ai.canshu.com
中文
VRAM Calculator Advisor & TCO API Pricing Compare Models Leaderboard GPUs

Search models, GPUs, and tools

↑↓ Navigate · Enter Open · ★ Watchlist prioritized ai.canshu.com
Cohere
Open-Weight Cohere · north-small-translate-09-2026 · Text

North Small Translate Official Specifications, Pricing & Benchmarks

North Small Translate (north-small-translate-09-2026) by Cohere, released 2026-09-09, featuring 32,768 context window, 16,000 max output tokens, and Text input.

📋 North Small Translate Official API & System Card Specifications

Verified against official Cohere developer documentation & pricing

API Model ID: north-small-translate-09-2026

1. Identity & Capabilities

API Spec
API Model ID
north-small-translate-09-2026
Release Date
2026-09-09
Weight License
Open-Weight (API Spec)
Native Reasoning
—
Function Calling & JSON Schema
部分支持
Batch API 异步批处理
✅ Supported (50% off)

2. Context, Output & Modalities

Limits
Max Context Window
33,000 tokens (33K)
Max Output Tokens
16,000 tokens
Input Modalities
Text
Output Modalities
Text
Direct China Access
🌐 Global / OpenRouter
Deployment Mode
Open-Weight + Cloud API

3. Official Pricing & Cache

USD / 1M
Input / 1M Tokens
$ 0
Cached Input / 1M
$ 0
Output / 1M Tokens
$ 0

🎛️ Official Sampling & Reasoning Parameters

Recommended generation settings & API parameter constraints

Standard Generation Config
temperature=0.7 top_p=0.95 max_tokens=16,000

Closest Self-Hostable Open-Weight Alternatives to North Small Translate

Open-weight models with full HuggingFace weights for private GPU / Mac deployment

Compare with these →

Frequently Asked Questions

Is North Small Translate open-source or proprietary?

North Small Translate (north-small-translate-09-2026) is a proprietary commercial model by Cohere. Weights and internal layer dimensions are undisclosed; it is accessed via cloud API.

What are the context limit and API pricing of North Small Translate?

North Small Translate supports 33K input context and 16,000 max output tokens, priced at $0/1M input ($0/1M cached) and $0/1M output.