b-latency was successfully pushed ✨
🪵 View logs for your deployment at https://app.baseten.co/models/abcd1234/logs/wxyz5678

Your model ID is the string after /models/ in the logs URL (abcd1234 in the example). Use it wherever you see {model_id} in the next section.

Call the model

Your deployment serves an OpenAI-compatible API. Replace {model_id} with your model ID and make sure BASETEN_API_KEY is set.Now call your deployment to run inference:

Python
cURL

main.py

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["BASETEN_API_KEY"],
    base_url="https://model-{model_id}.api.baseten.co/environments/production/sync/v1",
)

response = client.chat.completions.create(
    model="Qwen/Qwen3.5-9B",
    messages=[
        {"role": "user", "content": "What is machine learning?"}
    ],
)

print(response.choices[0].message.content)

curl -s https://model-{model_id}.api.baseten.co/environments/production/sync/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $BASETEN_API_KEY" \
  -d '{
    "model": "Qwen/Qwen3.5-9B",
    "messages": [
      {"role": "user", "content": "What is machine learning?"}
    ]
  }'

To access the model’s chain of thought, enable thinking mode. The server parses the reasoning output into a separate reasoning_content field on the response:

response = client.chat.completions.create(
    model="Qwen/Qwen3.5-9B",
    messages=[
        {"role": "user", "content": "How many r's in strawberry?"}
    ],
    extra_body={"chat_template_kwargs": {"enable_thinking": True}},
)
print(response.choices[0].message.reasoning_content)  # chain of thought
print(response.choices[0].message.content)            # final answer

To let the model call tools, pass a tools array. The server returns structured tool_calls on the response:

tools = [{
    "type": "function",
    "function": {
        "name": "get_weather",
        "parameters": {
            "type": "object",
            "properties": {"location": {"type": "string"}},
            "required": ["location"],
        },
    },
}]

response = client.chat.completions.create(
    model="Qwen/Qwen3.5-9B",
    messages=[
        {"role": "user", "content": "What's the weather in Paris?"}
    ],
    tools=tools,
)
print(response.choices[0].message.tool_calls)

Qwen/Qwen3.5-35B-A3B is a 35B-parameter hybrid MoE model (3B active per token) with up to 256K context.This variant ships in 2 presets tuned for different goals: Latency for lowest time-to-first-token, and Throughput for highest tokens per second. Pick the tab that matches your workload.

Latency
Throughput

This preset serves Qwen3.5-35B with BF16 weights on H100:2, optimized for low time-to-first-token on interactive chat and short-horizon agent workflows.

Hardware

H100 × 2

Engine

vLLM 0.18.0

Context

32K

Concurrency

128

Write the config

Create and move into the project directory:

mkdir qwen3.5-35b-latency && cd qwen3.5-35b-latency

Then create a file named config.yaml and paste the following:

config.yaml

model_name: "model:qwen3.5-35b preset:latency"
model_metadata:
  example_model_input:
    model: "Qwen/Qwen3.5-35B-A3B"
    messages:
      - role: user
        content: "What is the capital of France?"
    max_tokens: 100
    temperature: 0.7
base_image:
  image: vllm/vllm-openai:v0.18.0
weights:
  - source: "hf://Qwen/Qwen3.5-35B-A3B@main"
    mount_location: "/app/checkpoint/qwen3.5-35b-a3b"
    auth_secret_name: "hf_access_token"
build_commands: []
docker_server:
  start_command: >-
    sh -c "vllm serve /app/checkpoint/qwen3.5-35b-a3b
    --served-model-name Qwen/Qwen3.5-35B-A3B
    --host 0.0.0.0
    --port 8000
    --gpu-memory-utilization 0.95
    --max-model-len 32768
    --dtype bfloat16
    --tensor-parallel-size 2
    --reasoning-parser qwen3
    --enable-auto-tool-choice
    --tool-call-parser qwen3_coder
    --trust-remote-code"
  readiness_endpoint: /health
  liveness_endpoint: /health
  predict_endpoint: /v1/chat/completions
  server_port: 8000
environment_variables:
  HF_HUB_ENABLE_HF_TRANSFER: '1'
  VLLM_LOGGING_LEVEL: WARNING
runtime:
  predict_concurrency: 128
resources:
  accelerator: H100:2
  use_gpu: true
secrets:
  hf_access_token: null

Flags

The start_command passes these flags to the engine. Each one controls a runtime or serving behavior:

