Model rankings

Compare model usage and performance from all Kyma API traffic, including Kyma's own accounts.

Live data4.4B tokens across 100 models from 3,581 developers

100 models = has at least one request in the window; 102 models = full live catalog.

#	Model	Tokens	Speed	Uptime
1	deepseek-v4-flashby DeepSeek	1.2B	28tok/s	100%
2	qwen-3.6-plusby Alibaba	550.0M	51tok/s	99%
3	gemma-4-31bby Google	395.1M	5tok/s	100%
4	deepseek-v4.1-flashby DeepSeek	308.0M	59tok/s	100%
5	deepseek-v3by DeepSeek	183.4M		93%
6	gpt-oss-120bby OpenAI	131.7M	56tok/s	99%
7	minimax-m2.7by MiniMax	119.8M	34tok/s	100%
8	minimax-m2.5by MiniMax	105.7M	62tok/s	98%
9	gemini-3-flashby Google	97.6M	69tok/s	99%
10	qwen-3-coderby Alibaba	95.8M	8tok/s	100%
11	gemini-3.7-flashby Google	83.2M	92tok/s	96%
12	glm-5.3-flashby Zhipu AI	82.3M	45tok/s	100%
13	llama-3.3-70bby Meta	74.9M	7tok/s	90%
14	qwen3.7-flashby Alibaba	61.2M	96tok/s	96%
15	glm-4.7-flashby Zhipu AI	53.5M	30tok/s	98%
16	gpt-5.6-lunaby OpenAI	53.4M	80tok/s	97%
17	qwen-3.8-maxby Alibaba	45.2M		100%
18	kimi-k3by Moonshot	45.1M	49tok/s	96%
19	gemini-3.5-flashby Google	44.9M	79tok/s	100%
20	qwen3.8-flashby Alibaba	42.1M	42tok/s	92%
21	qwen-3-32bby Alibaba	38.4M		77%
22	glm-5.3by Zhipu AI	29.5M		99%
23	minimax-m3by MiniMax	27.0M	20tok/s	100%
24	deepseek-v4-flash-vision-expby DeepSeek	26.8M	34tok/s	97%
25	deepseek-r1by DeepSeek	23.5M	17tok/s	100%
26	glm-4.5-airby Zhipu AI	15.5M	38tok/s	100%
27	muse-spark-1.2by Meta	15.0M		96%
28	glm-5.1by Zhipu AI	15.0M		93%
29	gemini-3.5-flash-liteby Google	13.5M	13tok/s	100%
30	kimi-k2.6by Moonshot	12.7M		97%
31	gpt-5.6-solby OpenAI	12.7M	39tok/s	96%
32	gpt-5.6-luna-proby OpenAI	12.5M	63tok/s	87%
33	glm-5.2by Zhipu AI	11.3M	46tok/s	100%
34	qwen3.8-27bby Alibaba	10.0M	51tok/s	96%
35	gemini-3.6-flashby Google	8.9M	9tok/s	95%
36	grok-4.20-multi-agentby xAI	6.2M		91%
37	qwen-3.7-maxby Alibaba	5.8M	102tok/s	94%
38	claude-fable-5by Anthropic	5.7M		88%
39	grok-4.3by xAI	4.5M		93%
40	qwen-3.7-plusby Alibaba	3.9M		97%
41	gemini-3-flash-audioby Google	3.8M
42	claude-sonnet-5by Anthropic	3.7M	49tok/s	89%
43	gemini-3.8-flashby Google	3.6M	19tok/s	99%
44	kimi-k2.7-codeby Moonshot	3.1M		100%
45	gpt-5.6-terra-proby OpenAI	3.0M		91%
46	gpt-5.6-sol-proby OpenAI	2.6M		91%
47	claude-haiku-4-5by Anthropic	1.5M	75tok/s	99%
48	step-3.7-flashby StepFun	1.3M	62tok/s	100%
49	grok-buildby xAI	1.2M		91%
50	claude-opus-5by Anthropic	1.2M		85%
51	claude-fable-5.1by Anthropic	942.2K		77%
52	claude-sonnet-4-6by Anthropic	927.0K	37tok/s	96%
53	gpt-5.6-terraby OpenAI	840.3K		85%
54	sonarby Perplexity	743.5K		96%
55	whisper-v3-turboby OpenAI	677.3K		99%
56	nemotron-3-ultra-550bby NVIDIA	563.8K		100%
57	grok-4.5by xAI	486.1K	31tok/s	96%
58	grok-4.6by xAI	344.0K		91%
59	muse-spark-1.1by Meta	315.3K		87%
60	llama-4-maverickby Meta	295.1K	41tok/s	100%
61	mimo-v2.5by Xiaomi	232.2K	34tok/s	98%
62	grok-4.20by xAI	211.2K		91%
63	gemini-3.1-proby Google	210.8K		100%
64	grok-4.7by xAI	185.0K		100%
65	claude-opus-4-7by Anthropic	171.2K		91%
66	qwen3-embedding-8bby Alibaba	149.7K		100%
67	gpt-6-astraby OpenAI	136.1K		41%
68	hy3by Tencent	126.7K		95%
69	ideogram-v3by Ideogram	111.8K
70	flux-kontext-proby Black Forest Labs	104.1K
71	hermes-3-70bby Nous Research	88.4K		100%
72	bge-m3by BAAI	72.8K		100%
73	muse-glimmer-30bby Meta	69.6K		96%
74	multilingual-e5-largeby Microsoft	65.2K		100%
75	sonar-proby Perplexity	59.5K		94%
76	hermes-3-405bby Nous Research	56.1K		100%
77	jevby TypeSafe	55.5K		100%
78	embeddinggemma-300mby Google	52.9K		100%
79	gte-baseby Alibaba	51.3K		100%
80	bge-large-enby BAAI	50.7K		100%
81	bge-base-enby BAAI	50.7K		100%
82	qwen3-embedding-0.6bby Alibaba	50.6K		100%
83	qwen3-embedding-4bby Alibaba	50.6K		100%
84	all-minilm-l6by Sentence Transformers	33.1K		100%
85	gpt-4o-mini-transcribe-2025-12-15by OpenAI	18.9K		100%
86	all-minilm-l12by Sentence Transformers	16.3K		100%
87	qwen3-reranker-8bby Alibaba	11.7K
88	muse-spark-1.3by Meta	2.0K
89	eleven-flash-v2-5by ElevenLabs	112
90	flux-2-proby Black Forest Labs	56
91	minimax-speech-turboby MiniMax	56		85%
92	minimax-image-01by MiniMax	56		99%
93	recraft-v4by Recraft	56
94	recraft-v4-proby Recraft	56
95	recraft-v4-vectorby Recraft	56
96	eleven-multilingual-v2by ElevenLabs	56		100%
97	minimax-speech-hdby MiniMax	56		83%
98	eleven-turbo-v2-5by ElevenLabs	56
99	gpt-transcribeby OpenAI	0		100%
100	gemini-3.5-transcribeby Google	0		78%

Measured from real API traffic. Updated every 5 minutes. Read docs →