Compare

DeepSeek V4 Pro vs GLM-5.1

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
DeepSeek V4 Pro
deepseek/deepseek-v4-pro
GLM-5.1
zai-org/glm-5.1
Provider
Deepseek
Z.ai
Family
DeepSeek
Modality
text
text
Context window
131,072 tok
200,000 tok
Max output
32,768 tok
Released
2026-08-03
2026-06-23
License
Open-weight
Open-weight
Input price
$2.40 /1M
$1.40 /1M
Output price
$4.80 /1M
$4.40 /1M
Tools
yes
yes
Streaming
yes
yes
Vision
JSON mode
yes
yes
Reasoning
yes
yes
Prompt caching
Batch API
Try it
Open in playground →
Open in playground →
DeepSeek V4 Pro
deepseek/deepseek-v4-pro
Full spec →

DeepSeek V4 Pro is a high-capability reasoning model from DeepSeek, served via Fireworks infrastructure for production-grade inference.

Strengths
  • General-purpose chat
  • Long context
  • Tool use
Use cases
ChatbotsContent generationAgentic workflows
GLM-5.1
zai-org/glm-5.1
Full spec →
Strengths
  • General-purpose chat
  • Long context
  • Tool use
Use cases
ChatbotsContent generationAgentic workflows

Compare with another

Grok 4.6 vs DeepSeek V4 Pro
xai/grok-4.6 · deepseek/deepseek-v4-pro
Grok 4.6 vs GLM-5.1
xai/grok-4.6 · zai-org/glm-5.1
Claude Opus 5 vs DeepSeek V4 Pro
anthropic/claude-opus-5 · deepseek/deepseek-v4-pro
Claude Opus 5 vs GLM-5.1
anthropic/claude-opus-5 · zai-org/glm-5.1
Qwen3.8 Max vs DeepSeek V4 Pro
alibaba/qwen3.8-max · deepseek/deepseek-v4-pro
Qwen3.8 Max vs GLM-5.1
alibaba/qwen3.8-max · zai-org/glm-5.1
DeepSeek V4 Pro vs Kimi K3
deepseek/deepseek-v4-pro · moonshot/kimi-k3
DeepSeek V4 Pro vs GPT-5.6 Sol
deepseek/deepseek-v4-pro · openai/gpt-5.6-sol
DeepSeek V4 Pro vs Claude Fable 5
deepseek/deepseek-v4-pro · anthropic/claude-fable-5
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-...",
)

# DeepSeek V4 Pro
client.chat.completions.create(
    model="deepseek/deepseek-v4-pro",
    messages=[{"role":"user","content":"hello"}],
)

# GLM-5.1
client.chat.completions.create(
    model="zai-org/glm-5.1",
    messages=[{"role":"user","content":"hello"}],
)
Get an AIgateway keyRun an eval on these →