Flag	Value	What it does
`--gpu-memory-utilization`	`0.95`	Fraction of GPU memory vLLM may use for weights and KV cache.
`--max-model-len`	`32768`	Maximum context length (tokens) the server accepts per request.
`--dtype`	`bfloat16`	Weight precision loaded at runtime. bfloat16: BF16 weights, no quantization.
`--tensor-parallel-size`	`2`	Number of GPUs to shard the model across.
`--reasoning-parser`	`qwen3`	Server-side parser that separates reasoning output into `reasoning_content`. qwen3: Qwen3-family thinking format (used by Qwen3, Qwen3.5, and Qwen3.6).
`--enable-auto-tool-choice`	(no value)	Let the model choose when to call tools without requiring `tool_choice: "required"`.
`--tool-call-parser`	`qwen3_coder`	Server-side parser that emits structured `tool_calls` on the response. qwen3_coder: Qwen3-Coder tool format.
`--trust-remote-code`	(no value)	Execute model-specific Python from the checkpoint (required for many Qwen, Phi, and custom architectures).

Deploy

Push the config to Baseten:

uvx truss push

You should see output similar to:

✨ Model qwen3.5-35b-latency was successfully pushed ✨
🪵 View logs for your deployment at https://app.baseten.co/models/abcd1234/logs/wxyz5678

Your model ID is the string after /models/ in the logs URL (abcd1234 in the example). Use it wherever you see {model_id} in the next section.

Call the model

Your deployment serves an OpenAI-compatible API. Replace {model_id} with your model ID and make sure BASETEN_API_KEY is set.Now call your deployment to run inference:

Python
cURL

main.py

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["BASETEN_API_KEY"],
    base_url="https://model-{model_id}.api.baseten.co/environments/production/sync/v1",
)

response = client.chat.completions.create(
    model="Qwen/Qwen3.5-35B-A3B",
    messages=[
        {"role": "user", "content": "What is machine learning?"}
    ],
)

print(response.choices[0].message.content)

curl -s https://model-{model_id}.api.baseten.co/environments/production/sync/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $BASETEN_API_KEY" \
  -d '{
    "model": "Qwen/Qwen3.5-35B-A3B",
    "messages": [
      {"role": "user", "content": "What is machine learning?"}
    ]
  }'

To access the model’s chain of thought, enable thinking mode. The server parses the reasoning output into a separate reasoning_content field on the response:

response = client.chat.completions.create(
    model="Qwen/Qwen3.5-35B-A3B",
    messages=[
        {"role": "user", "content": "How many r's in strawberry?"}
    ],
    extra_body={"chat_template_kwargs": {"enable_thinking": True}},
)
print(response.choices[0].message.reasoning_content)  # chain of thought
print(response.choices[0].message.content)            # final answer

To let the model call tools, pass a tools array. The server returns structured tool_calls on the response:

tools = [{
    "type": "function",
    "function": {
        "name": "get_weather",
        "parameters": {
            "type": "object",
            "properties": {"location": {"type": "string"}},
            "required": ["location"],
        },
    },
}]

response = client.chat.completions.create(
    model="Qwen/Qwen3.5-35B-A3B",
    messages=[
        {"role": "user", "content": "What's the weather in Paris?"}
    ],
    tools=tools,
)
print(response.choices[0].message.tool_calls)

This preset serves Qwen3.5-35B FP8 on a single B200, with prefix caching and chunked prefill enabled. It maximizes aggregate throughput at high concurrency with minor quality impact from FP8.

Hardware

B200

Engine

vLLM 0.18.0

Context

256K

Concurrency

1000

Write the config

Create and move into the project directory:

mkdir qwen3.5-35b-throughput && cd qwen3.5-35b-throughput

Then create a file named config.yaml and paste the following:

config.yaml

########################################################
# Remove ( --language-model-only ) from the start command to turn on multimodal mode
########################################################

model_name: "model:qwen3.5-35b preset:throughput"
model_metadata:
  example_model_input:
    model: "Qwen/Qwen3.5-35B-A3B-FP8"
    messages:
      - role: user
        content: "What is the capital of France?"
    max_tokens: 100
    temperature: 0.7
base_image:
  image: vllm/vllm-openai:v0.18.0
weights:
  - source: "hf://Qwen/Qwen3.5-35B-A3B-FP8@main"
    mount_location: "/app/model_cache/qwen3.5-35b-a3b-fp8"
    auth_secret_name: "hf_access_token"
build_commands:
  - pip install --upgrade transformers
environment_variables:
  VLLM_USE_FLASHINFER_MOE_FP8: "0"
  PYTORCH_ALLOC_CONF: "expandable_segments:True"
docker_server:
  start_command: >-
    vllm serve /app/model_cache/qwen3.5-35b-a3b-fp8
    --served-model-name Qwen/Qwen3.5-35B-A3B-FP8
    --host 0.0.0.0
    --language-model-only
    --port 8000
    --gpu-memory-utilization 0.95
    --kv-cache-dtype fp8
    --reasoning-parser qwen3
    --enable-chunked-prefill
    --enable-prefix-caching
    --max-num-seqs 512
    --trust-remote-code
  readiness_endpoint: /health
  liveness_endpoint: /health
  predict_endpoint: /v1/chat/completions
  server_port: 8000
runtime:
  predict_concurrency: 1000
  health_checks:
    restart_check_delay_seconds: 1500
    restart_threshold_seconds: 1500
    stop_traffic_threshold_seconds: 120
resources:
  accelerator: B200
  use_gpu: true
secrets:
  hf_access_token: null

