Compare

Eleven V3 vs Gpt-Oss-120b

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
Eleven V3
elevenlabs/eleven-v3
Gpt-Oss-120b
openai/gpt-oss-120b
Provider
Elevenlabs
OpenAI
Family
Modality
audio-tts
text
Context window
128,000 tok
Max output
32,768 tok
Released
2026-07-24
2025-08-05
License
Open-weight
Open-weight
Input price
$0.350 /1M
Output price
$0.750 /1M
Per 1K chars
$0.0001 /1K ch
Tools
yes
Streaming
yes
Vision
JSON mode
yes
Reasoning
yes
Prompt caching
Batch API
Try it
View model →
Open in playground →
Eleven V3
elevenlabs/eleven-v3
Full spec →

ElevenLabs' latest text-to-speech model for highly expressive, natural speech generation with advanced voice control.

Strengths
  • Natural speech synthesis
Use cases
VoiceoversIVRAudiobooks
Gpt-Oss-120b
openai/gpt-oss-120b
Full spec →

OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases – gpt-oss-120b is for production, general purpose, high reasoning use-cases.

Strengths
  • OpenAI's first open-weight release
  • Strong instruction following
  • Apache-2.0 license
Use cases
General chatOn-prem replacement for closed GPT

Compare with another

Claude Opus 5 vs Eleven V3
anthropic/claude-opus-5 · elevenlabs/eleven-v3
Claude Opus 5 vs Gpt-Oss-120b
anthropic/claude-opus-5 · openai/gpt-oss-120b
Grok 4.5 vs Eleven V3
xai/grok-4.5 · elevenlabs/eleven-v3
Grok 4.5 vs Gpt-Oss-120b
xai/grok-4.5 · openai/gpt-oss-120b
Kimi K3 vs Eleven V3
moonshot/kimi-k3 · elevenlabs/eleven-v3
Kimi K3 vs Gpt-Oss-120b
moonshot/kimi-k3 · openai/gpt-oss-120b
Gemini 3.6 Flash vs Eleven V3
google/gemini-3.6-flash · elevenlabs/eleven-v3
Gemini 3.6 Flash vs Gpt-Oss-120b
google/gemini-3.6-flash · openai/gpt-oss-120b
GPT-5.6 Sol vs Eleven V3
openai/gpt-5.6-sol · elevenlabs/eleven-v3
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-...",
)

# Eleven V3
client.chat.completions.create(
    model="elevenlabs/eleven-v3",
    messages=[{"role":"user","content":"hello"}],
)

# Gpt-Oss-120b
client.chat.completions.create(
    model="openai/gpt-oss-120b",
    messages=[{"role":"user","content":"hello"}],
)
Get an AIgateway keyRun an eval on these →