💻

OpenCode

Speed: ⚡ 52 tok/s avg

Models: 15

Price: $10/mo flat

Status: ✅ Online

Avg Speed

52 tok/s

Models

Price

$10/mo

Best For

GLM-5, MiniMax, Value

💰 Plan & Pricing

✅

Best Value — $10/mo flat
15 models, no usage caps, no rate limits. GLM-5 champion provider. MiniMax M2.5/M2.7 exclusive. Best per-dollar value by far.

🔑 API Key

sk-Owk...7HMm

🌐 Endpoint

https://opencode.ai/zen/go/v1/chat/completions

📦 Models (15 total)

Model	Speed	Category	Notes
glm-5.1	⚡ 69 tok/s	Chat	🥇 GLM-5.1 champion
minimax-m2.7	⚡ 87 tok/s	Chat	🥇 MiniMax M2.7 champion
glm-5	⚡ 52 tok/s	Chat	GLM-5
claude-sonnet-4	⚡ 52 tok/s	Chat	Claude Sonnet 4
deepseek-r1-0528	⚡ 65 tok/s	Reasoning	DeepSeek R1
deepseek-v4-flash	⚡ 58 tok/s	Chat	DeepSeek V4 Flash
deepseek-v4-pro	⚡ 52 tok/s	Reasoning	DeepSeek V4 Pro
minimax-m2.5	⚡ 80 tok/s	Chat	🥇 MiniMax M2.5 champion
kimi-k2.5	⚡ 58 tok/s	Chat	Kimi K2.5
gpt-4.1	⚡ 48 tok/s	Chat	GPT-4.1
qwen3-235b	⚡ 45 tok/s	Chat	Qwen3 235B
qwen3-30b-a3b	⚡ 55 tok/s	Chat	Qwen3 30B MoE
step-3-chat	⚡ 50 tok/s	Chat	Step-3 Chat
glm-5-vision	⚡ 40 tok/s	Vision/OCR	GLM-5 Vision
minimax-vl-01	⚡ 42 tok/s	Vision	MiniMax Vision

💻 cURL Example

curl -X POST https://opencode.ai/zen/go/v1/chat/completions \
  -H "Authorization: Bearer sk-Owk...7HMm" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm-5.1",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

🐍 Python Example

from openai import OpenAI

client = OpenAI(
    api_key="sk-Owk...7HMm",
    base_url="https://opencode.ai/zen/go/v1"
)

response = client.chat.completions.create(
    model="glm-5.1",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

⚠️ Pitfalls & Notes

✅

Best Value — At $10/mo flat for 15 models with no rate limits, OpenCode is the best per-dollar provider. Particularly strong for GLM and MiniMax models.

💡

GLM-5 Champion — OpenCode is the best provider for GLM-5.1 at 73 tok/s, beating all other providers for this model family.

🏷️ Categories

Chat Coding Vision OCR