Flags

The start_command passes these flags to the engine. Each one controls a runtime or serving behavior:

Flag	Value	What it does
`--language-model-only`	(no value)	Disable the multimodal path; text-only serving. Remove to enable image/video inputs.
`--gpu-memory-utilization`	`0.95`	Fraction of GPU memory vLLM may use for weights and KV cache.
`--kv-cache-dtype`	`fp8`	KV cache numeric precision. fp8: ~2× KV cache density with negligible quality impact on most models.
`--reasoning-parser`	`qwen3`	Server-side parser that separates reasoning output into `reasoning_content`. qwen3: Qwen3-family thinking format (used by Qwen3, Qwen3.5, and Qwen3.6).
`--enable-chunked-prefill`	(no value)	Process long prompts in chunks so decode requests keep running.
`--enable-prefix-caching`	(no value)	Reuse KV cache across requests that share a prefix.
`--max-num-seqs`	`512`	Maximum number of concurrent sequences in the batch.
`--trust-remote-code`	(no value)	Execute model-specific Python from the checkpoint (required for many Qwen, Phi, and custom architectures).

Deploy

Push the config to Baseten:

uvx truss push

You should see output similar to:

✨ Model qwen3.5-35b-throughput was successfully pushed ✨
🪵 View logs for your deployment at https://app.baseten.co/models/abcd1234/logs/wxyz5678

Your model ID is the string after /models/ in the logs URL (abcd1234 in the example). Use it wherever you see {model_id} in the next section.

Call the model

Your deployment serves an OpenAI-compatible API. Replace {model_id} with your model ID and make sure BASETEN_API_KEY is set.Now call your deployment to run inference:

Python
cURL

main.py

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["BASETEN_API_KEY"],
    base_url="https://model-{model_id}.api.baseten.co/environments/production/sync/v1",
)

response = client.chat.completions.create(
    model="Qwen/Qwen3.5-35B-A3B-FP8",
    messages=[
        {"role": "user", "content": "What is machine learning?"}
    ],
)

print(response.choices[0].message.content)

curl -s https://model-{model_id}.api.baseten.co/environments/production/sync/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $BASETEN_API_KEY" \
  -d '{
    "model": "Qwen/Qwen3.5-35B-A3B-FP8",
    "messages": [
      {"role": "user", "content": "What is machine learning?"}
    ]
  }'

To access the model’s chain of thought, enable thinking mode. The server parses the reasoning output into a separate reasoning_content field on the response:

response = client.chat.completions.create(
    model="Qwen/Qwen3.5-35B-A3B-FP8",
    messages=[
        {"role": "user", "content": "How many r's in strawberry?"}
    ],
    extra_body={"chat_template_kwargs": {"enable_thinking": True}},
)
print(response.choices[0].message.reasoning_content)  # chain of thought
print(response.choices[0].message.content)            # final answer

Qwen/Qwen3.5-122B-A10B is a 122B-parameter MoE model (10B active per token) with up to 256K context.This preset serves Qwen3.5-122B with BF16 weights on H100:4. It keeps time-to-first-token low while fitting the full model on a single H100 node.

Hardware

H100 × 4

Engine

vLLM 0.18.0

Context

32K

Concurrency

128

Write the config

Create and move into the project directory:

mkdir qwen3.5-122b-latency && cd qwen3.5-122b-latency

Then create a file named config.yaml and paste the following:

config.yaml

model_name: "model:qwen3.5-122b preset:latency"
model_metadata:
  example_model_input:
    model: "Qwen/Qwen3.5-122B-A10B"
    messages:
      - role: user
        content: "What is the capital of France?"
    max_tokens: 100
    temperature: 0.7
base_image:
  image: vllm/vllm-openai:v0.18.0
weights:
  - source: "hf://Qwen/Qwen3.5-122B-A10B@main"
    mount_location: "/app/checkpoint/qwen3.5-122b-a10b"
    auth_secret_name: "hf_access_token"
build_commands: []
docker_server:
  start_command: >-
    sh -c "vllm serve /app/checkpoint/qwen3.5-122b-a10b
    --served-model-name Qwen/Qwen3.5-122B-A10B
    --host 0.0.0.0
    --port 8000
    --gpu-memory-utilization 0.95
    --max-model-len 32768
    --dtype bfloat16
    --tensor-parallel-size 4
    --reasoning-parser qwen3
    --enable-auto-tool-choice
    --tool-call-parser qwen3_coder
    --trust-remote-code"
  readiness_endpoint: /health
  liveness_endpoint: /health
  predict_endpoint: /v1/chat/completions
  server_port: 8000
environment_variables:
  HF_HUB_ENABLE_HF_TRANSFER: '1'
  VLLM_LOGGING_LEVEL: WARNING
runtime:
  predict_concurrency: 128
resources:
  accelerator: H100:4
  use_gpu: true
secrets:
  hf_access_token: null

