Skip to content
OneAtlas

LLM Gateway

Docs @ai-sdk/openai-compatibleLLMGATEWAY_API_KEYhttps://api.llmgateway.io/v1
431
Models
21
Labs

Models on this provider

USD per 1M tokens

ModelProvider model IDContextOutputInput $Output $Cache readCache writeReasoningToolsStructuredUpdated
GPT-6.1 TerraOpenAIopenai/gpt-6.1-terra1.05M128K$1.00$5.00$0.05$1.25YesYesYesOct 26, 2026
Kimi K3.1 ProMoonshot AImoonshot/kimi-k3.1-pro1.05M1.05M$2.00$10.00$0.20$2.00YesYesYesOct 23, 2026
Kimi K3.1 ProMoonshot AImoonshot/kimi-k3.1-pro-highspeed1.05M1.05M$4.00$20.00$0.20$4.00YesYesYesOct 23, 2026
MiniMax-M3.1-FlashMiniMaxminimax/minimax-m3.1-flash1.05M524K$0.15$0.60$0.01—YesYesNoOct 19, 2026
MiniMax-M3.1-FlashMiniMaxtogether-ai/minimax-m3.1-flash1.05M1.05M$0.15$0.60$0.01—YesYesNoOct 19, 2026
MiniMax-M3.1-FlashMiniMaxinference.net/minimax-m3.1-flash1M524K$0.10$0.50$0.005—YesYesNoOct 19, 2026
MiniMax-M3.1-FlashMiniMaxnebius/minimax-m3.1-flash1.05M1.05M$0.15$0.60$0.01—YesYesNoOct 19, 2026
MiniMax-M3.1-FlashMiniMaxnovita/minimax-m3.1-flash1M524K$0.15$0.60$0.01—YesYesNoOct 19, 2026
DeepSeek V4.1 Flash 1017DeepSeekdeepseek/deepseek-v4.1-flash-10171.05M393K$0.15$0.60$0.003—YesYesNoOct 17, 2026
DeepSeek V4.1 Flash 1017DeepSeekalibaba/deepseek-v4.1-flash-10171M393K$0.30$1.20$0.03—YesYesNoOct 17, 2026
DeepSeek V4.1 Flash 1017DeepSeekreka-ai/deepseek-v4.1-flash-10171.05M393K$0.15$0.60$0.003—YesYesYesOct 17, 2026
DeepSeek V4.1 Flash 1017DeepSeektogether-ai/deepseek-v4.1-flash-10171.05M393K$0.30$1.20$0.006—YesYesYesOct 17, 2026
DeepSeek V4.1 Flash 1017DeepSeeksciforium/deepseek-v4.1-flash-10171.06M384K$0.15$0.60$0.003—YesYesYesOct 17, 2026
DeepSeek V4.1 Flash 1017DeepSeekrunware/deepseek-v4.1-flash-10171.05M1.05M$0.15$0.60$0.01—YesYesYesOct 17, 2026
DeepSeek V4.1 Flash 1017DeepSeekinference.net/deepseek-v4.1-flash-1017262K131K$0.30$1.00$0.007—YesYesYesOct 17, 2026
DeepSeek V4.1 Flash 1017DeepSeekentrim/deepseek-v4.1-flash-10171.05M384K$0.20$0.80$0.005—YesYesYesOct 17, 2026
DeepSeek V4.1 Flash 1017DeepSeekdeepinfra/deepseek-v4.1-flash-10171.05M393K$0.20$0.60$0.006—YesYesYesOct 17, 2026
DeepSeek V4.1 Flash 1017DeepSeeknovita/deepseek-v4.1-flash-10171.05M393K$0.30$1.20$0.006—YesYesNoOct 17, 2026
Gemini 4 ArgonGooglegoogle-vertex/gemini-4-argon1.05M1.05M$4.00$20.00$0.20$0.38YesYesYesOct 13, 2026
Gemini 4 ArgonGooglegoogle-ai-studio/gemini-4-argon1.05M1.05M$4.00$20.00$0.20$0.38YesYesYesOct 13, 2026
Muse WonderMetameta/muse-wonder-1.01.05M1.05M$4.00$20.00$0.20—YesYesYesOct 12, 2026
Claude Haiku 5.5Anthropicanthropic/claude-haiku-5-51M128K$0.10$0.50$0.01$0.13YesYesYesOct 7, 2026
Claude Haiku 5.5Anthropicaws-bedrock/claude-haiku-5-51M128K$0.10$0.50$0.01$0.13YesYesNoOct 7, 2026
Mistral Large 4Mistralmistral/mistral-large-41M262K$1.36$4.18$0.14—NoYesYesOct 6, 2026
GPT-6.1 SolOpenAIopenai/gpt-6.1-sol1.05M128K$2.00$10.00$0.10$2.50YesYesYesSep 29, 2026
GPT-6.1 SolOpenAIazure/gpt-6.1-sol1.05M128K$2.00$10.00$0.10$2.50YesYesYesSep 29, 2026
Claude Sonnet 5.5Anthropicanthropic/claude-sonnet-5-51M128K$2.00$10.00$0.10$2.50YesYesYesSep 28, 2026
Claude Sonnet 5.5Anthropicazure-anthropic/claude-sonnet-5-51M128K$2.00$10.00$0.10$2.50YesYesYesSep 28, 2026
Claude Sonnet 5.5Anthropicaws-bedrock/claude-sonnet-5-51M128K$2.00$10.00$0.10$2.50YesYesNoSep 28, 2026
Claude Opus 5.5Anthropicanthropic/claude-opus-5-51M128K$4.00$20.00$0.20$5.00YesYesYesSep 22, 2026
Claude Opus 5.5Anthropicazure-anthropic/claude-opus-5-51M128K$4.00$20.00$0.20$5.00YesYesYesSep 22, 2026
Claude Opus 5.5Anthropicaws-bedrock/claude-opus-5-51M128K$4.00$20.00$0.20$5.00YesYesNoSep 22, 2026
GPT-6 LunaOpenAIopenai/gpt-6-luna1.05M128K$0.10$0.50$0.01$0.13YesYesYesSep 22, 2026
GPT-6 LunaOpenAIazure/gpt-6-luna1.05M128K$0.10$0.50$0.01$0.13YesYesYesSep 22, 2026
GPT-6 SolOpenAIopenai/gpt-6-sol1.05M128K$2.00$10.00$0.20$2.50YesYesYesSep 22, 2026
GPT-6 SolOpenAIazure/gpt-6-sol1.05M128K$2.00$10.00$0.20$2.50YesYesYesSep 22, 2026
MiMo-V2.6-FlashXiaomixiaomi/mimo-v2.6-flash1M131K$0.14$0.28$0.0028—YesYesNoSep 22, 2026
MiMo-V2.6-FlashXiaomideepinfra/mimo-v2.6-flash1.05M66K$0.14$0.28$0.0028—YesYesYesSep 22, 2026
MiMo-V2.6-FlashXiaomiconsensusprotocol/mimo-v2.6-flash1.05M131K$0.12$0.25$0.0025—YesYesYesSep 22, 2026
MiMo-V2.6-ProXiaomixiaomi/mimo-v2.6-pro1M131K$0.43$0.87$0.0036—YesYesNoSep 22, 2026
MiMo-V2.6-ProXiaomideepinfra/mimo-v2.6-pro1.05M66K$0.43$0.87$0.0036—YesYesYesSep 22, 2026
Grok 4.7xAIxai/grok-4-7500K500K$2.00$6.00$0.50—YesYesNoSep 21, 2026
Grok 4.7xAIvertex-openai/grok-4-7524K524K$2.00$6.00$0.50—YesYesYesSep 21, 2026
Grok 4.7xAIaws-bedrock/grok-4-7524K524K$2.00$6.00$0.50—YesYesYesSep 21, 2026
Fugu MaxSakana AIsakana/fugu-max1M1M$2.00$6.00$0.25—YesYesYesSep 11, 2026
Fugu Ultra v2Sakana AIsakana/fugu-ultra-v2.01M1M$5.00$30.00$0.50—YesYesYesSep 11, 2026
DeepSeek V4.1 FlashDeepSeekscx-ai-gp/deepseek-v4.1-flash1M384K$0.15$0.60$0.01—NoNoNoSep 10, 2026
DeepSeek V4.1 FlashDeepSeekluminal/deepseek-v4.1-flash1M384K$0.14$0.54$0.0027—YesYesNoSep 10, 2026
