Current writer default: v4 (requires opentine 0.26+). Legacy v1/v2 files and v3 repositories remain readable. Bare tine migrate now writes a sibling file; use --dry-run for preview only. Read upgrade notes.

v0.34 model catalog

The v0.34 release refreshes the signed catalog from 231 to 248 cards, checked by the project against provider pricing pages on 2026-11-03. Added cards are not necessarily newly launched models, and this snapshot is not a live provider-price guarantee.

Terminal

tine pricing check
tine pricing show openai gpt-6.1-terra
tine pricing list --provider mistral
tine price run.tine --json

Added model coverage

OpenAI: gpt-6.1-terra, gpt-5.5-pro, gpt-5.4-pro, gpt-5.2-pro, gpt-5-pro, gpt-4.1, gpt-4.1-mini, gpt-4o-mini, o3, and o3-pro.
Google: gemini-2.5-flash and gemini-2.5-flash-lite, including recorded audio dimensions.
xAI: grok-4.20-0309-non-reasoning and grok-4.20-multi-agent-0309.
Mistral-hosted: zai-glm-5-3-flash and deepseek-v4-flash-1017. These cards do not establish direct Z.AI or DeepSeek endpoint rates.

Effective dates are part of the evidence

Where launch dates are not published, new cards begin on 2026-11-03. Earlier runs remain cost-unknown rather than being assigned current prices. Mistral Large 4's new rate starts on that date because the actual change date is unpublished; runs dated 2026-10-21 through 2026-11-02 report unknown cost for that gap.

Long-context multipliers and model-specific dimensions still matter. The snapshot marks gemini-2.5-flash deprecated and records scheduled routing to gemini-3.5-flash-lite from 2026-12-01; that catalog entry is not an availability promise. Prefer installed card inspection over copying a single headline token price.

Model support, endpoint availability, catalog coverage, and known usage are separate questions. Missing rates or usage remain explicit unknown/partial results. See pricing semantics and the tagged release snapshot.