Flags

The start_command passes these flags to the engine. Each one controls a runtime or serving behavior:

Flag	Value	What it does
`--gpu-memory-utilization`	`0.95`	Fraction of GPU memory vLLM may use for weights and KV cache.
`--max-model-len`	`32768`	Maximum context length (tokens) the server accepts per request.
`--dtype`	`bfloat16`	Weight precision loaded at runtime. bfloat16: BF16 weights, no quantization.
`--tensor-parallel-size`	`4`	Number of GPUs to shard the model across.
`--reasoning-parser`	`qwen3`	Server-side parser that separates reasoning output into `reasoning_content`. qwen3: Qwen3-family thinking format (used by Qwen3, Qwen3.5, and Qwen3.6).
`--enable-auto-tool-choice`	(no value)	Let the model choose when to call tools without requiring `tool_choice: "required"`.
`--tool-call-parser`	`qwen3_coder`	Server-side parser that emits structured `tool_calls` on the response. qwen3_coder: Qwen3-Coder tool format.
`--trust-remote-code`	(no value)	Execute model-specific Python from the checkpoint (required for many Qwen, Phi, and custom architectures).

Deploy

Push the config to Baseten:

uvx truss push

You should see output similar to:

✨ Model qwen3.5-122b-latency was successfully pushed ✨
🪵 View logs for your deployment at https://app.baseten.co/models/abcd1234/logs/wxyz5678

Your model ID is the string after /models/ in the logs URL (abcd1234 in the example). Use it wherever you see {model_id} in the next section.

Call the model

Your deployment serves an OpenAI-compatible API. Replace {model_id} with your model ID and make sure BASETEN_API_KEY is set.Now call your deployment to run inference:

Python
cURL

main.py

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["BASETEN_API_KEY"],
    base_url="https://model-{model_id}.api.baseten.co/environments/production/sync/v1",
)

response = client.chat.completions.create(
    model="Qwen/Qwen3.5-122B-A10B",
    messages=[
        {"role": "user", "content": "What is machine learning?"}
    ],
)

print(response.choices[0].message.content)

curl -s https://model-{model_id}.api.baseten.co/environments/production/sync/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $BASETEN_API_KEY" \
  -d '{
    "model": "Qwen/Qwen3.5-122B-A10B",
    "messages": [
      {"role": "user", "content": "What is machine learning?"}
    ]
  }'

To access the model’s chain of thought, enable thinking mode. The server parses the reasoning output into a separate reasoning_content field on the response:

response = client.chat.completions.create(
    model="Qwen/Qwen3.5-122B-A10B",
    messages=[
        {"role": "user", "content": "How many r's in strawberry?"}
    ],
    extra_body={"chat_template_kwargs": {"enable_thinking": True}},
)
print(response.choices[0].message.reasoning_content)  # chain of thought
print(response.choices[0].message.content)            # final answer

To let the model call tools, pass a tools array. The server returns structured tool_calls on the response:

tools = [{
    "type": "function",
    "function": {
        "name": "get_weather",
        "parameters": {
            "type": "object",
            "properties": {"location": {"type": "string"}},
            "required": ["location"],
        },
    },
}]

response = client.chat.completions.create(
    model="Qwen/Qwen3.5-122B-A10B",
    messages=[
        {"role": "user", "content": "What's the weather in Paris?"}
    ],
    tools=tools,
)
print(response.choices[0].message.tool_calls)

​Setup

Hardware

Engine

Context

Concurrency

​Write the config

​Flags

​Deploy

​Call the model

Hardware

Engine

Context

Concurrency

​Write the config

​Flags

​Deploy

​Call the model

Hardware

Engine

Context

Concurrency

​Write the config

​Flags

​Deploy

​Call the model

Hardware

Engine

Context

Concurrency

​Write the config

​Flags

​Deploy

​Call the model

Hardware

Engine

Context

Concurrency

​Write the config

​Flags

​Deploy

​Call the model

Setup

Write the config

Flags

Deploy

Call the model

Write the config

Flags

Deploy

Call the model

Write the config

Flags

Deploy

Call the model

Write the config

Flags

Deploy

Call the model

Write the config

Flags

Deploy

Call the model