DeepSeek V4.1 FlashDeepSeekbaidu/deepseek-v4.1-flash1.05M393K$0.30$1.20$0.006—YesYesYesSep 10, 2026
DeepSeek V4.1 FlashDeepSeekalibaba/deepseek-v4.1-flash1M393K$0.30$1.20$0.03—YesYesNoSep 10, 2026
DeepSeek V4.1 FlashDeepSeekreka-ai/deepseek-v4.1-flash1.05M393K$0.10$0.30$0.0025—YesYesYesSep 10, 2026
DeepSeek V4.1 FlashDeepSeektogether-ai/deepseek-v4.1-flash1.05M393K$0.30$1.20$0.006—YesYesYesSep 10, 2026
DeepSeek V4.1 FlashDeepSeekrunware/deepseek-v4.1-flash1.05M384K$0.15$0.60$0.01—YesYesYesSep 10, 2026
DeepSeek V4.1 FlashDeepSeekentrim/deepseek-v4.1-flash1.05M384K$0.20$0.60$0.005—YesYesYesSep 10, 2026
DeepSeek V4.1 FlashDeepSeekdeepinfra/deepseek-v4.1-flash1.05M393K$0.20$0.60$0.006—YesYesYesSep 10, 2026
DeepSeek V4.1 FlashDeepSeekfireworks/deepseek-v4.1-flash1.05M393K$0.22$0.66$0.007—YesYesYesSep 10, 2026
DeepSeek V4.1 FlashDeepSeekconsensusprotocol/deepseek-v4.1-flash1.05M384K$0.15$0.55$0.005—YesYesNoSep 10, 2026
DeepSeek V4.1 FlashDeepSeeknovita/deepseek-v4.1-flash1.05M393K$0.30$1.20$0.006—YesYesNoSep 10, 2026
Ling 3.0 Flash VLinclusionAIdeepinfra/ling-3.0-flash-vl131K33K$0.06$0.18$0.01—YesYesYesSep 10, 2026
GPT-6 AstraOpenAIaws-mantle/gpt-6-astra1.05M128K$10.00$50.00$1.00$12.50YesYesYesSep 4, 2026
GPT-6 AstraOpenAIopenai/gpt-6-astra1.05M128K$10.00$50.00$1.00$12.50YesYesYesSep 4, 2026
GPT-6 AstraOpenAIazure/gpt-6-astra1.05M128K$10.00$50.00$1.00$12.50YesYesYesSep 4, 2026
Gemini 3.8 FlashGooglegoogle-vertex/gemini-3.8-flash1.05M66K$0.75$3.75$0.07$0.08YesYesYesSep 2, 2026
Gemini 3.8 FlashGooglegoogle-ai-studio/gemini-3.8-flash1.05M66K$0.75$3.75$0.07$0.08YesYesYesSep 2, 2026
Muse Spark 1.3Metameta/muse-spark-1.31.05M1.05M$1.25$4.25$0.15—YesYesYesSep 2, 2026
Muse Spark 1.3 Contributor (Meta Contributor)Metameta-contributor/muse-spark-1.3-contributor1.05M1.05M$0.10$0.20$0.002—YesYesYesSep 2, 2026
Claude Fable 5.1Anthropicanthropic/claude-fable-5-11M128K$10.00$50.00$0.25$12.50YesYesYesSep 1, 2026
Claude Fable 5.1Anthropicazure-anthropic/claude-fable-5-11M128K$10.00$50.00$0.25$12.50YesYesYesSep 1, 2026
Claude Fable 5.1Anthropicaws-bedrock/claude-fable-5-11M128K$10.00$50.00$0.25$12.50YesYesNoSep 1, 2026
Hy4 previewTencenttencent/hy4-preview1M66K$0.83$2.50$0.04—YesYesYesAug 28, 2026
GLM-5.3-FlashZhipu AIscx-ai-gp/glm-5.3-flash1.05M131K$0.09$0.25$0.03—YesYesNoAug 26, 2026
GLM-5.3-FlashZhipu AIgreenference/glm-5.3-flash1.05M131K$0.14$0.49$0.03—YesYesNoAug 26, 2026
GLM-5.3-FlashZhipu AIreka-ai/glm-5.3-flash262K262K$0.15$0.50$0.02—YesYesYesAug 26, 2026
GLM-5.3-FlashZhipu AItogether-ai/glm-5.3-flash1.05M944K$0.15$0.50$0.03—YesYesYesAug 26, 2026
GLM-5.3-FlashZhipu AIrunware/glm-5.3-flash1M131K$0.15$0.50$0.03—YesYesYesAug 26, 2026
GLM-5.3-FlashZhipu AIinference.net/glm-5.3-flash1.05M128K$0.09$0.28$0.02—YesYesYesAug 26, 2026
GLM-5.3-FlashZhipu AIzai/glm-5.3-flash1.05M131K$0.15$0.50$0.03—YesYesNoAug 26, 2026
GLM-5.3-FlashZhipu AIentrim/glm-5.3-flash1.05M131K$0.10$0.35$0.02—YesYesYesAug 26, 2026
GLM-5.3-FlashZhipu AIfireworks/glm-5.3-flash1.05M131K$0.15$0.50$0.03—YesYesNoAug 26, 2026
GLM-5.3-FlashZhipu AIconsensusprotocol/glm-5.3-flash1.05M131K$0.10$0.25$0.01—YesYesNoAug 26, 2026
GLM-5.3-FlashZhipu AInovita/glm-5.3-flash1.05M131K$0.15$0.50$0.03—YesYesNoAug 26, 2026
Qwen3.8 FlashAlibabaalibaba/qwen3.8-flash984K131K$0.15$0.47$0.02$0.20YesYesYesAug 26, 2026
Qwen3.8 FlashAlibabanovita/qwen3.8-flash1M131K$0.15$0.47$0.02—YesYesYesAug 26, 2026
Granite 4.2 8BIBMdeepinfra/granite-4.2-8b131K118K$0.06$0.25$0.01—YesYesNoAug 25, 2026
GLM-5.3Zhipu AIscx-ai-gp/glm-5.3-fast1M128K$2.80$8.80$0.56—NoNoNoAug 14, 2026
GLM-5.3Zhipu AIscx-ai-gp/glm-5.31M128K$0.92$2.90$0.17—YesYesNoAug 14, 2026
GLM-5.3Zhipu AIbaidu/glm-5.31.05M131K$1.40$4.40$0.26—YesYesNoAug 14, 2026
GLM-5.3Zhipu AIalibaba/glm-5.31.05M131K$1.40$4.40$0.28—YesYesNoAug 14, 2026
GLM-5.3Zhipu AIreka-ai/glm-5.31.05M262K$0.45$1.80$0.14—YesYesYesAug 14, 2026
GLM-5.3Zhipu AItogether-ai/glm-5.31.05M944K$1.40$4.40$0.26—YesYesYesAug 14, 2026
GLM-5.3Zhipu AIrunware/glm-5.31M131K$1.20$4.00$0.20—YesYesYesAug 14, 2026
GLM-5.3Zhipu AIinference.net/glm-5.31.05M131K$0.90$3.00$0.15—YesYesYesAug 14, 2026
GLM-5.3Zhipu AIzai/glm-5.31M128K$1.40$4.40$0.26—YesYesNoAug 14, 2026
GLM-5.3Zhipu AIentrim/glm-5.31.05M131K$0.50$2.00$0.15—YesYesYesAug 14, 2026
GLM-5.3Zhipu AImistral/glm-5.31.05M131K$1.40$4.40$0.14—YesYesYesAug 14, 2026
GLM-5.3Zhipu AIfireworks/glm-5.31.05M131K$1.40$4.40$0.26—YesYesNoAug 14, 2026
GLM-5.3Zhipu AInovita/glm-5.31.05M131K$1.40$4.40$0.26—YesYesNoAug 14, 2026
Qwen3.8 27BAlibabaconsensusprotocol/Qwen3.8-27B262K33K$0.08$0.35$0.05—YesYesNoAug 14, 2026
Qwen3.8 27BAlibabanovita/qwen3.8-27b1M131K$0.42$3.00$0.09—YesYesNoAug 14, 2026
Gemini 3.7 FlashGooglegoogle-vertex/gemini-3.7-flash1.05M66K$0.75$3.75$0.07$0.08YesYesYesAug 13, 2026
Grok 4.6xAIxai/grok-4-6500K500K$2.00$6.00$0.50—YesYesNoAug 12, 2026
Grok 4.6xAIvertex-openai/grok-4-6500K500K$2.00$6.00$0.50—YesYesYesAug 12, 2026
