Model rankings

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

Live data4.4B tokens across 101 models from 3,616 developers

101 models = has at least one request in the window; 106 models = full live catalog.

#	Model	Tokens	Speed	Uptime
1	deepseek-v4-flashby DeepSeek	1.2B	33tok/s	100%
2	qwen-3.6-plusby Alibaba	550.5M	50tok/s	100%
3	gemma-4-31bby Google	395.5M	15tok/s	100%
4	deepseek-v4.1-flashby DeepSeek	319.8M	52tok/s	100%
5	deepseek-v3by DeepSeek	183.4M		98%
6	gpt-oss-120bby OpenAI	131.7M	56tok/s	98%
7	minimax-m2.7by MiniMax	119.8M	13tok/s	100%
8	minimax-m2.5by MiniMax	102.7M	58tok/s	98%
9	gemini-3-flashby Google	97.6M	103tok/s	99%
10	qwen-3-coderby Alibaba	95.8M	5tok/s	100%
11	glm-5.3-flashby Zhipu AI	89.6M	31tok/s	100%
12	gemini-3.7-flashby Google	83.3M	89tok/s	99%
13	llama-3.3-70bby Meta	74.9M	10tok/s	88%
14	qwen3.7-flashby Alibaba	61.2M	90tok/s	97%
15	gpt-5.6-lunaby OpenAI	53.7M	66tok/s	98%
16	glm-4.7-flashby Zhipu AI	53.5M	9tok/s	100%
17	kimi-k3by Moonshot	45.4M	52tok/s	99%
18	qwen-3.8-maxby Alibaba	45.2M		100%
19	gemini-3.5-flashby Google	45.0M	100tok/s	97%
20	qwen3.8-flashby Alibaba	42.1M	9tok/s	92%
21	qwen-3-32bby Alibaba	38.4M	13tok/s	72%
22	glm-5.3by Zhipu AI	29.5M		100%
23	minimax-m3by MiniMax	27.0M	8tok/s	100%
24	deepseek-v4-flash-vision-expby DeepSeek	26.8M	14tok/s	97%
25	deepseek-r1by DeepSeek	23.5M	17tok/s	100%
26	glm-4.5-airby Zhipu AI	15.5M	19tok/s	100%
27	muse-spark-1.2by Meta	15.0M		100%
28	glm-5.1by Zhipu AI	15.0M
29	gemini-3.5-flash-liteby Google	13.7M	222tok/s	99%
30	gpt-5.6-solby OpenAI	13.3M	36tok/s	97%
31	kimi-k2.6by Moonshot	12.7M		100%
32	gpt-5.6-luna-proby OpenAI	12.6M	22tok/s	86%
33	glm-5.2by Zhipu AI	11.3M	55tok/s	100%
34	qwen3.8-27bby Alibaba	10.0M	18tok/s	99%
35	gemini-3.6-flashby Google	8.9M		88%
36	grok-4.20-multi-agentby xAI	6.2M
37	qwen-3.7-maxby Alibaba	5.8M	102tok/s	100%
38	claude-fable-5by Anthropic	5.7M		100%
39	grok-4.3by xAI	4.5M
40	qwen-3.7-plusby Alibaba	4.0M	17tok/s	100%
41	claude-sonnet-5by Anthropic	3.7M	49tok/s	93%
42	gemini-3.8-flashby Google	3.6M	42tok/s	99%
43	kimi-k2.7-codeby Moonshot	3.1M
44	gpt-5.6-terra-proby OpenAI	3.0M
45	gpt-5.6-sol-proby OpenAI	2.6M
46	claude-haiku-4-5by Anthropic	1.6M	172tok/s	99%
47	step-3.7-flashby StepFun	1.3M	11tok/s	100%
48	grok-buildby xAI	1.2M
49	claude-opus-5by Anthropic	1.2M
50	claude-fable-5.1by Anthropic	942.2K		100%
51	claude-sonnet-4-6by Anthropic	932.3K	39tok/s	100%
52	gpt-5.6-terraby OpenAI	840.3K
53	sonarby Perplexity	743.5K		100%
54	whisper-v3-turboby OpenAI	677.3K		99%
55	nemotron-3-ultra-550bby NVIDIA	563.8K
56	grok-4.5by xAI	485.3K		100%
57	grok-4.6by xAI	344.0K
58	kling-3-proby Kuaishou	330.8K
59	muse-spark-1.1by Meta	315.3K
60	llama-4-maverickby Meta	297.8K	7tok/s	100%
61	mimo-v2.5by Xiaomi	232.2K		100%
62	grok-4.20by xAI	211.2K
63	gemini-3.1-proby Google	210.8K
64	grok-4.7by xAI	185.0K		100%
65	claude-opus-4-7by Anthropic	171.2K
66	qwen3-embedding-8bby Alibaba	150.3K		100%
67	gpt-6-astraby OpenAI	136.1K		41%
68	hy3by Tencent	127.9K	7tok/s	100%
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	muse-glimmer-30bby Meta	73.0K	27tok/s	100%
73	bge-m3by BAAI	72.8K		100%
74	multilingual-e5-largeby Microsoft	65.2K
75	sonar-proby Perplexity	59.5K
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
80	bge-large-enby BAAI	50.7K
81	bge-base-enby BAAI	50.7K
82	qwen3-embedding-0.6bby Alibaba	50.6K
83	qwen3-embedding-4bby Alibaba	50.6K
84	all-minilm-l6by Sentence Transformers	33.1K
85	gpt-4o-mini-transcribe-2025-12-15by OpenAI	18.9K		100%
86	all-minilm-l12by Sentence Transformers	16.3K
87	muse-spark-1.3by Meta	14.3K	91tok/s
88	qwen3-reranker-8bby Alibaba	11.7K
89	eleven-flash-v2-5by ElevenLabs	112
90	minimax-image-01by MiniMax	56		98%
91	minimax-speech-hdby MiniMax	56
92	minimax-speech-turboby MiniMax	56
93	recraft-v4by Recraft	56
94	eleven-turbo-v2-5by ElevenLabs	56
95	flux-2-proby Black Forest Labs	56
96	recraft-v4-vectorby Recraft	56
97	eleven-multilingual-v2by ElevenLabs	56		100%
98	recraft-v4-proby Recraft	56
99	lyria-3.5by Google	0
100	gemini-3.5-transcribeby Google	0		93%
101	gpt-transcribeby OpenAI	0		100%

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