Skip to navigation
Authors and ModelsAlibaba Cloud

Qwen3.8 27B

Qwen3.8 27B
Alibaba Cloud · Text Generation
POST /v1/chat/completions

Multimodal reasoner with 256K context, image and video input, function tools, structured JSON, and thinking on by default.

At a glance

FieldValue
Model idqwen3-8-27b
Model release date2026-08-14
Input modalitiesText, Image, Video
Output modalitiesText
Context window256K
Weight precisionNVFP4 weights + FP8 KV
Max output tokens32,768
Featuresreasoning, vision, video, function_calling, cache, multimodal, json_mode, logprobs
Native inferenceYes
NewNo
Structured outputJSON Schema
Supported endpointsPOST /v1/chat/completions, POST /v1/responses, POST /v1/messages, POST /v1/completions, POST /v1beta/models/qwen3-8-27b:generateContent
Alternate model idsqwen3.8-27b, qwen/qwen3-8-27b, qwen/qwen3.8-27b

Pricing

ChargeSpecRate
Inputper 1M prompt tokens$0.45 $0.17
Outputper 1M generated tokens$3.20 $0.50
Implicit cache readper 1M cached input tokens$0.08
Web Search (Linkup)per call when invoked$0.013

Example request

curl https://api.empiriolabs.ai/v1/chat/completions \
  -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{"model": "qwen3-8-27b", "messages": [{"role":"user","content":"Hello"}]}'

Parameters

ParameterTypeRequiredDefaultDescription
temperaturenumberno1.0Sampling temperature. 0 is deterministic and 2 is maximum randomness. · Range: 0 – 2
top_pnumberno0.95Nucleus sampling probability mass. Lower values make outputs more focused. · Range: 0.01 – 1
max_tokensintegerno32768Maximum output tokens. · Range: 1 – 32768
stopstringno-Up to 4 strings where the model will stop generating further tokens.
enable_thinkingbooleannotrueEnable reasoning before answering.
reasoning_effortenumno"xhigh"Reasoning effort level. none disables thinking. low, medium, and xhigh select discrete thinking depths. There is no token budget control. · Allowed: none, low, medium, xhigh
top_kintegerno20Limit sampling to the top K candidate tokens when supported. · Min: 1
min_pnumberno0Minimum probability threshold for token sampling. · Range: 0 – 1
frequency_penaltynumberno0Penalty based on how often a token has already appeared. · Range: -2 – 2
presence_penaltynumberno0Penalty for tokens that already appeared in the generated text. · Range: -2 – 2
repetition_penaltynumberno1Higher values discourage repeated phrasing. · Min: 0.1
seedintegerno-Optional random seed for reproducible sampling. · Range: 0 – 2147483647
logprobsbooleannofalseReturn token log probabilities when supported.
top_logprobsintegerno-Return up to this many top token log probabilities. · Range: 0 – 20
logit_biasobjectno-Bias token IDs by adding positive or negative values before sampling.
toolsarrayno-OpenAI-compatible function tool definitions.
tool_choiceobjectno-OpenAI-compatible function tool selection.
response_formatenumno-Constrain the output to valid JSON. Use JSON mode for any JSON object, or supply a JSON Schema to force an exact response shape.
web_search_linkupbooleannofalseOptional web search powered by Linkup. When enabled, recent web sources are retrieved using your latest user message as the query and provided to the model as additional context. Adds $0.013 per call when invoked on top of the model’s normal token cost. Disabled by default.
disable_formattingbooleannofalseReturn the answer without the Sources list that web search adds.

Notes

Supports text, image, and video input, streaming, function tools, structured JSON output, seed control, and thinking mode on by default. Use reasoning_effort (xhigh, medium, low) or enable_thinking=false for direct answers. Automatic cache reads are billed at the cached-input rate when reported by the model service. Explicit cache controls are not supported. Open-weight context is 256K; hosted 1M context and official built-in tools are not included.

Machine-readable schema: GET https://api.empiriolabs.ai/v1/models/qwen3-8-27b.