Grok 4.6xAIaws-bedrock/grok-4-6500K500K$2.00$6.00$0.50—YesYesYesAug 12, 2026
Qwen3.8 2.4T A95BAlibabatogether-ai/qwen3.8-2.4t-a95b1.01M909K$2.00$6.00$0.25—YesYesYesAug 12, 2026
Qwen3.8 2.4T A95BAlibabanovita/qwen3.8-2.4t-a95b1M131K$2.00$6.00$0.25—YesYesYesAug 12, 2026
Muse Glimmer 30BMetatogether-ai/muse-glimmer-30b131K118K$0.35$1.50$0.04—YesYesYesAug 10, 2026
Muse Glimmer 30BMetadeepinfra/muse-glimmer-30b131K16K$0.30$1.20$0.04—YesYesYesAug 10, 2026
Muse Spark 1.2 Contributor (Meta Contributor)Metameta-contributor/muse-spark-1.2-contributor1.05M131K$0.10$0.20$0.002—YesYesYesAug 6, 2026
Muse Spark 1.2Metameta/muse-spark-1.21.05M131K$1.25$4.25$0.15—YesYesYesAug 5, 2026
Qwen3.8 MaxAlibabascx-ai-gp/qwen3.8-max1M131K$1.54$4.63$0.20$2.50YesYesNoAug 3, 2026
Qwen3.8 MaxAlibabaalibaba/qwen3.8-max984K131K$2.00$6.00$0.25$2.50YesYesNoAug 3, 2026
Qwen3.8 MaxAlibabanovita/qwen3.8-max1M131K$2.00$6.00$0.25—YesYesYesAug 3, 2026
GPT-Live-TranscribeOpenAIopenai/gpt-live-transcribe——FreeFree——NoNoNoJul 28, 2026
GPT-TranscribeOpenAIopenai/gpt-transcribe——FreeFree——NoNoNoJul 28, 2026
Claude Opus 5Anthropicanthropic/claude-opus-51M128K$5.00$25.00$0.50$6.25YesYesYesJul 24, 2026
Claude Opus 5Anthropicazure-anthropic/claude-opus-51M128K$5.00$25.00$0.50$6.25YesYesYesJul 24, 2026
Claude Opus 5Anthropicaws-bedrock/claude-opus-51M128K$5.00$25.00$0.50$6.25YesYesNoJul 24, 2026
Ling 3.0 FlashinclusionAIdeepinfra/ling-3.0-flash262K33K$0.06$0.18$0.01—YesYesNoJul 23, 2026
Ling 3.0 FlashinclusionAInovita/ling-3.0-flash262K33K$0.06$0.18$0.01—YesYesNoJul 23, 2026
Gemini 3.5 Flash LiteGooglegoogle-vertex/gemini-3.5-flash-lite1.05M66K$0.30$2.50$0.03$0.08YesYesYesJul 21, 2026
Gemini 3.5 Flash LiteGooglegoogle-ai-studio/gemini-3.5-flash-lite1.05M66K$0.30$2.50$0.03$0.08YesYesYesJul 21, 2026
Gemini 3.6 FlashGooglegoogle-vertex/gemini-3.6-flash1.05M66K$0.75$3.75$0.07$0.08YesYesYesJul 21, 2026
Gemini 3.6 FlashGooglegoogle-ai-studio/gemini-3.6-flash1.05M66K$0.75$3.75$0.07$0.08YesYesYesJul 21, 2026
Kimi K3Moonshot AIscx-ai-gp/kimi-k31.05M1.05M$3.13$15.68$0.32—YesYesYesJul 16, 2026
Kimi K3Moonshot AIalibaba/kimi-k31.05M1.05M$3.00$15.00$0.30—YesYesYesJul 16, 2026
Kimi K3Moonshot AIcanopywave/kimi-k31.05M1.05M$3.00$15.00$0.30—YesYesNoJul 16, 2026
Kimi K3Moonshot AImoonshot/kimi-k31.05M1.05M$3.00$15.00$0.30—YesYesNoJul 16, 2026
Kimi K3Moonshot AItogether-ai/kimi-k31M1M$3.00$15.00$0.30—YesYesNoJul 16, 2026
Kimi K3Moonshot AItencent/kimi-k31.05M1.05M$3.00$15.00$0.30—YesYesYesJul 16, 2026
Kimi K3Moonshot AIrunware/kimi-k31.05M1.05M$3.00$15.00$0.30—YesYesYesJul 16, 2026
Kimi K3Moonshot AIrunpod/kimi-k31.05M1.05M$3.00$15.00$0.30—YesYesYesJul 16, 2026
Kimi K3Moonshot AIaws-bedrock/kimi-k31.05M1.05M$3.00$15.00$0.30$3.75YesYesYesJul 16, 2026
Kimi K3Moonshot AIfireworks/kimi-k31.04M1.04M$3.00$15.00$0.30—YesYesNoJul 16, 2026
Kimi K3Moonshot AIfireworks/kimi-k3-fast1.04M1.04M$4.50$22.50$0.45—YesYesNoJul 16, 2026
Kimi K3Moonshot AInovita/kimi-k31.05M1.05M$3.00$15.00$0.30—YesYesNoJul 16, 2026
Qwen3.7 FlashAlibabaalibaba/qwen3.7-flash984K66K$0.03$0.13$0.006$0.04YesYesNoJul 15, 2026
GPT-5.6 LunaOpenAIaws-mantle/gpt-5.6-luna922K128K$0.22$1.32$0.02$0.28YesYesYesJul 9, 2026
GPT-5.6 LunaOpenAIopenai/gpt-5.6-luna1.05M128K$0.20$1.20$0.02$0.25YesYesYesJul 9, 2026
GPT-5.6 LunaOpenAIazure/gpt-5.6-luna1.05M128K$0.20$1.20$0.02$0.25YesYesYesJul 9, 2026
GPT-5.6 SolOpenAIaws-mantle/gpt-5.6-sol922K128K$4.40$22.00$0.44$5.50YesYesYesJul 9, 2026
GPT-5.6 SolOpenAIopenai/gpt-5.6-sol1.05M128K$4.00$20.00$0.40$5.00YesYesYesJul 9, 2026
GPT-5.6 SolOpenAIazure/gpt-5.6-sol1.05M128K$4.00$20.00$0.40$5.00YesYesYesJul 9, 2026
GPT-5.6 TerraOpenAIaws-mantle/gpt-5.6-terra922K128K$2.20$13.20$0.22$2.75YesYesYesJul 9, 2026
GPT-5.6 TerraOpenAIopenai/gpt-5.6-terra1.05M128K$2.00$12.00$0.20$2.50YesYesYesJul 9, 2026
GPT-5.6 TerraOpenAIazure/gpt-5.6-terra1.05M128K$2.00$12.00$0.20$2.50YesYesYesJul 9, 2026
Muse Spark 1.1Metameta/muse-spark-1.11.05M131K$1.25$4.25$0.15—YesYesYesJul 9, 2026
Grok 4.5xAIxai/grok-4-5500K500K$2.00$6.00$0.30—YesYesNoJul 8, 2026
Hy3Tencenttencent/hy3262K131K$0.13$0.53$0.03—YesYesYesJul 6, 2026
Hy3Tencentnovita/hy3262K262K$0.14$0.58$0.04—YesYesYesJul 6, 2026
Claude Sonnet 5Anthropicanthropic/claude-sonnet-51M128K$2.00$10.00$0.20$2.50YesYesYesJun 30, 2026
Claude Sonnet 5Anthropicazure-anthropic/claude-sonnet-51M128K$2.00$10.00$0.20$2.50YesYesYesJun 30, 2026
Claude Sonnet 5Anthropicaws-bedrock/claude-sonnet-51M128K$2.00$10.00$0.20$2.50YesYesNoJun 30, 2026
Claude Sonnet 5Anthropicvertex-anthropic/claude-sonnet-51M128K$2.00$10.00$0.20$2.50YesYesYesJun 30, 2026
Fugu UltraSakana AIsakana/fugu-ultra1M1M$5.00$30.00$0.50—YesYesNoJun 15, 2026
GLM-5.2Zhipu AIbytedance/glm-5.21.02M128K$1.40$4.40$0.26—YesYesNoJun 13, 2026
GLM-5.2Zhipu AIscx-ai-gp/glm-5.2-fast1M131K$2.16$6.78$0.43—YesYesNoJun 13, 2026
GLM-5.2Zhipu AIscx-ai-gp/glm-5.21M131K$0.60$2.12$0.15—YesYesNoJun 13, 2026
