Skip to content

Latest commit

 

History

History
111 lines (84 loc) · 6.25 KB

MODELS.md

File metadata and controls

111 lines (84 loc) · 6.25 KB

Model settings and comparison

Change defaults and order · Compare models · All models and source details

Compare models below before setting up U-M GPT. Once your umgpt or umgpt-low identity exists, use the steps here to change its saved default and picker order.

Change defaults and order

Run these commands from the repository directory, after creating the identity you want to update. The helper skips either standard identity that does not exist.

1. Find your settings file.

./bin/codex-home model-settings

Open the path printed after Edit your settings:, normally ~/.codex-homes/umgpt-models.toml. Your choices survive repository updates.

2. Choose your defaults and favorites.

umgpt = "gpt-6-luna"
umgpt_low = "gpt-6-luna"

umgpt_order = ["gpt-6.1-sol", "gpt-6-sol", "gpt-6-astra"]
umgpt_low_order = ["claude-sonnet-5", "gemini-3.8-flash", "claude-haiku-4-5"]

The first two lines select defaults; the arrays put your other favorites in order. Keep each array on one line. Use [] for automatic ordering. Find exact IDs in the available model list.

The picker shows your default → your favorites → remaining models by family, newer versions first. Sorting never changes your default. The example above starts the low picker with Luna → Sonnet → Gemini → Haiku.

3. Apply, reload, and check.

./bin/codex-home apply-model-settings

Restart the CLI, or run Developer: Reload Window in VS Code and start a new Codex chat. Check your choices in the model picker. Run model-settings again to compare saved and active defaults.

Changes not showing? · Reset or use a model for one session

Compare models

16 November 2026 · USD per million tokens. Prices are U-M Toolkit standard estimates. Scores use Artificial Analysis Intelligence Index v5.0.1; higher is better. Price conditions, evaluator settings, and sources.

This shortlist covers 18 currently advertised text models. Eleven have a verified score for the displayed effort; missing scores remain blank rather than borrowing a result from another index version or model revision.

Model Evaluated effort Index U-M input U-M output Tokens/s¹
GPT-6 Luna Medium 18 $0.10 $0.50 95
GPT-6 Sol Medium — $2.00 $10.00 —
GPT-6 Astra Medium 52 $10.00 $50.00 44
GPT-6.1 Sol Medium 46 $2.00 $10.00 52
Claude Haiku 4.5 Reasoning 7 $1.00 $5.00 116
Claude Haiku 5.5 Medium 25 $0.10 $0.50 221
Claude Sonnet 5 Medium — $2.20 $11.00 102
Claude Sonnet 5.5 Medium† 31 $2.00 $10.00 128
Claude Opus 5.5 Medium† 48 $4.40 $22.00 107
Claude Fable 5.1 Medium† 43 $11.00 $55.00 87
Claude Fable 5.2 Medium† 56 $8.80 $44.00 104
Gemini 3.8 Flash Medium 30 $0.75 $3.75 118
Grok 4.6 Xhigh 31 $1.25 $6.00 71
DeepSeek V4 Flash 0731 Max — $0.19 $0.51 141
DeepSeek V4.1 Flash Revision unverified — $0.30 $1.20 —
DeepSeek V4 Pro Revision unverified — $1.74 $3.48 —
Kimi K3 Max — $3.00 $15.00 48
Kimi K2.5 Reasoning — $0.60 $3.00 43

† Evaluator's default fallback configuration. ¹ External end-to-end output speed, including time to first token; not measured through U-M. “—” means no verified comparable value. Efforts differ where shown; these are not settings the helper applies. Detailed qualifications.

Rates depend on context/cache and can change. Haiku 5.5's provider has a higher-price tier above 100K input tokens; GPT-6.1 Sol's provider has a tier above 272K. Provider conditions versus U-M estimates. Token prices do not determine cost per completed task.

Luna remains the repository default for both identities. Compare models on your own tasks and verify the selected route before use; a listed ID and an external benchmark do not establish Codex tool-call compatibility.

Intelligence Index v5.0.1 versus U-M standard input and output token estimates for eleven models with verified scores. Green diamonds identify Luna, the repository default. Seven models with unavailable or unresolved scores are omitted.

Higher and further left indicates a higher benchmark score at a lower token price. No uncertainty intervals are supplied; small score gaps may not be meaningful. Full-size chart · Editable SVG · Current data and sources (CSV)

The September 2026 comparison, its provider prices, and v4.3.2 scores are archived separately. The two index versions are not directly comparable.

Back to README · U-M GPT setup