Skip to main content

​
Models & pricing

Prices are in USD per 1M tokens.

​
Gemma 4 31B

Model ID: gemma-4-31b

​
Standard pricing

WindowInputOutputCached input
Standard window$0.12$0.3790% off

​
Flex pricing

Gemma 4 31B Flex pricing is discounted from Standard pricing based on Pacific Time. Windows: weekday daytime (Mon-Fri, outside 12:00AM-6:00AM PT), weekday nighttime (Mon-Fri, 12:00AM-6:00AM PT), and weekend (Sat-Sun PT).
Flex windowDiscountEffective inputEffective outputCached input
Weekday daytime20% off$0.096$0.29690% off
Weekday nighttime35% off$0.078$0.240590% off
Weekend50% off$0.06$0.18590% off
Weekend pricing overrides the daytime and night discounts.

​
Standard window request

from openai import OpenAI

client = OpenAI(
    base_url="https://api.terminal.fyi/v1",
    api_key="TERMINAL_API_KEY",
)

response = client.chat.completions.create(
    model="gemma-4-31b",
    messages=[
        {
            "role": "user",
            "content": "Draft a concise changelog entry for improved cache hit rates.",
        }
    ],
    max_tokens=8000,
)

print(response.choices[0].message.content)

​
Flex window request

from openai import OpenAI

client = OpenAI(
    base_url="https://api.terminal.fyi/v1",
    api_key="TERMINAL_API_KEY",
    timeout=1800.0,
)

response = client.chat.completions.create(
    model="gemma-4-31b",
    service_tier="flex",
    messages=[
        {
            "role": "user",
            "content": "Summarize a nightly batch result for an ML platform team.",
        }
    ],
    max_tokens=8000,
)

print(response.choices[0].message.content)

​
MiniMax M3

Model ID: minimax-m3

​
Standard pricing

WindowInputOutputCached input
Standard window$0.30$1.2080% off

​
Flex pricing

MiniMax M3 Flex pricing is discounted from Standard pricing based on Pacific Time. Windows: weekday daytime (Mon-Fri, outside 12:00AM-6:00AM PT), weekday nighttime (Mon-Fri, 12:00AM-6:00AM PT), and weekend (Sat-Sun PT).
Flex windowDiscountEffective inputEffective output
Weekday daytime20% off$0.24$0.96
Weekday nighttime35% off$0.195$0.78
Weekend50% off$0.15$0.60
Weekend pricing overrides the daytime and night discounts.

​
Standard window request

from openai import OpenAI

client = OpenAI(
    base_url="https://api.terminal.fyi/v1",
    api_key="TERMINAL_API_KEY",
)

response = client.chat.completions.create(
    model="minimax-m3",
    messages=[
        {
            "role": "user",
            "content": "Write a compact implementation plan for adding workspace search.",
        }
    ],
    max_tokens=8000,
)

print(response.choices[0].message.content)

​
Flex window request

from openai import OpenAI

client = OpenAI(
    base_url="https://api.terminal.fyi/v1",
    api_key="TERMINAL_API_KEY",
    timeout=1800.0,
)

response = client.chat.completions.create(
    model="minimax-m3",
    service_tier="flex",
    messages=[
        {
            "role": "user",
            "content": "Turn these benchmark notes into three prioritized next steps.",
        }
    ],
    max_tokens=8000,
)

print(response.choices[0].message.content)

​
Request-only models

The following models are request-only. Email shubham@terminal.fyi with the model name, expected token volume, and whether you need Standard, Flex, or both.
ModelStatus
GLM 5.2Request only
DeepSeek V4 ProRequest only
Kimi K2.6Request only
DeepSeek V4 FlashRequest only
NVIDIA Nemotron 3 UltraRequest only

​
API keys

To request access, email shubham@terminal.fyi.