GLM-5.2Zhipu AIbaidu/glm-5.21.05M131K$1.40$4.40$0.26—YesYesNoJun 13, 2026
GLM-5.2Zhipu AIalibaba/glm-5.21M131K$1.40$4.40$0.28—YesYesNoJun 13, 2026
GLM-5.2Zhipu AIcanopywave/glm-5.2200K33K$1.40$4.40$0.26—YesYesNoJun 13, 2026
GLM-5.2Zhipu AItencent/glm-5.21M128K$1.40$4.40$0.26—YesYesNoJun 13, 2026
GLM-5.2Zhipu AIrunware/glm-5.21.02M128K$0.80$2.55$0.16—YesYesNoJun 13, 2026
GLM-5.2Zhipu AIzai/glm-5.21M128K$1.40$4.40$0.26—YesYesNoJun 13, 2026
GLM-5.2Zhipu AIembercloud/glm-5.2203K131K$1.26$3.96$0.23—YesYesNoJun 13, 2026
GLM-5.2Zhipu AInovita/glm-5.21.05M131K$1.40$4.40$0.26—YesYesNoJun 13, 2026
Kimi K2.7 CodeMoonshot AIscx-ai-gp/kimi-k2.7-code262K262K$0.74$3.08$0.14—YesYesNoJun 12, 2026
Kimi K2.7 CodeMoonshot AImoonshot/kimi-k2.7-code262K262K$0.95$4.00$0.19—YesYesNoJun 12, 2026
Kimi K2.7 CodeMoonshot AItencent/kimi-k2.7-code262K262K$0.95$4.00$0.19—YesYesYesJun 12, 2026
Kimi K2.7 CodeMoonshot AInovita/kimi-k2.7-code262K262K$0.95$4.00$0.19—YesYesYesJun 12, 2026
Kimi K2.7 Code HighspeedMoonshot AImoonshot/kimi-k2.7-code-highspeed262K262K$1.90$8.00$0.38—YesYesNoJun 12, 2026
Kimi K2.7 Code HighspeedMoonshot AItencent/kimi-k2.7-code-highspeed262K262K$1.90$8.00$0.38—YesYesYesJun 12, 2026
Claude Fable 5Anthropicanthropic/claude-fable-51M128K$10.00$50.00$1.00$12.50YesYesYesJun 9, 2026
Claude Fable 5Anthropicazure-anthropic/claude-fable-51M128K$10.00$50.00$1.00$12.50YesYesYesJun 9, 2026
Claude Fable 5Anthropicaws-bedrock/claude-fable-51M128K$10.00$50.00$1.00$12.50YesYesNoJun 9, 2026
Qwen3.7 PlusAlibabaalibaba/qwen3.7-plus984K66K$0.40$1.60$0.08$0.50YesYesNoJun 2, 2026
MiniMax-M3MiniMaxminimax/minimax-m3512K131K$0.60$2.40$0.12—YesYesNoJun 1, 2026
MiniMax-M3MiniMaxtogether-ai/minimax-m3524K131K$0.30$1.20$0.06—YesNoYesJun 1, 2026
MiniMax-M3MiniMaxtencent/minimax-m31M131K$0.30$1.20$0.06—YesYesNoJun 1, 2026
MiniMax-M3MiniMaxconsensusprotocol/minimax-m31.05M512K$0.28$1.10$0.05—YesYesYesJun 1, 2026
Nemotron 3 Ultra 550BNVIDIAdeepinfra/nemotron-3-ultra-550b262K262K$0.50$2.20$0.10—NoYesNoJun 1, 2026
Step 3.7 FlashStepFun (China)novita/step-3.7-flash262K256K$0.20$1.15$0.04—YesYesNoMay 29, 2026
Claude Opus 4.8Anthropicanthropic/claude-opus-4-81M128K$5.00$25.00$0.50$6.25YesYesYesMay 28, 2026
Claude Opus 4.8Anthropicazure-anthropic/claude-opus-4-81M128K$5.00$25.00$0.50$6.25YesYesYesMay 28, 2026
Claude Opus 4.8Anthropicaws-bedrock/claude-opus-4-81M128K$5.00$25.00$0.50$6.25YesYesNoMay 28, 2026
Hy-MT2 Plus (Tencent Cloud)Tencenttencent/hy-mt2-plus8K4K$0.07$0.29——NoNoNoMay 21, 2026
Qwen3.7 MaxAlibabaalibaba/qwen3.7-max984K66K$2.50$7.50$0.50$3.13YesYesNoMay 21, 2026
Qwen3.7 MaxAlibabanovita/qwen3.7-max1M66K$1.25$3.75$0.25—YesYesNoMay 21, 2026
Gemini 3.5 FlashGooglegoogle-vertex/gemini-3.5-flash1.05M66K$1.50$9.00$0.15$0.08YesYesYesMay 19, 2026
Gemini 3.1 Flash LiteGooglegoogle-vertex/gemini-3.1-flash-lite1.05M66K$0.25$1.50$0.03$0.08YesYesYesMay 7, 2026
Gemini 3.1 Flash LiteGooglegoogle-ai-studio/gemini-3.1-flash-lite1.05M66K$0.25$1.50$0.03$0.08YesYesYesMay 7, 2026
Mistral Medium 3.5Mistralmistral/mistral-medium-3-5262K262K$1.50$7.50——NoYesYesApr 30, 2026
Seed 2.0 Lite (260428) (ByteDance)ByteDance Seedbytedance/seed-2-0-lite-260428262K131K$0.25$2.00$0.05—YesYesYesApr 28, 2026
Seed 2.0 Mini (260428) (ByteDance)ByteDance Seedbytedance/seed-2-0-mini-260428262K131K$0.10$0.40$0.02—YesYesYesApr 28, 2026
Qwen3.6 FlashAlibabaalibaba/qwen3.6-flash984K66K$0.25$1.50$0.05$0.31YesYesNoApr 27, 2026
DeepSeek V4 FlashDeepSeekbytedance/deepseek-v4-flash1.05M393K$0.44$1.32$0.01—YesYesNoApr 24, 2026
DeepSeek V4 FlashDeepSeekranoai/deepseek-v4-flash1M393K$0.14$0.28$0.03—YesYesYesApr 24, 2026
DeepSeek V4 FlashDeepSeekbaidu/deepseek-v4-flash1.05M131K$0.44$1.32$0.01—YesYesNoApr 24, 2026
DeepSeek V4 FlashDeepSeekalibaba/deepseek-v4-flash1M393K$0.20$0.40$0.04—YesYesNoApr 24, 2026
DeepSeek V4 FlashDeepSeekcanopywave/deepseek-v4-flash1M393K$0.14$0.28$0.03—YesYesNoApr 24, 2026
DeepSeek V4 FlashDeepSeektencent/deepseek-v4-flash1M393K$0.14$0.28$0.0028—YesYesNoApr 24, 2026
DeepSeek V4 FlashDeepSeekrunware/deepseek-v4-flash1.05M384K$0.08$0.15$0.01—YesYesYesApr 24, 2026
DeepSeek V4 FlashDeepSeekdeepinfra/deepseek-v4-flash1M393K$0.08$0.18$0.02—YesYesNoApr 24, 2026
DeepSeek V4 FlashDeepSeekconsensusprotocol/deepseek-v4-flash1M384K$0.10$0.20$0.005—YesYesNoApr 24, 2026
DeepSeek V4 FlashDeepSeeknovita/deepseek-v4-flash1.05M393K$0.14$0.28$0.03—YesYesNoApr 24, 2026
DeepSeek V4 ProDeepSeekbytedance/deepseek-v4-pro1.05M393K$1.32$3.96$0.04—YesYesNoApr 24, 2026
DeepSeek V4 ProDeepSeekdeepseek/deepseek-v4-pro1.05M393K$0.43$0.87$0.0036—YesYesNoApr 24, 2026
DeepSeek V4 ProDeepSeekbaidu/deepseek-v4-pro1.05M131K$1.32$3.96$0.04—YesYesNoApr 24, 2026
DeepSeek V4 ProDeepSeekalibaba/deepseek-v4-pro1M393K$2.40$4.80$0.20—YesYesNoApr 24, 2026
DeepSeek V4 ProDeepSeekreka-ai/deepseek-v4-pro1.05M393K$0.90$1.90$0.07—YesYesYesApr 24, 2026
DeepSeek V4 ProDeepSeekcanopywave/deepseek-v4-pro1M393K$1.74$3.48$0.01—YesYesNoApr 24, 2026
