Compare

Qwen 3.5 397B A17B vs Inworld TTS 2

Pricing per million tokens, context window, capabilities — pulled from each provider's public docs. All 2 are available via the same AIgateway OpenAI-compatible endpoint; flip the model string to switch.

Search2/4
Qwen 3.5 397B A17B
alibaba/qwen3.5-397b-a17b
IT
Inworld TTS 2
inworld/tts-2
Provider
Alibaba
Inworld
Family
Qwen
Inworld TTS
Modality
text
audio-tts
Context window
262,144 tok
Max output
4,096 tok
Released
2026-04-15
2026-05-05
License
Open-weight
Proprietary
Input price
$0.600 /1M
Output price
$3.60 /1M
Per 1K chars
$0.035 /1K ch
Tools
yes
Streaming
yes
Vision
JSON mode
yes
Reasoning
yes
Prompt caching
Batch API
Try it
Open in playground →
Open in playground →
Qwen 3.5 397B A17B
alibaba/qwen3.5-397b-a17b
Full spec →

Alibaba's Qwen 3.5 is a 397B-parameter mixture-of-experts model with 17B active parameters, offering strong reasoning capabilities with efficient inference.

Strengths
  • MoE efficiency: 17B active of 397B
  • Strong reasoning at low cost
  • 262k context
Use cases
Production chatMulti-lingualCost-sensitive reasoning
Inworld TTS 2
inworld/tts-2
Full spec →

Inworld's most powerful and expressive text-to-speech model. Builds on TTS 1.5 with rich expressive speech, real-time latency, natural language steering (e.g. [whisper], [say excitedly]), and stronger multilingual support across 15 production languages plus 90+ experimental languages.

Strengths
  • Natural speech synthesis
Use cases
VoiceoversIVRAudiobooks

Compare with another

GPT-5.5 Pro vs Qwen 3.5 397B A17B
openai/gpt-5.5-pro · alibaba/qwen3.5-397b-a17b
GPT-5.5 Pro vs Inworld TTS 2
openai/gpt-5.5-pro · inworld/tts-2
GPT-5.5 vs Qwen 3.5 397B A17B
openai/gpt-5.5 · alibaba/qwen3.5-397b-a17b
GPT-5.5 vs Inworld TTS 2
openai/gpt-5.5 · inworld/tts-2
Claude Opus 4.7 vs Qwen 3.5 397B A17B
anthropic/claude-opus-4.7 · alibaba/qwen3.5-397b-a17b
Claude Opus 4.7 vs Inworld TTS 2
anthropic/claude-opus-4.7 · inworld/tts-2
Claude Sonnet 4.6 vs Qwen 3.5 397B A17B
anthropic/claude-sonnet-4.6 · alibaba/qwen3.5-397b-a17b
Claude Sonnet 4.6 vs Inworld TTS 2
anthropic/claude-sonnet-4.6 · inworld/tts-2
Kimi-K2.6 vs Qwen 3.5 397B A17B
moonshot/kimi-k2.6 · alibaba/qwen3.5-397b-a17b
SWITCH BETWEEN THEM

One key, all 2, one line different.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.aigateway.sh/v1",
    api_key="sk-aig-...",
)

# Qwen 3.5 397B A17B
client.chat.completions.create(
    model="alibaba/qwen3.5-397b-a17b",
    messages=[{"role":"user","content":"hello"}],
)

# Inworld TTS 2
client.chat.completions.create(
    model="inworld/tts-2",
    messages=[{"role":"user","content":"hello"}],
)
Get an AIgateway keyRun an eval on these →