Cheaper Inference / Model rankings

The most popular models on Cheaper Inference.

Ranked only when completed requests record token usage in the selected timeframe.

Leading models right now

Showing model rankings for the last 1 day.

#01Most used

deepseek-v4.1-flash

DeepSeek

Ranked from completed requests with recorded token usage.

View model

#02Runner-up

claude-sonnet-4.5

Anthropic

Ranked from completed requests with recorded token usage.

View model

#03Third place

gpt-6-luna

OpenAI

Ranked from completed requests with recorded token usage.

View model

Updated Oct 10, 2026, 2:30 AM UTC

RankModelProviderDetails

01deepseek-v4.1-flashDeepSeekDeepSeek

02claude-sonnet-4.5AnthropicAnthropic

03gpt-6-lunaOpenAIOpenAI

04glm-5.3-flashZ.aiZ.ai

05deepseek-v4-flash-0731DeepSeekDeepSeek

06deepseek-v4-flashDeepSeekDeepSeek

07gpt-5.6-lunaOpenAIOpenAI

08mimo-v2.6-proXiaomiXiaomi

09deepseek-v4-proDeepSeekDeepSeek

10claude-opus-5.5AnthropicAnthropic

11mimo-v2.6-flashXiaomiXiaomi

12glm-5.3Z.aiZ.ai

13claude-sonnet-5.5AnthropicAnthropic

14claude-opus-4.8AnthropicAnthropic

15gpt-5.6-solOpenAIOpenAI

16claude-sonnet-5AnthropicAnthropic

17deepseek-v4-pro-0813DeepSeekDeepSeek

18claude-sonnet-4.6AnthropicAnthropic

19claude-opus-4.6AnthropicAnthropic

20kimi-k3MoonshotMoonshot

21claude-opus-5AnthropicAnthropic

22qwen3.8-flashAlibabaAlibaba

23gemini-3.6-flashGoogleGoogle

24gpt-5.6-terraOpenAIOpenAI

25claude-opus-4.7AnthropicAnthropic

26gemini-3.1-flash-liteGoogleGoogle

27gemini-3.7-flashGoogleGoogle

28gemini-3.8-flashGoogleGoogle

29gpt-6.1-solOpenAIOpenAI

30grok-4.7SpaceXAISpaceXAI

31gpt-6-astraOpenAIOpenAI

32glm-5.2Z.aiZ.ai

33gpt-5.4-miniOpenAIOpenAI

34claude-fable-5.1AnthropicAnthropic

35gpt-oss-120bOpenAIOpenAI

36claude-fable-5AnthropicAnthropic

37aion-3.0Aion LabsAion Labs

38gpt-5.4OpenAIOpenAI

39claude-haiku-4.5AnthropicAnthropic

40gemini-3.5-flash-liteGoogleGoogle

41gpt-5-miniOpenAIOpenAI

42qwen3.8-maxAlibabaAlibaba

43qwen3.8-27bAlibabaAlibaba

44gpt-4.1-nanoOpenAIOpenAI

45gemini-3.5-flashGoogleGoogle

46gemini-2.5-flashGoogleGoogle

47grok-4.5xAIxAI

48gpt-5-nanoOpenAIOpenAI

49gemini-3.1-proGoogleGoogle

50minimax-m3MiniMaxMiniMax

51glm-5Z.aiZ.ai

52gpt-5.4-nanoOpenAIOpenAI

53nano-banana-2GoogleGoogle

54kimi-k2-thinkingMoonshotMoonshot

55glm-5.1Z.aiZ.ai

56grok-4.3xAIxAI

57gpt-6-solOpenAIOpenAI

58glm-5.3-primeZ.aiZ.ai

59kimi-k2.5MoonshotMoonshot

60glm-4.6Z.aiZ.ai

61qwen3.6-35b-a3bAlibabaAlibaba

62glm-4.7Z.aiZ.ai

63qwen3-vl-235b-a22b-instructAlibabaAlibaba

64gemini-3-flashGoogleGoogle

65minimax-m2.7MiniMaxMiniMax

66qwen3-next-80b-a3b-instructAlibabaAlibaba

67minimax-m2.5MiniMaxMiniMax

68grok-4.6SpaceXAISpaceXAI

69gpt-5.5OpenAIOpenAI

70glm-4.5-airZ.aiZ.ai

71nano-banana-proGoogleGoogle

72gpt-image-2OpenAIOpenAI

73gemma-3-4b-itGoogleGoogle

74qwen3.6-27bAlibabaAlibaba

75glm-4.5Z.aiZ.ai

76claude-opus-4.5AnthropicAnthropic

77qwen3-coder-nextAlibabaAlibaba

78gemma-4-31b-itGoogleGoogle

79aion-3.0-miniAion LabsAion Labs

80glm-4.7-flashZ.aiZ.ai

81muse-spark-1.2MetaMeta

82qwen3-coder-30b-a3b-instructAlibabaAlibaba

83claude-opus-4.8-fastAnthropicAnthropic

84gpt-5.2-codexOpenAIOpenAI

85gemma-3-12b-itGoogleGoogle

86qwen3.8-2.4t-a95bAlibabaAlibaba

87qwen3-32bAlibabaAlibaba

88qwen3.5-35b-a3bAlibabaAlibaba

89claude-opus-5-fastAnthropicAnthropic

90gemma-3-27b-itGoogleGoogle

91gpt-5.5-proOpenAIOpenAI

92gemma-4-26b-a4b-itGoogleGoogle

93minimax-m2MiniMaxMiniMax

94minimax-m2.1MiniMaxMiniMax

Ready when you are

One API key. Multiple providers.

Access leading models from multiple providers through one OpenAI-compatible API.

