Effective public catalog

Model rankings

Deterministic views of RouteShift's effective public model catalog. These tables rank catalog facts, not adoption or traffic estimates.

Method. Prices sort ascending; context and sourced capability indices sort descending. Ties use provider, then model ID.

Source. RouteShift curated registry plus the generated LiteLLM supplement. Generated .

Cheapest input

Positive catalog input prices, lowest cost per million tokens first. Zero or unavailable prices are omitted.

Cheapest input model ranking
RankModelProviderInput priceRouting
1text-embedding-3-smallOpenAI$0.02 / 1MExplicit only
2text-embedding-004Google$0.025 / 1MExplicit only
3gemma-7b-itGroq$0.05 / 1MExplicit only
4llama-3.1-8b-instantGroq$0.05 / 1MExplicit only
5gpt-5-nanoOpenAI$0.05 / 1MExplicit only
6gpt-5-nano-2025-08-07OpenAI$0.05 / 1MExplicit only
7qwen-turboQwen$0.05 / 1MExplicit only
8qwen-turbo-2024-11-01Qwen$0.05 / 1MExplicit only
9qwen-turbo-2025-04-28Qwen$0.05 / 1MExplicit only
10qwen-turbo-latestQwen$0.05 / 1MExplicit only

Cheapest output

Positive catalog output prices, lowest cost per million tokens first. Embeddings, zero prices, and unavailable prices are omitted.

Cheapest output model ranking
RankModelProviderOutput priceRouting
1gemma-7b-itGroq$0.08 / 1MExplicit only
2llama-3.1-8b-instantGroq$0.08 / 1MExplicit only
3glm-4-32b-0414-128kZ.ai$0.10 / 1MExplicit only
4qwen-turboQwen$0.20 / 1MExplicit only
5qwen-turbo-2024-11-01Qwen$0.20 / 1MExplicit only
6qwen-turbo-2025-04-28Qwen$0.20 / 1MExplicit only
7qwen-turbo-latestQwen$0.20 / 1MExplicit only
8glm-4.5-airZ.ai$0.20 / 1MAuto or explicit
9gpt-oss-20bOpenAI$0.25 / 1MAuto or explicit
10together-ai-8.1b-21bTogether$0.30 / 1MExplicit only

Largest context

Published catalog context windows, highest token count first.

Largest context model ranking
RankModelProviderContext windowRouting
1gpt-5.4-2026-03-05OpenAI1,050,000 tokensExplicit only
2gpt-5.5-2026-04-23OpenAI1,050,000 tokensExplicit only
3gpt-5.6OpenAI1,050,000 tokensExplicit only
4gpt-5.6-lunaOpenAI1,050,000 tokensExplicit only
5gpt-5.6-terraOpenAI1,050,000 tokensExplicit only
6@cf/zai-org/glm-5.3-flashCloudflare Workers AI1,048,576 tokensAuto or explicit
7gemini-2.0-flash-001Google1,048,576 tokensExplicit only
8gemini-2.5-flash-liteGoogle1,048,576 tokensExplicit only
9gemini-3-pro-previewGoogle1,048,576 tokensExplicit only
10gemini-3.5-flash-liteGoogle1,048,576 tokensExplicit only