LLM model rankings
Two rankings that do not depend on each other. The first counts real usage — what developers building on uttapen actually send to the API. The second is a value score that puts the toman price, the capabilities and the context window on one scale. Usage figures refresh every half hour.
Most used models, last 30 days
Each model's share of all the tokens uttapen users processed in the last 30 days. The 7-day column shows what is climbing.
| # | Model | Share of usage | 7-day rank | Output / 1M tokens (toman) |
|---|---|---|---|---|
| 1 | 1 Gemini 3.8 Flashgoogle/gemini-3.8-flash | 47% | — | 1,298,323 |
| 2 | 2Gemini 2.5 Flash Litegoogle/gemini-2.5-flash-lite | 28% | 2 | 138,488 |
| 3 | 3Gemini 3.1 Flash Litegoogle/gemini-3.1-flash-lite | 5.4% | 1 | 519,329 |
| 4 | 4Claude Sonnet 5anthropic/claude-sonnet-5 | 4.4% | — | 3,462,194 |
| 5 | 5Text Embedding 3 Smallopenai/text-embedding-3-small | 3.9% | 3 | — |
| 6 | 6Gemini 2.5 Flashgoogle/gemini-2.5-flash | 3.9% | — | 865,548 |
| 7 | 7Claude Haiku 5.5anthropic/claude-haiku-5.5 | 2.9% | — | 173,110 |
| 8 | 8 DeepSeek V4.1 Flashdeepseek/deepseek-v4.1-flash | 0.9% | — | 173,110 |
| 9 | 9Nano Banana 2 (Gemini 3.1 Flash Image)google/gemini-3.1-flash-image | 0.7% | — | 1,038,658 |
| 10 | 10GPT-4o-miniopenai/gpt-4o-mini | 0.6% | 4 | 207,732 |
Best value models
Score out of 100, from three things only: 50% cheapness (the toman cost of one 1,000-word request), 30% capabilities (tools, vision, reasoning, json, files) and 20% context size. The weights never change, so the same model scores the same way twice. It is not a quality benchmark.
| # | Model | Capabilities | Context (tokens) | ≈ 1,000 words (toman) | Score |
|---|---|---|---|---|---|
| 1 | 1GLM Flash Latest | Image input · Tool calling +2 | 1,048,576 | 54 | 85.7 |
| 2 | 2 Qwen3.7 Flash | Image input · Tool calling +2 | 1,000,000 | 72 | 82.5 |
| 3 | 3Ling 3.0 Tiny | Tool calling · Reasoning +1 | 262,144 | 27 | 82.4 |
| 4 | 4GPT-6 Luna Pro (batch) | Image input · Tool calling +3 | 1,050,000 | 135 | 81.8 |
| 5 | 5GPT-6 Luna (batch) | Image input · Tool calling +3 | 1,050,000 | 135 | 81.8 |
| 6 | 6Claude Haiku 5.5 (batch) | Image input · Tool calling +3 | 1,000,000 | 135 | 81.6 |
| 7 | 7GPT-5 Nano (batch) | Image input · Tool calling +3 | 400,000 | 101 | 81.6 |
| 8 | 8Extract | Image input · File input | 1,000,000 | 18 | 81.1 |
| 9 | 9Summarize | Image input · File input | 1,000,000 | 18 | 81.1 |
| 10 | 10Ling 3.0 Flash | Tool calling · Reasoning +1 | 262,144 | 38 | 78.7 |
| 11 | 11GLM 5.3 Flash (batch) | Image input · Tool calling +2 | 1,048,576 | 104 | 78.6 |
| 12 | 12Gemini 2.5 Flash Lite | Image input · Tool calling +4 | 1,048,576 | 225 | 76.2 |
| 13 | 13Ternary Bonsai 2 9B | Image input · Tool calling +2 | 262,144 | 95 | 74.8 |
| 14 | 14Qwen3.5-Flash | Image input · Tool calling +2 | 1,000,000 | 146 | 74.8 |
| 15 | 15Nex-N2.5-Mini | Image input · Reasoning +1 | 262,144 | 56 | 74.5 |
| 16 | 16GPT-6 Luna | Image input · Tool calling +3 | 1,050,000 | 270 | 74.3 |
| 17 | 17GPT-6 Luna Pro | Image input · Tool calling +3 | 1,050,000 | 270 | 74.3 |
| 18 | 18GPT Luna Latest | Image input · Tool calling +3 | 1,050,000 | 270 | 74.3 |
| 19 | 19Claude Haiku 5.5 | Image input · Tool calling +3 | 1,000,000 | 270 | 74.1 |
| 20 | 20Claude Haiku Latest | Image input · Tool calling +3 | 1,000,000 | 270 | 74.1 |
Most used providers, last 30 days
Usage figures are aggregated and anonymous; no request content is ever stored or published (privacy).