DeepSeek V4 ProDeepSeektogether-ai/deepseek-v4-pro1.05M164K$1.32$3.96$0.13—YesYesYesApr 24, 2026
DeepSeek V4 ProDeepSeektencent/deepseek-v4-pro1M393K$0.43$0.87$0.0036—YesYesNoApr 24, 2026
DeepSeek V4 ProDeepSeekrunware/deepseek-v4-pro1.05M384K$0.96$1.92$0.08—YesYesYesApr 24, 2026
DeepSeek V4 ProDeepSeekdeepinfra/deepseek-v4-pro1.05M64K$1.30$2.60$0.10—YesYesNoApr 24, 2026
GPT-5.5OpenAIopenai/gpt-5.51.05M128K$5.00$30.00$0.50—YesYesYesApr 23, 2026
GPT-5.5OpenAIazure/gpt-5.51.05M128K$5.00$30.00$0.50—YesYesYesApr 23, 2026
GPT-5.5 ProOpenAIopenai/gpt-5.5-pro1.05M128K$30.00$180——YesYesNoApr 23, 2026
Qwen3.6 27BAlibabagreenference/qwen3.6-27b16K8K$0.15$1.35——NoYesYesApr 22, 2026
Kimi K2.6Moonshot AIbaidu/kimi-k2.6262K262K$0.95$4.00$0.16—YesYesNoApr 20, 2026
Kimi K2.6Moonshot AIcanopywave/kimi-k2.6262K33K$0.95$4.00$0.16—YesYesNoApr 20, 2026
Kimi K2.6Moonshot AImoonshot/kimi-k2.6262K262K$0.95$4.00$0.16—YesYesNoApr 20, 2026
Kimi K2.6Moonshot AItencent/kimi-k2.6262K262K$0.86$3.57$0.14—YesYesYesApr 20, 2026
Kimi K2.6Moonshot AIrunware/kimi-k2.6262K131K$0.60$3.05$0.13—YesYesNoApr 20, 2026
Kimi K2.6Moonshot AInovita/kimi-k2.6262K262K$0.80$3.40$0.16—YesYesNoApr 20, 2026
Grok 4.3xAIazure-ai-foundry/grok-4-320K8K$1.25$2.50$0.20—YesYesNoApr 17, 2026
Grok 4.3xAIxai/grok-4-31M1M$1.25$2.50$0.20—YesYesNoApr 17, 2026
Grok 4.3xAIaws-bedrock/grok-4-31M131K$1.25$2.50$0.20—YesYesYesApr 17, 2026
Qwen3.6 35B-A3BAlibabaalibaba/qwen3.6-35b-a3b262K66K$0.38$2.25——YesYesNoApr 17, 2026
Qwen3.6 35B-A3BAlibabanovita/qwen3.6-35b-a3b262K64K$0.25$1.49——YesYesNoApr 17, 2026
Claude Opus 4.7Anthropicanthropic/claude-opus-4-71M128K$5.00$25.00$0.50$6.25YesYesYesApr 16, 2026
Claude Opus 4.7Anthropicazure-anthropic/claude-opus-4-71M128K$5.00$25.00$0.50$6.25YesYesYesApr 16, 2026
Claude Opus 4.7Anthropicaws-bedrock/claude-opus-4-71M128K$5.00$25.00$0.50$6.25YesYesNoApr 16, 2026
Claude Opus 4.7Anthropicvertex-anthropic/claude-opus-4-71M128K$5.00$25.00$0.50$6.25YesYesYesApr 16, 2026
Grok Build 0.1xAIxai/grok-build-0-1256K256K$1.00$2.00$0.20—YesYesNoApr 16, 2026
GLM-5.1Zhipu AIbaidu/glm-5.1203K131K$1.40$4.40$0.26—YesYesNoApr 7, 2026
GLM-5.1Zhipu AItencent/glm-5.1200K128K$1.40$4.40$0.26—YesYesNoApr 7, 2026
GLM-5.1Zhipu AIzai/glm-5.1200K128K$1.40$4.40$0.26—YesYesNoApr 7, 2026
GLM-5.1Zhipu AIembercloud/glm-5.1203K131K$0.93$2.93$0.17—YesYesNoApr 7, 2026
GLM-5.1Zhipu AInovita/glm-5.1205K131K$1.38$4.40$0.26—YesYesNoApr 7, 2026
Gemma 4 26B A4B ITGoogledeepinfra/gemma-4-26b-a4b-it262K33K$0.07$0.34——YesYesNoApr 2, 2026
Gemma 4 26B A4B ITGooglenovita/gemma-4-26b-a4b-it262K33K$0.13$0.40——NoYesNoApr 2, 2026
Gemma 4 31B ITGooglerunware/gemma-4-31b-it262K66K$0.10$0.30$0.01—YesYesNoApr 2, 2026
Gemma 4 31B ITGooglecerebras/gemma-4-31b-it131K33K$0.99$1.49——YesYesNoApr 2, 2026
Gemma 4 31B ITGoogledeepinfra/gemma-4-31b-it262K33K$0.20$0.40——YesYesNoApr 2, 2026
Gemma 4 31B ITGoogleconsensusprotocol/gemma-4-31b-it262K33K$0.10$0.25$0.01—YesYesNoApr 2, 2026
Gemma 4 31B ITGooglenovita/gemma-4-31b-it262K33K$0.14$0.40——NoYesNoApr 2, 2026
Qwen3.6 PlusAlibabaalibaba/qwen3.6-plus984K66K$0.50$3.00$0.05$0.63YesYesNoApr 2, 2026
GLM-5V-TurboZhipu AItencent/glm-5v-turbo200K128K$1.20$4.00$0.24—YesYesNoApr 1, 2026
Seed 2.0 Code Preview (260328) (ByteDance)ByteDance Seedbytedance/seed-2-0-code-preview-260328262K131K$0.50$3.00$0.10—YesYesNoMar 28, 2026
Seed 2.0 Pro (260328) (ByteDance)ByteDance Seedbytedance/seed-2-0-pro-260328262K131K$0.50$3.00$0.10—YesYesYesMar 28, 2026
MiniMax-M2.7MiniMaxminimax/minimax-m2.7205K131K$0.30$1.20$0.06—YesYesNoMar 18, 2026
MiniMax-M2.7MiniMaxscx-ai/minimax-m2.7197K197K$0.48$1.79$0.05—YesYesNoMar 18, 2026
MiniMax-M2.7MiniMaxtencent/minimax-m2.7200K128K$0.30$1.20$0.06—YesYesNoMar 18, 2026
MiniMax-M2.7MiniMaxgonka24/minimax-m2.7205K131K$0.08$0.32$0.02—YesYesNoMar 18, 2026
MiniMax-M2.7MiniMaxnovita/minimax-m2.7205K131K$0.30$1.20$0.06—YesYesNoMar 18, 2026
MiniMax-M2.7-highspeedMiniMaxminimax/minimax-m2.7-highspeed205K131K$0.60$2.40$0.06—YesYesNoMar 18, 2026
GPT-5.4 miniOpenAIopenai/gpt-5.4-mini400K128K$0.75$4.50$0.07—YesYesYesMar 17, 2026
GPT-5.4 miniOpenAIazure/gpt-5.4-mini400K128K$0.75$4.50$0.07—YesYesYesMar 17, 2026
GPT-5.4 nanoOpenAIopenai/gpt-5.4-nano400K128K$0.20$1.25$0.02—YesYesYesMar 17, 2026
GPT-5.4 nanoOpenAIazure/gpt-5.4-nano400K128K$0.20$1.25$0.02—YesYesYesMar 17, 2026
GLM-5-TurboZhipu AItencent/glm-5-turbo200K128K$1.20$4.00$0.24—YesYesNoMar 16, 2026
Mistral Small 4Mistralmistral/mistral-small-2603262K256K$0.15$0.60——NoYesYesMar 16, 2026
Claude Opus 4.6Anthropicanthropic/claude-opus-4-61M128K$5.00$25.00$0.50$6.25YesYesYesMar 13, 2026
Claude Opus 4.6Anthropicazure-anthropic/claude-opus-4-61M128K$5.00$25.00$0.50$6.25YesYesYesMar 13, 2026
Claude Opus 4.6Anthropicaws-bedrock/claude-opus-4-61M128K$5.00$25.00$0.50$6.25YesYesYesMar 13, 2026
Claude Opus 4.6Anthropicvertex-anthropic/claude-opus-4-61M128K$5.00$25.00$0.50$6.25YesYesYesMar 13, 2026
