LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

North Mini Code

cohere·cohere/north-mini-code-1-0·GA·Open weights·north series
Cohere coding model for practical software engineering and agentic edits

Specs & pricing

Input / output per 1M tokens
Official price·Cohere
$0 / $0
Blended $0 · Cache read —
Lowest paid
No paid channels
2 more $0 channels
Context
256,000
Output limit
64,000
Knowledge cutoff
2025-09-23
Released / updated
2026-06-09 / 2026-06-09
Capabilities
✓ Reasoning✓ Tool useStructured output✓ TemperatureAttachments
Modalities
Text

North Mini Code by cohere is offered by 2 providers on this page. Its official list price is $0 per 1M tokens. It also has 2 free ($0) channels; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.

Artificial Analysis rates it 3.4 on the Intelligence Index, with 9.9 for Engineering, its strongest domain. Median output speed is 212 tokens per second, with 0.37s to the first token.

The context window is 256,000 tokens, with an output limit of 64,000 tokens. It supports reasoning and tool use. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Its training knowledge cuts off at 2025-09-23.

Quality & performanceArtificial Analysis · Intelligence Index v5

Intelligence3.4
Value—
Engineering9.9
Finance & Accounting9.3
Legal7.9
Healthcare & Medical6.3
Strategy & Ops6.2
Economics9.9
Output speed212 tok/s
TTFT0.37 s

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 2 providers0 with public prices · 2 free

  • ProviderInput / Output
  • CohereOfficialFirst-party
    Free
    Context 256,000Output limit 64,000
  • OpenCodeGateway
    north-mini-code-free
    Free
    Context 256,000Output limit 64,000deprecated
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
CohereOfficialFirst-partyFree——256,00064,000
OpenCode
north-mini-code-free
GatewayFree——256,00064,000deprecated

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Reasoning control

effort = noneeffort = high

Interleaved thinking (reasoning between tool calls) is declared by 2 of 2 providers.

Your usage cost

Common scenarios

This model is $0 across all listed channels (Cohere, OpenCode).

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$0.0001$02026-08-052026-08-13
2026-08-13Input list $0Output list $0Min blended —

Benchmark6 items

NameConditionsScoreMetricSource
SWE-Bench Verifiedharness: SWE-agent67.6resolvedSource ↗
SWE-Bench Proharness: SWE-agent40.2resolve rateSource ↗
Artificial Analysis Intelligence Index—27.6index scoreSource ↗
Artificial Analysis Coding Index—33.4index scoreSource ↗
GDPval-AA—14win rateSource ↗
τ²-Bench Telecom—37success rateSource ↗

The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.

Artificial Analysis evaluations23 items

GPQA Diamond75.7%
Humanity's Last Exam11.1%
HLE-Diamond4.2%
CritPt0.3%
CritPt v2 Hard1.0%
SciCode38.8%
FrontierCode 2.00.2%
Terminal-Bench Hard31.1%
Terminal-Bench 2.135.6%
Terminal-Bench 4.00.5%
Terminal-Bench-Science0.0%
τ²-Bench Telecom37.4%
τ³-Bench Banking6.4%
AutomationBench-AA1.5%
AA-Briefcase212
GDPval-AA319
GDP.pdf1.8%
AA-LCR37.3%
MLCR-AA4.4%
IFBench57.6%
AA-Omniscience Index-49.8
AA-Omniscience Accuracy18.4%
AA-Omniscience Non-Hallucination16.5%

Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and scale (percent correct, points or an index), so rows are not comparable with one another.

Related models

North Small Translatesame series$0 / $0Command R7Bsame lab$0.038 / $0.15Command Asame lab—
Data partly from models.dev (MIT) · Cohere official docs ↗