Cheaper Inference / Model rankings

The most popular models on Cheaper Inference.

Ranked by token volume from completed text requests.

Leading text models

Showing model rankings for the last 1 day.

#01Most used

deepseek-v4.1-flash-1017

DeepSeek

Ranked by token volume from completed text requests.

View model

#02Runner-up

deepseek-v4.1-flash

DeepSeek

Ranked by token volume from completed text requests.

View model

#03Third place

claude-sonnet-4.6

Anthropic

Ranked by token volume from completed text requests.

View model

Updated Nov 10, 2026, 12:04 AM UTC

RankModelProviderDetails

01deepseek-v4.1-flash-1017DeepSeekDeepSeek

02deepseek-v4.1-flashDeepSeekDeepSeek

03claude-sonnet-4.6AnthropicAnthropic

04claude-opus-4.6AnthropicAnthropic

05claude-opus-5.5AnthropicAnthropic

06glm-5.3-flashZ.aiZ.ai

07gpt-6-lunaOpenAIOpenAI

08gpt-6.1-solOpenAIOpenAI

09claude-sonnet-5.5AnthropicAnthropic

10deepseek-v4-flashDeepSeekDeepSeek

11claude-sonnet-4.5AnthropicAnthropic

12claude-sonnet-5AnthropicAnthropic

13nemotron-3.5-lightning-freenvidianvidia

14deepseek-v4.1-flash-1017-fastDeepSeekDeepSeek

15gemini-3.8-flashGoogleGoogle

16gpt-5.6-lunaOpenAIOpenAI

17glm-5.3Z.aiZ.ai

18deepseek-v4-flash-0731DeepSeekDeepSeek

19mimo-v2.6-flashXiaomiXiaomi

20deepseek-v4.1-flash-fastDeepSeekDeepSeek

21claude-opus-5AnthropicAnthropic

22deepseek-v4-pro-0813DeepSeekDeepSeek

23mimo-v2.6-proXiaomiXiaomi

24kimi-k3.1-proMoonshotAIMoonshotAI

25claude-opus-4.8AnthropicAnthropic

26deepseek-v4-proDeepSeekDeepSeek

27gemini-3.1-flash-liteGoogleGoogle

28grok-4.3xAIxAI

29gpt-5-miniOpenAIOpenAI

30gemini-4-argonGoogleGoogle

31beam-freereflectionreflection

32claude-fable-5.1AnthropicAnthropic

33claude-haiku-5.5AnthropicAnthropic

34kimi-k3MoonshotMoonshot

35muse-emberMetaMeta

36qwen3.8-flashAlibabaAlibaba

37gpt-6.1-terraOpenAIOpenAI

38kimi-k3.1-pro-highspeedMoonshot AIMoonshot AI

39gemini-3.7-flashGoogleGoogle

40minimax-m3.1-flashMiniMaxMiniMax

41gpt-5.6-terraOpenAIOpenAI

42glm-5.3-flashx-legalZ.aiZ.ai

43gemini-3.6-flashGoogleGoogle

44qwen3.8-27bAlibabaAlibaba

45gemini-3.1-pro-previewGoogleGoogle

46grok-4.7SpaceXAISpaceXAI

47deepseek-v4.1-flash-1017-ultrafastdeepseekdeepseek

48claude-haiku-4.5AnthropicAnthropic

49minimax-m3MiniMaxMiniMax

50mercury-2.5InceptionInception

51gemini-3.5-flash-liteGoogleGoogle

52gpt-5.4-nanoOpenAIOpenAI

53gpt-5.4-miniOpenAIOpenAI

54gpt-5.4OpenAIOpenAI

55minimax-m2.7MiniMaxMiniMax

56gpt-6-solOpenAIOpenAI

57qwen3.7-flashAlibabaAlibaba

58grok-4.5xAIxAI

59gpt-4.1-miniOpenAIOpenAI

60deepseek-v4-flash-vision-expDeepSeekDeepSeek

61gpt-5.6-solOpenAIOpenAI

62qwen3.8-maxAlibabaAlibaba

63gpt-4.1-nanoOpenAIOpenAI

64gemini-3.5-flashGoogleGoogle

65kimi-k2.7-codeMoonshotMoonshot

66gemini-3-flashGoogleGoogle

67grok-4.6SpaceXAISpaceXAI

68kimi-k2-thinkingMoonshotMoonshot

69gpt-5.6-luna-fastOpenAIOpenAI

70claude-fable-5.2AnthropicAnthropic

71gpt-oss-120bOpenAIOpenAI

72mercury-3InceptionInception

73gpt-5-nanoOpenAIOpenAI