Claude Sonnet 4.6Anthropicanthropic/claude-sonnet-4-61M64K$3.00$15.00$0.30$3.75YesYesYesMar 13, 2026
Claude Sonnet 4.6Anthropicaws-bedrock/claude-sonnet-4-61M64K$3.00$15.00$0.30$3.75YesYesYesMar 13, 2026
Claude Sonnet 4.6Anthropicvertex-anthropic/claude-sonnet-4-61M64K$3.00$15.00$0.30$3.75YesYesYesMar 13, 2026
Grok 4.20 (Non-Reasoning)xAIxai/grok-4-20-beta-0309-non-reasoning2M30K$2.00$6.00$0.20—NoYesNoMar 9, 2026
Grok 4.20 (Non-Reasoning)xAIvertex-openai/grok-4-20-non-reasoning2M30K$1.25$2.50$0.20—NoYesNoMar 9, 2026
Grok 4.20 (Reasoning)xAIxai/grok-4-20-beta-0309-reasoning2M30K$2.00$6.00$0.20—YesYesNoMar 9, 2026
Grok 4.20 (Reasoning)xAIvertex-openai/grok-4-20-reasoning2M30K$1.25$2.50$0.20—YesYesNoMar 9, 2026
GPT-5.4OpenAIopenai/gpt-5.41.05M128K$2.50$15.00$0.25—YesYesYesMar 5, 2026
GPT-5.4OpenAIazure/gpt-5.41.05M128K$2.50$15.00$0.25—YesYesYesMar 5, 2026
GPT-5.4 ProOpenAIopenai/gpt-5.4-pro1.05M128K$30.00$180——YesYesNoMar 5, 2026
GPT-5.4 ProOpenAIazure/gpt-5.4-pro1.05M128K$30.00$180——YesYesNoMar 5, 2026
Gemini Pro Latest (Google AI Studio)Googlegoogle-ai-studio/gemini-pro-latest1.05M66K$2.00$12.00$0.20—YesYesYesFeb 27, 2026
Qwen3.5 122B-A10BAlibabaalibaba/qwen3.5-122b-a10b262K66K$0.40$3.20——YesYesNoFeb 23, 2026
Qwen3.5 122B-A10BAlibabanovita/qwen3.5-122b-a10b262K66K$0.40$3.20——YesYesNoFeb 23, 2026
Qwen3.5 27BAlibabaalibaba/qwen3.5-27b262K66K$0.30$2.40——YesYesNoFeb 23, 2026
Qwen3.5 35B-A3BAlibabaalibaba/qwen3.5-35b-a3b262K66K$0.25$2.00——YesYesNoFeb 23, 2026
Qwen3.5 9BAlibabadeepinfra/qwen3.5-9b262K33K$0.10$0.15——YesYesYesFeb 23, 2026
Gemini 3.1 Pro PreviewGooglequartz/gemini-3.1-pro-preview1.05M66K$2.00$12.00$0.20—YesYesYesFeb 19, 2026
Gemini 3.1 Pro PreviewGooglegoogle-vertex/gemini-3.1-pro-preview1.05M66K$2.00$12.00$0.20—YesYesYesFeb 19, 2026
Gemini 3.1 Pro PreviewGooglegoogle-ai-studio/gemini-3.1-pro-preview1.05M66K$2.00$12.00$0.20—YesYesYesFeb 19, 2026
Qwen3.5 397B-A17BAlibabaalibaba/qwen35-397b-a17b262K66K$0.60$3.60——YesYesNoFeb 15, 2026
Qwen3.5 397B-A17BAlibabanovita/qwen35-397b-a17b262K64K$0.60$3.60——YesYesNoFeb 15, 2026
MiniMax-M2.5-highspeedMiniMaxminimax/minimax-m2.5-highspeed205K131K$0.60$2.40$0.03—YesYesNoFeb 13, 2026
GLM-5Zhipu AIalibaba/glm-5203K16K$0.57$2.58——YesYesNoFeb 12, 2026
GLM-5Zhipu AItencent/glm-5200K128K$1.00$3.20$0.20—YesYesNoFeb 12, 2026
GLM-5Zhipu AIzai/glm-5203K131K$1.00$3.20$0.20—YesYesNoFeb 12, 2026
GLM-5Zhipu AIembercloud/glm-5203K131K$0.72$2.30$0.14—YesYesNoFeb 12, 2026
GLM-5Zhipu AInovita/glm-5203K131K$1.00$3.20$0.20—YesYesNoFeb 12, 2026
MiniMax-M2.5MiniMaxminimax/minimax-m2.5205K131K$0.30$1.20$0.03—YesYesNoFeb 12, 2026
MiniMax-M2.5MiniMaxnovita/minimax-m2.5205K131K$0.30$1.20$0.03—YesYesNoFeb 12, 2026
GPT-5.3 CodexOpenAIopenai/gpt-5.3-codex400K128K$1.75$14.00$0.17—YesYesNoFeb 5, 2026
GPT-5.3 CodexOpenAIazure/gpt-5.3-codex400K128K$1.75$14.00$0.17—YesYesNoFeb 5, 2026
Qwen3 Coder NextAlibabaembercloud/qwen3-coder-next262K262K$0.11$0.68$0.06—NoYesNoFeb 3, 2026
Kimi K2.5Moonshot AIalibaba/kimi-k2.5262K98K$0.57$3.01——YesYesNoJan 27, 2026
Kimi K2.5Moonshot AImoonshot/kimi-k2.5262K33K$0.60$3.00$0.10—YesYesNoJan 27, 2026
Kimi K2.5Moonshot AIembercloud/kimi-k2.5262K262K$0.41$1.98$0.23—NoYesNoJan 27, 2026
GLM-4.7-FlashZhipu AIembercloud/glm-4.7-flash200K131K$0.06$0.40$0.01—NoYesNoJan 19, 2026
GLM-4.7-FlashXZhipu AIzai/glm-4.7-flashx200K128K$0.07$0.40$0.01—YesYesNoJan 19, 2026
MiniMax-M2.1MiniMaxminimax/minimax-m2.1197K131K$0.27$1.10——YesYesNoDec 23, 2025
MiniMax-M2.1MiniMaxnovita/minimax-m2.1205K131K$0.30$1.20$0.03—YesYesNoDec 23, 2025
MiniMax-M2.1MiniMaxminimax/minimax-m2.1-lightning197K131K$0.12$0.48——YesYesNoDec 23, 2025
GLM-4.7Zhipu AIbytedance/glm-4.7200K128K$0.60$2.20$0.11—YesYesNoDec 22, 2025
GLM-4.7Zhipu AItogether-ai/glm-4.7203K128K$0.45$2.00——YesNoNoDec 22, 2025
GLM-4.7Zhipu AIzai/glm-4.7200K128K$0.60$2.20$0.11—YesYesNoDec 22, 2025
GLM-4.7Zhipu AIembercloud/glm-4.7200K131K$0.38$1.98$0.19—YesYesNoDec 22, 2025
GLM-4.7Zhipu AIcerebras/glm-4.7200K128K$2.25$2.75——YesYesNoDec 22, 2025
GLM-4.7Zhipu AInovita/glm-4.7205K128K$0.60$2.20$0.11—YesYesNoDec 22, 2025
Seed 1.8 (251228) (ByteDance)ByteDance Seedbytedance/seed-1-8-251228256K256K$0.25$2.00$0.05—YesYesNoDec 18, 2025
Gemini 3 Flash PreviewGooglegoogle-vertex/gemini-3-flash-preview1.05M66K$0.50$3.00$0.05—YesYesYesDec 17, 2025
Gemini 3 Flash PreviewGooglegoogle-ai-studio/gemini-3-flash-preview1.05M66K$0.50$3.00$0.05—YesYesYesDec 17, 2025
GPT-5.2OpenAIopenai/gpt-5.2400K128K$1.75$14.00$0.17—YesYesYesDec 11, 2025
GPT-5.2OpenAIazure/gpt-5.2400K128K$1.75$14.00$0.17—YesYesYesDec 11, 2025
GPT-5.2 CodexOpenAIazure/gpt-5.2-codex400K128K$1.75$14.00$0.17—YesYesNoDec 11, 2025
GPT-5.2 ProOpenAIopenai/gpt-5.2-pro400K272K$21.00$168——YesYesNoDec 11, 2025
Devstral 2Mistralmistral/devstral-2512262K262K$0.40$2.00——NoNoNoDec 9, 2025
GLM-4.6VZhipu AIzai/glm-4.6v128K16K$0.30$0.90$0.05—YesYesNoDec 8, 2025
