LLM Pricing
PricingLeaderboardsToolsProvidersReleasesGuides

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list
op

MiniCPM5-2B

openbmb·openbmb/minicpm5-2b·GA·Open weights·NEW
Dense 2B-class open-source model for on-device and resource-constrained use, with native long-context support, tool calling, and agentic tasks

MiniCPM5-2B by openbmb is currently listed from a single provider. Its reference price is $0.124 per 1M input tokens and $0.743 per 1M output tokens.

Artificial Analysis rates it 12.5 on the Intelligence Index, with 14.5 for coding and 6.7 for agentic tasks. Against its lowest blended price of $0.279 per 1M, that is roughly 45 index points per dollar, which is the value ratio the leaderboards rank on.

The context window is 131,072 tokens, with an output limit of 131,072 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.

Specs & pricing

Input / output per 1M tokens
Reference price·AMD
$0.124 / $0.743
Blended $0.279 · Cache read $0.124
Lowest paid·AMDCloud
$0.124 / $0.743
Blended $0.279
Context
131,072
Output limit
131,072
Knowledge cutoff
—
Released / updated
2026-09-06 / 2026-09-12
Capabilities
✓ Reasoning✓ Tool use? Structured output✓ TemperatureAttachments
Modalities
Text
License
Apache-2.0
Weights
Hugging Face

Quality & performanceArtificial Analysis · Intelligence Index v4.3

Intelligence12.5
Value45
Coding14.5
Agentic6.7
Output speed—
TTFT—
Value formulaIQ 12.5 ÷ min blended $0.279 = 45

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

Available at 1 providers1 with public prices

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
AMD
MiniCPM5-2B
Cloud$0.124$0.743$0.124—131,072131,072

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

Upstream provides no control info

1 / 1 providers expose no reasoning control (reasoning_options: []).

Your usage cost

1AMD$61.93
The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input list $0.124Output list $0.743Min blended $0.279

Price history accumulates from each data sync; currently only 1 sample(s) (2026-09-15). Each future sync adds a point, and once accumulated a line is drawn here.

Artificial Analysis evaluations6 items

GPQA Diamond70.2%
Humanity's Last Exam8.9%
SciCode26.3%
Terminal-Bench 2.18.6%
τ³-Bench Banking20.8%
AA-LCR59.3%

Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and harness, so rows are not comparable with one another. The Intelligence Index above draws on a different, newer set of evaluations.

Related models

GPT-5 Nanocheaper alternative$0.05 / $0.40Hy3cheaper alternative$0 / $0Step 3.5 Flashcheaper alternative$0.10 / $0.30Nemotron 3.5 Lightning 30B A3Bcheaper alternative$0 / $0
Data partly from models.dev (MIT) · AMD official docs ↗