74beamReflection AIReflection AI

75glm-5.1Z.aiZ.ai

76mistral-smallMistral AIMistral AI

77gpt-6-astraOpenAIOpenAI

78qwen3-coder-nextAlibabaAlibaba

79gemma-3-12b-itGoogleGoogle

80scaledown-summarize-1ScaleDownScaleDown

81gemini-2.5-flash-liteGoogleGoogle

82grok-4.20-reasoningxAIxAI

83gemini-2.5-proGoogleGoogle

84deepseek-r1DeepSeekDeepSeek

85gpt-4oOpenAIOpenAI

86gemma-4-31b-itGoogleGoogle

87deepseek-v3.2-thinkingDeepSeekDeepSeek

88gemini-2.5-flashGoogleGoogle

89claude-opus-4.7AnthropicAnthropic

90gpt-oss-20bOpenAIOpenAI

91glm-5.2Z.aiZ.ai

92gpt-4o-miniOpenAIOpenAI

93nemotron-3.5-super-vlNVIDIANVIDIA

94gemma-4-26b-a4b-itGoogleGoogle

95nemotron-3-ultra-550b-a55bNVIDIANVIDIA

96gpt-5.3-codexOpenAIOpenAI

97qwen-3-32bAlibabaAlibaba

98gpt-5.5OpenAIOpenAI

99qwen3.8-max-primeAlibabaAlibaba

100glm-4.7-flashZ.aiZ.ai

101llama-3.3-70bMetaMeta

102kimi-k2.6MoonshotMoonshot

103gpt-6-luna-fastOpenAIOpenAI

104nemotron-3-super-120b-a12bNVIDIANVIDIA

105gpt-5.2OpenAIOpenAI

106mercury-2InceptionInception

107kimi-k2.5MoonshotMoonshot

108mistral-nemoMistral AIMistral AI

109grok-4.20-multi-agent-betaxAIxAI

110o3-miniOpenAIOpenAI

111qwen3.7-plusAlibabaAlibaba

112fugu-ultraSakana AISakana AI

113fugu-ultra-v2SakanaSakana

114arrow-2QuiverAIQuiverAI

115glm-5v-turboZ.aiZ.ai

116qwen3-coder-30b-a3balibabaalibaba

117glm-4.5Z.aiZ.ai

118claude-opus-4.5AnthropicAnthropic

119o3-fastOpenAIOpenAI

120qwen3.8-omni-flashAlibabaAlibaba

121grok-4.20-multi-agentxAIxAI

122ling-3.1-flashinclusionAIinclusionAI

123gpt-5OpenAIOpenAI

124nvidia-nemotron-3.5-lightning-30b-a3bNVIDIANVIDIA

125nemotron-nano-9b-v2NVIDIANVIDIA

126nova-2-liteAmazonAmazon

127qwen3.5-flashAlibabaAlibaba

128muse-spark-1.2MetaMeta

129muse-spark-1.3MetaMeta

130qwen3.8-max-0902AlibabaAlibaba

131qwen3.6-plusAlibabaAlibaba

132qwen3-vl-235b-a22b-instructAlibabaAlibaba

133o4-miniOpenAIOpenAI

134muse-spark-openMetaMeta

135muse-spark-1.1MetaMeta

136qwen3.5-9bAlibabaAlibaba

137qwen3.5-plusAlibabaAlibaba

138muse-spark-1.2-contributorMetaMeta

139grok-build-0.1xAIxAI

140muse-glimmer-30bMetaMeta

141glm-4.7Z.aiZ.ai

142qwen3.7-maxAlibabaAlibaba

143glimpseElorianElorian

144gpt-5.5-fastOpenAIOpenAI

145interfaze-betaInterfazeInterfaze

146muse-wonder-1.0MetaMeta

147fugu-maxSakanaSakana

148qwen3.5-397b-a17bAlibabaAlibaba

149qwen3.8-2.4t-a95bAlibabaAlibaba

150qwen3-30b-a3bAlibabaAlibaba

151claude-opus-4.8-fastAnthropicAnthropic

152gpt-4.1OpenAIOpenAI

153minimax-m2.1MiniMaxMiniMax

154glm-5Z.aiZ.ai

155deepseek-r1-0528DeepSeekDeepSeek

156mistral-medium-3.5Mistral AIMistral AI

157hy3TencentTencent

158qwen3.6-27bAlibabaAlibaba

159seed-2.1-turboByteDance SeedByteDance Seed

160deepseek-v3.2DeepSeekDeepSeek

161minimax-m2.7-highspeedMiniMaxMiniMax

162qwen3-next-80b-a3b-instructAlibabaAlibaba

163seed-2.0-codeByteDance SeedByteDance Seed

164hy4-previewTencentTencent

165arrow-2-telosQuiverAIQuiverAI

166gpt-oss-safeguard-20bOpenAIOpenAI

167command-aCohereCohere

168gpt-5-mini-fastOpenAIOpenAI