GLM-4.6VZhipu AInovita/glm-4.6v131K16K$0.30$0.90$0.06—YesYesNoDec 8, 2025
GLM-4.6V-FlashZhipu AIzai/glm-4.6v-flashx128K16K$0.04$0.40$0.004—YesYesNoDec 8, 2025
Ministral 3 14B 2512Mistralmistral/ministral-14b-2512262K262K$0.20$0.20——NoNoNoDec 2, 2025
Ministral 3 8B 2512Mistralmistral/ministral-8b-2512262K262K$0.15$0.15——NoNoNoDec 2, 2025
Ministral 3BMistralmistral/ministral-3b-2512131K131K$0.10$0.10——NoNoNoDec 2, 2025
Mistral Large (latest)Mistralmistral/mistral-large-latest128K262K$4.00$12.00——NoNoNoDec 2, 2025
Mistral Large 3Mistralmistral/mistral-large-2512262K262K$0.50$1.50——NoNoNoDec 2, 2025
DeepSeek V3.2DeepSeekbytedance/deepseek-v3.2131K33K$0.28$0.42$0.06—YesYesNoDec 1, 2025
DeepSeek V3.2DeepSeekdeepinfra/deepseek-v3.2160K66K$0.26$0.38$0.13—NoYesNoDec 1, 2025
DeepSeek V3.2DeepSeeknovita/deepseek-v3.2164K66K$0.27$0.40$0.13—YesYesNoDec 1, 2025
Claude Opus 4.5Anthropicanthropic/claude-opus-4-5-20251101200K32K$5.00$25.00$0.50$6.25YesYesYesNov 24, 2025
Claude Opus 4.5Anthropicaws-bedrock/claude-opus-4-5-20251101200K32K$5.00$25.00$0.50$6.25YesYesYesNov 24, 2025
Claude Opus 4.5Anthropicvertex-anthropic/claude-opus-4-5-20251101200K32K$5.00$25.00$0.50$6.25YesYesYesNov 24, 2025
Grok 4.1 Fast (Reasoning)xAIazure-ai-foundry/grok-4-1-fast-reasoning2M30K$0.20$0.50——YesYesNoNov 19, 2025
Grok 4.1 Fast Non-Reasoning (Azure AI Foundry)xAIazure-ai-foundry/grok-4-1-fast-non-reasoning2M30K$0.20$0.50——NoYesNoNov 19, 2025
GPT-5.1OpenAIopenai/gpt-5.1400K128K$1.25$10.00$0.13—YesYesYesNov 13, 2025
GPT-5.1OpenAIazure/gpt-5.1400K128K$1.25$10.00$0.13—YesYesYesNov 13, 2025
GPT-5.1 CodexOpenAIazure/gpt-5.1-codex400K272K$1.25$10.00——YesYesNoNov 13, 2025
GPT-5.1 Codex miniOpenAIazure/gpt-5.1-codex-mini400K128K$0.25$2.00$0.03—YesYesNoNov 13, 2025
MiniMax-M2MiniMaxminimax/minimax-m2197K131K$0.20$1.00$0.03—YesYesNoOct 27, 2025
Claude Haiku 4.5Anthropicanthropic/claude-haiku-4-5-20251001200K64K$1.00$5.00$0.10$1.25YesYesYesOct 15, 2025
Claude Haiku 4.5Anthropicaws-bedrock/claude-haiku-4-5-20251001200K64K$1.00$5.00$0.10$1.25YesYesYesOct 15, 2025
Claude Haiku 4.5 (latest)Anthropicanthropic/claude-haiku-4-5200K64K$1.00$5.00$0.10$1.25YesYesYesOct 15, 2025
Claude Haiku 4.5 (latest)Anthropicaws-bedrock/claude-haiku-4-5200K64K$1.00$5.00$0.10$1.25YesYesYesOct 15, 2025
Claude Haiku 4.5 (latest)Anthropicvertex-anthropic/claude-haiku-4-5200K64K$1.00$5.00$0.10$1.25YesYesYesOct 15, 2025
GPT-5 ProOpenAIopenai/gpt-5-pro400K272K$15.00$120——YesYesYesOct 6, 2025
Qwen3 VL 30B A3B InstructAlibabadeepinfra/qwen3-vl-30b-a3b-instruct262K33K$0.15$0.60——NoYesNoOct 4, 2025
Qwen3 VL 30B A3B InstructAlibabanovita/qwen3-vl-30b-a3b-instruct131K33K$0.20$0.70——NoYesNoOct 4, 2025
GLM-4.6Zhipu AIzai/glm-4.6200K131K$0.60$2.20$0.11—YesYesNoSep 30, 2025
GLM-4.6Zhipu AInovita/glm-4.6205K131K$0.55$2.20$0.11—YesYesNoSep 30, 2025
Claude Sonnet 4.5Anthropicanthropic/claude-sonnet-4-5-20250929200K64K$3.00$15.00$0.30$3.75YesYesYesSep 29, 2025
Claude Sonnet 4.5Anthropicaws-bedrock/claude-sonnet-4-5-20250929200K8K$3.00$15.00$0.30$3.75YesYesYesSep 29, 2025
Claude Sonnet 4.5 (latest)Anthropicanthropic/claude-sonnet-4-5200K64K$3.00$15.00$0.30$3.75YesYesYesSep 29, 2025
Claude Sonnet 4.5 (latest)Anthropicaws-bedrock/claude-sonnet-4-5200K8K$3.00$15.00$0.30$3.75YesYesYesSep 29, 2025
Claude Sonnet 4.5 (latest)Anthropicvertex-anthropic/claude-sonnet-4-5200K64K$3.00$15.00$0.30$3.75YesYesYesSep 29, 2025
Qwen3 MaxAlibabanovita/qwen3-max262K66K$0.84$3.38——NoYesNoSep 23, 2025
Qwen3 VL 235B A22B InstructAlibabadeepinfra/qwen3-vl-235b-a22b-instruct262K33K$0.20$0.88$0.11—NoYesNoSep 23, 2025
Qwen3 VL 235B A22B InstructAlibabanovita/qwen3-vl-235b-a22b-instruct131K33K$0.30$1.50——NoYesNoSep 23, 2025
Qwen3 VL 235B A22B ThinkingAlibabanovita/qwen3-vl-235b-a22b-thinking131K33K$0.98$3.95——YesNoNoSep 23, 2025
Qwen3-VL PlusAlibabaalibaba/qwen3-vl-plus262K33K$0.20$1.60$0.04$0.25NoNoNoSep 23, 2025
Seed 1.6 (250915) (ByteDance)ByteDance Seedbytedance/seed-1-6-250915256K256K$0.25$2.00$0.05—YesYesNoSep 15, 2025
Qwen PlusAlibabaalibaba/qwen-plus131K32K$0.40$1.20$0.08$0.50NoYesNoSep 11, 2025
SonarPerplexityperplexity/sonar130K4K$0.25$2.50—$0.25NoNoYesSep 1, 2025
Qwen3-Next 80B-A3B InstructAlibabanovita/qwen3-next-80b-a3b-instruct131K33K$0.15$1.50——NoYesNoSep 2025
GLM-4.5VZhipu AIzai/glm-4.5v128K16K$0.60$1.80$0.11—YesYesNoAug 11, 2025
GLM-4.5VZhipu AInovita/glm-4.5v66K16K$0.60$1.80$0.11—YesYesNoAug 11, 2025
GPT-5OpenAIopenai/gpt-5400K128K$1.25$10.00$0.13—YesYesYesAug 7, 2025
GPT-5OpenAIazure/gpt-5400K128K$1.25$10.00$0.13—YesYesYesAug 7, 2025
GPT-5 MiniOpenAIopenai/gpt-5-mini400K128K$0.25$2.00$0.03—YesYesYesAug 7, 2025
GPT-5 MiniOpenAIazure/gpt-5-mini400K128K$0.25$2.00$0.03—YesYesYesAug 7, 2025
GPT-5 NanoOpenAIopenai/gpt-5-nano400K128K$0.05$0.40$0.005—YesYesYesAug 7, 2025
GPT-5 NanoOpenAIazure/gpt-5-nano400K128K$0.05$0.40$0.005—YesYesYesAug 7, 2025
GPT OSS 120BOpenAIbytedance/gpt-oss-120b128K32K$0.10$0.50$0.02—YesYesNoAug 5, 2025
