Cohere's compact coding model for fast code generation, code editing, and agentic coding prompts. It supports a 256K-token input context, up to 64K output tokens, and configurable thinking.
Added Jun 18, 2026
Model weightsContext Window
256.0K
Max Output
64.0K
Input Price (Auto)
$0.20/1M
Output Price (Auto)
$0.80/1M
Cache Read (Auto)
$0.10/1M
Capabilities
Benchmarks
Benchmarks
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
20.6
Reasoning
GPQA Diamond
Graduate-level scientific reasoning
75.7%
Better than 66% of models compared
HLE
Humanity's Last Exam
9.9%
Better than 65% of models compared
IFBench
Instruction-following benchmark
57.6%
Better than 70% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
37.4%
Better than 47% of models compared
AA-LCR
Long context reasoning evaluation
32.3%
Better than 47% of models compared
Coding
SciCode
Python programming for scientific computing
38.2%
Better than 69% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
31.1%
Better than 75% of models compared
Last updated Jun 28, 2026
Artificial AnalysisProviders
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Related text models
Compare Cohere North Mini Code 1.0 with similar models from the same provider or model family.
Cohere: Command R+
cohere/command-r-plus-08-2024104B parameter model that performs conversational language tasks at a higher quality, more reliably, and with a longer context than previous models. It can be used for complex workflows like code generation, retrieval augmented generation (RAG), tool use, and agents
Cohere Command A+ (05/2026)
command-a-plus-05-2026Cohere's open-weight Command A+ model for complex agentic, multimodal, multilingual, and reasoning tasks. It is a 218B total parameter sparse MoE model with 25B active parameters, supports text and image inputs, structured outputs, and 48 languages.
Cohere Command A (08/2025)
command-a-reasoning-08-2025Cohere's first reasoning model designed for enterprise customer service and automation. 111B parameters with tool-use capabilities, supports 256K context and 23 languages including English, French, Spanish, Japanese, Arabic, and Hindi. Optimized for document processing, scheduling, data analysis, and more.
Kimi K2.7 Code TEE
TEE/kimi-k2.7-codeKimi K2.7 Code is Moonshot AI's coding-focused agentic model built for long-horizon software engineering workflows. It supports native image input, tool calling, and forced thinking mode while running inside a Trusted Execution Environment (TEE) with attestation support.
ByteDance Seed 2.0 Code
bytedance-seed/seed-2.0-codeByteDance Seed 2.0 Code is a multimodal model optimized for agentic coding, frontend development, multilingual programming, long-running tool workflows, and coding agents. It supports image and video input, a 262k context window, and up to 131k output tokens.
AionLabs: Aion 3.0 Mini
aion-labs/aion-3.0-miniAion 3.0 Mini is a DeepSeek-family collaborative generation model tuned for immersive roleplay and storytelling, with stronger narrative structure, tension, conflict, and nuanced mature themes.