169glm-4.5-airZ.aiZ.ai

170mistral-large-4Mistral AIMistral AI

171inkling-smallThinking Machines LabThinking Machines Lab

172ember-1FireworksFireworks

173qwen3.5-27bAlibabaAlibaba

174grok-4.20-non-reasoningxAIxAI

175glm-4.6Z.aiZ.ai

176mimo-v2.6-pro-ultraspeedXiaomiXiaomi

177llama-4-maverickMetaMeta

178gpt-oss-safeguard-120bOpenAIOpenAI

179glm-5-turboZ.aiZ.ai

180step-3.7-flashStepFunStepFun

181glm-5.3-flashxZ.aiZ.ai

182inklingThinking MachinesThinking Machines

183nemotron-3-nano-30b-a3bNVIDIANVIDIA

184qwen3-coder-30b-a3b-instructAlibabaAlibaba

185step-5-previewStepFunStepFun

186nemotron-3.5-lightningnvidianvidia

187kimi-k3-fastMoonshotMoonshot

188qwen3-coderAlibabaAlibaba

189mistral-large-3Mistral AIMistral AI

190grok-code-fast-1xAIxAI

191seed-1.8ByteDanceByteDance

192gpt-5-codexOpenAIOpenAI

193llama-4-scoutMetaMeta

194glm-4.5vZ.aiZ.ai

195ling-3.0-flash-vlinclusionAI (Ant Group)inclusionAI (Ant Group)

196claude-opus-5.5-fastAnthropicAnthropic

197ling-3.0-flash-fininclusionAI (Ant Group)inclusionAI (Ant Group)

198minimax-m2.1-lightningMiniMaxMiniMax

199ling-3.0-flash-santeinclusionAI (Ant Group)inclusionAI (Ant Group)

200qwen3.5-35b-a3bAlibabaAlibaba

201grok-4.20-reasoning-betaspacexaispacexai

202seed-1.6ByteDanceByteDance

203ling-3.1-flash-1019inclusionaiinclusionai

204gpt-5.1-codex-maxOpenAIOpenAI

205grok-4.20-non-reasoning-betaspacexaispacexai

206glm-5.2-fastZ.aiZ.ai

207kimi-k2MoonshotMoonshot

208ministral-3bMistral AIMistral AI

209qwen-3-30balibabaalibaba

210ling-3.0-flashinclusionAI (Ant Group)inclusionAI (Ant Group)

211glm-4.6vZ.aiZ.ai

212glm-4.7-flashxZ.aiZ.ai

213longcat-2.5-previewMeituan (LongCat)Meituan (LongCat)

214nova-liteAmazonAmazon

215nova-proAmazonAmazon

216qwen3-vl-instructalibabaalibaba

217morph-v3-largeMorphMorph

218glm-5.3-fastZ.aiZ.ai

219nova-microAmazonAmazon

220toast-1MixedbreadMixedbread

221ministral-14bMistral AIMistral AI

222hy-mt2-proTencentTencent

223ministral-8bMistral AIMistral AI

224kimi-k2-0905Moonshot AIMoonshot AI

225gpt-5-fastOpenAIOpenAI

226gpt-5.1-thinkingOpenAIOpenAI

227gpt-5.1-codex-miniOpenAIOpenAI

228gemma-3-4b-itGoogleGoogle

229gpt-5.1-codexOpenAIOpenAI

230gpt-5.2-codexOpenAIOpenAI

231gpt-6-sol-fastOpenAIOpenAI

232gemma-3-27b-itGoogleGoogle

233gpt-5.1-thinking-fastOpenAIOpenAI

234gpt-5.2-fastOpenAIOpenAI

235gpt-5.4-fastOpenAIOpenAI

236gpt-5.4-mini-fastOpenAIOpenAI

237gpt-6.1-sol-fastOpenAIOpenAI

238gpt-4o-fastOpenAIOpenAI

239gpt-5.3-codex-fastOpenAIOpenAI

240qwen-mt-plusAlibabaAlibaba

241llama-3.1-8bMetaMeta

242deepseek-v3.1DeepSeekDeepSeek

243morph-v3-fastMorphMorph

244minimax-m2.5-highspeedMiniMaxMiniMax

245schematron-v2-smallInference.netInference.net

246claude-opus-5-fastAnthropicAnthropic

247gemini-omni-1.2-flashgooglegoogle

248llama-3.1-70bMetaMeta

249o1OpenAIOpenAI

250hy-mt2-liteTencentTencent

251gpt-6-astra-fastOpenAIOpenAI

252nemotron-nano-12b-v2-vlNVIDIANVIDIA

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