GPT OSS 120BOpenAIgroq/gpt-oss-120b131K33K$0.15$0.75——YesYesNoAug 5, 2025
GPT OSS 120BOpenAIscx-ai/gpt-oss-120b131K33K$0.17$0.55——YesYesNoAug 5, 2025
GPT OSS 120BOpenAItogether-ai/gpt-oss-120b131K33K$0.15$0.60——YesYesNoAug 5, 2025
GPT OSS 120BOpenAIrunware/gpt-oss-120b131K33K$0.03$0.14$0.03—YesYesNoAug 5, 2025
GPT OSS 120BOpenAIazure/gpt-oss-120b131K33K$0.15$0.60——YesYesNoAug 5, 2025
GPT OSS 120BOpenAIcerebras/gpt-oss-120b131K33K$0.35$0.75——YesYesNoAug 5, 2025
GPT OSS 20BOpenAIgroq/gpt-oss-20b131K33K$0.10$0.50——YesYesNoAug 5, 2025
GPT OSS 20BOpenAIconsensusprotocol/gpt-oss-20b128K33K$0.04$0.19$0.01—YesYesNoAug 5, 2025
Qwen3-Coder 30B-A3B InstructAlibabanovita/qwen3-coder-30b-a3b-instruct160K33K$0.07$0.27——NoYesNoJul 31, 2025
Codestral 25.08Mistralmistral/codestral-2508256K256K$0.30$0.90——NoNoNoJul 30, 2025
GLM-4.5Zhipu AIzai/glm-4.5128K98K$0.60$2.20$0.11—YesYesNoJul 28, 2025
GLM-4.5Zhipu AIembercloud/glm-4.5131K96K$0.60$2.20$0.11—NoYesNoJul 28, 2025
GLM-4.5 AirXZhipu AIzai/glm-4.5-airx128K128K$1.10$4.50$0.22—NoYesNoJul 28, 2025
GLM-4.5 XZhipu AIzai/glm-4.5-x128K128K$2.20$8.90$0.45—YesYesNoJul 28, 2025
GLM-4.5-AirZhipu AIzai/glm-4.5-air128K98K$0.20$1.10$0.03—NoYesNoJul 28, 2025
GLM-4.5-AirZhipu AIembercloud/glm-4.5-air131K96K$0.13$0.85$0.03—NoYesNoJul 28, 2025
Qwen FlashAlibabaalibaba/qwen-flash1M32K$0.05$0.40$0.01$0.06NoYesNoJul 28, 2025
Qwen3 Coder FlashAlibabaalibaba/qwen3-coder-flash998K66K$0.30$1.50$0.06$0.38NoYesNoJul 28, 2025
Seed 1.6 Flash (250715) (ByteDance)ByteDance Seedbytedance/seed-1-6-flash-250715256K256K$0.07$0.30$0.01—YesYesNoJul 26, 2025
Qwen3 235B A22B Thinking 2507Alibabanovita/qwen3-235b-a22b-thinking-2507131K33K$0.30$3.00——NoYesNoJul 25, 2025
Qwen3 Coder 480B A35B InstructAlibabanovita/qwen3-coder-480b-a35b-instruct262K66K$0.38$1.55——NoYesNoJul 22, 2025
Qwen3 235B A22B Instruct 2507Alibabacerebras/qwen3-235b-a22b-instruct-2507262K8K$0.60$1.20——NoYesNoJul 21, 2025
Qwen3 235B A22B Instruct 2507Alibabanovita/qwen3-235b-a22b-instruct-2507131K16K$0.09$0.58——NoYesNoJul 21, 2025
Kimi K2Moonshot AInovita/kimi-k2131K131K$0.57$2.30——NoYesNoJul 11, 2025
Grok 4xAIxai/grok-4256K256K$3.00$15.00$0.75—YesYesNoJul 9, 2025
ERNIE 4.5 VL 424B A47BBaidunovita/ernie-4.5-vl-424b-a47b123K16K$0.42$1.25——YesNoNoJun 30, 2025
Seed 1.6 (250615) (ByteDance)ByteDance Seedbytedance/seed-1-6-250615256K256K$0.25$2.00$0.05—YesYesNoJun 25, 2025
Mistral Small 3.2Mistralmistral/mistral-small-2506128K16K$0.10$0.30——NoNoNoJun 20, 2025
Qwen3 14B (greenference)Alibabagreenference/qwen3-14b16K8K$0.08$0.23——NoYesYesApr 28, 2025
Qwen3 235B-A22BAlibabanovita/qwen3-235b-a22b-fp841K20K$0.20$0.80——NoNoNoApr 28, 2025
Qwen3 30B A3BAlibabagreenference/qwen3-30b-a3b8K4K$0.10$0.28——NoNoYesApr 28, 2025
Qwen3 32BAlibabascx-ai/qwen3-32b33K8K$0.36$0.87——YesYesNoApr 28, 2025
o3OpenAIopenai/o3200K100K$2.00$8.00$0.50—NoNoYesApr 16, 2025
GLM-4 32B (0414-128k)Zhipu AIzai/glm-4-32b-0414-128k128K128K$0.10$0.10——NoYesNoApr 14, 2025
GPT-4.1OpenAIopenai/gpt-4.11M33K$2.00$8.00$0.50—NoYesYesApr 14, 2025
GPT-4.1OpenAIazure/gpt-4.11M33K$2.00$8.00$0.50—NoYesYesApr 14, 2025
GPT-4.1 miniOpenAIopenai/gpt-4.1-mini1M33K$0.40$1.60$0.10—NoYesYesApr 14, 2025
GPT-4.1 miniOpenAIazure/gpt-4.1-mini1M33K$0.40$1.60$0.10—NoYesYesApr 14, 2025
Llama 4 Maverick 17B InstructMetaaws-bedrock/llama-4-maverick-17b-instruct8K2K$0.24$0.97——NoNoNoApr 5, 2025
Llama 4 Maverick 17B InstructMetanovita/llama-4-maverick-17b-instruct1.05M8K$0.27$0.85——NoNoNoApr 5, 2025
Llama 4 Scout 17B InstructMetaaws-bedrock/llama-4-scout-17b-instruct8K2K$0.17$0.66——NoNoNoApr 5, 2025
Llama 4 Scout 17B InstructMetanovita/llama-4-scout-17b-instruct131K131K$0.18$0.59——NoNoNoApr 5, 2025
GPT-4o Mini TranscribeOpenAIopenai/gpt-4o-mini-transcribe16K2K$1.25$5.00——NoNoNoMar 20, 2025
GPT-4o TranscribeOpenAIopenai/gpt-4o-transcribe16K2K$2.50$10.00——NoNoNoMar 20, 2025
Qwen MaxAlibabaalibaba/qwen-max33K8K$1.60$6.40——NoYesNoJan 25, 2025
MiniMax Text 01MiniMaxminimax/minimax-text-011M131K$0.20$1.10——YesYesNoJan 15, 2025
Llama-3.3-70B-InstructMetacerebras/llama-3.3-70b-instruct128K4K$0.85$1.20——NoYesNoDec 6, 2024
Llama-3.3-70B-InstructMetanovita/llama-3.3-70b-instruct131K120K$0.14$0.40——NoYesNoDec 6, 2024
Llama 3.2 11B Instruct (Inference.net)Metainference.net/llama-3.2-11b-instruct128K128K$0.07$0.33——NoNoNoSep 25, 2024
Llama 3.2 3B InstructMetanovita/llama-3.2-3b-instruct33K32K$0.03$0.05——NoNoNoSep 18, 2024
Qwen Plus Latest (Alibaba Cloud)Alibabaalibaba/qwen-plus-latest1M32K$0.40$1.20$0.08$0.50NoYesNoSep 9, 2024
GPT-4oOpenAIopenai/gpt-4o128K16K$2.50$10.00$1.25—NoYesYesAug 6, 2024
GPT-4oOpenAIazure/gpt-4o128K16K$2.50$10.00$1.25—NoYesNoAug 6, 2024
Llama 3.1 70B InstructMetaaws-bedrock/llama-3.1-70b-instruct128K2K$0.72$0.72——NoNoNoJul 23, 2024
GPT-4o miniOpenAIopenai/gpt-4o-mini128K16K$0.15$0.60$0.07—NoYesYesJul 18, 2024
Llama 3 70B InstructMetanovita/llama-3-70b-instruct8K8K$0.51$0.74——NoNoNoApr 18, 2024