Get API key Browse live rates

Cheaper Inference / Model rankings

The most popular models on Cheaper Inference.

Ranked only when completed requests record token usage in the selected timeframe.

Leading models right now

Showing model rankings for the last 1 day.

#01Most used

deepseek-v4.1-flash

DeepSeek

Ranked from completed requests with recorded token usage.

View model

#02Runner-up

claude-sonnet-4.5

Anthropic

Ranked from completed requests with recorded token usage.

View model

#03Third place

gpt-6-luna

OpenAI

Ranked from completed requests with recorded token usage.

View model

Updated Oct 10, 2026, 2:30 AM UTC

RankModelProviderDetails

01deepseek-v4.1-flashDeepSeekDeepSeek

02claude-sonnet-4.5AnthropicAnthropic

03gpt-6-lunaOpenAIOpenAI

04glm-5.3-flashZ.aiZ.ai

05deepseek-v4-flash-0731DeepSeekDeepSeek

06deepseek-v4-flashDeepSeekDeepSeek

07gpt-5.6-lunaOpenAIOpenAI

08mimo-v2.6-proXiaomiXiaomi

09deepseek-v4-proDeepSeekDeepSeek

10claude-opus-5.5AnthropicAnthropic

11mimo-v2.6-flashXiaomiXiaomi

12glm-5.3Z.aiZ.ai

13claude-sonnet-5.5AnthropicAnthropic

14claude-opus-4.8AnthropicAnthropic

15gpt-5.6-solOpenAIOpenAI

16claude-sonnet-5AnthropicAnthropic

17deepseek-v4-pro-0813DeepSeekDeepSeek

18claude-sonnet-4.6AnthropicAnthropic

19claude-opus-4.6AnthropicAnthropic

20kimi-k3MoonshotMoonshot

21claude-opus-5AnthropicAnthropic

22qwen3.8-flashAlibabaAlibaba

23gemini-3.6-flashGoogleGoogle

24gpt-5.6-terraOpenAIOpenAI

25claude-opus-4.7AnthropicAnthropic

26gemini-3.1-flash-liteGoogleGoogle

27gemini-3.7-flashGoogleGoogle

28gemini-3.8-flashGoogleGoogle

29gpt-6.1-solOpenAIOpenAI

30grok-4.7SpaceXAISpaceXAI

31gpt-6-astraOpenAIOpenAI

32glm-5.2Z.aiZ.ai

33gpt-5.4-miniOpenAIOpenAI

34claude-fable-5.1AnthropicAnthropic

35gpt-oss-120bOpenAIOpenAI

36claude-fable-5AnthropicAnthropic

37aion-3.0Aion LabsAion Labs

38gpt-5.4OpenAIOpenAI

39claude-haiku-4.5AnthropicAnthropic

40gemini-3.5-flash-liteGoogleGoogle

41gpt-5-miniOpenAIOpenAI

42qwen3.8-maxAlibabaAlibaba

43qwen3.8-27bAlibabaAlibaba

44gpt-4.1-nanoOpenAIOpenAI

45gemini-3.5-flashGoogleGoogle

46gemini-2.5-flashGoogleGoogle

47grok-4.5xAIxAI

48gpt-5-nanoOpenAIOpenAI

49gemini-3.1-proGoogleGoogle

50minimax-m3MiniMaxMiniMax

51glm-5Z.aiZ.ai

52gpt-5.4-nanoOpenAIOpenAI

53nano-banana-2GoogleGoogle

54kimi-k2-thinkingMoonshotMoonshot

55glm-5.1Z.aiZ.ai

56grok-4.3xAIxAI

57gpt-6-solOpenAIOpenAI

58glm-5.3-primeZ.aiZ.ai

59kimi-k2.5MoonshotMoonshot

60glm-4.6Z.aiZ.ai

61qwen3.6-35b-a3bAlibabaAlibaba

62glm-4.7Z.aiZ.ai

63qwen3-vl-235b-a22b-instructAlibabaAlibaba

64gemini-3-flashGoogleGoogle

65minimax-m2.7MiniMaxMiniMax

66qwen3-next-80b-a3b-instructAlibabaAlibaba

67minimax-m2.5MiniMaxMiniMax

68grok-4.6SpaceXAISpaceXAI

69gpt-5.5OpenAIOpenAI

70glm-4.5-airZ.aiZ.ai

71nano-banana-proGoogleGoogle

72gpt-image-2OpenAIOpenAI

73gemma-3-4b-itGoogleGoogle

74qwen3.6-27bAlibabaAlibaba

75glm-4.5Z.aiZ.ai

76claude-opus-4.5AnthropicAnthropic

77qwen3-coder-nextAlibabaAlibaba

78gemma-4-31b-itGoogleGoogle

79aion-3.0-miniAion LabsAion Labs

80glm-4.7-flashZ.aiZ.ai

81muse-spark-1.2MetaMeta

82qwen3-coder-30b-a3b-instructAlibabaAlibaba

83claude-opus-4.8-fastAnthropicAnthropic

84gpt-5.2-codexOpenAIOpenAI

85gemma-3-12b-itGoogleGoogle

86qwen3.8-2.4t-a95bAlibabaAlibaba

87qwen3-32bAlibabaAlibaba

88qwen3.5-35b-a3bAlibabaAlibaba

89claude-opus-5-fastAnthropicAnthropic

90gemma-3-27b-itGoogleGoogle

91gpt-5.5-proOpenAIOpenAI

92gemma-4-26b-a4b-itGoogleGoogle

93minimax-m2MiniMaxMiniMax

94minimax-m2.1MiniMaxMiniMax

Ready when you are

One API key. Multiple providers.

Access leading models from multiple providers through one OpenAI-compatible API.

Get API key Browse live rates