AllocateModel catalog
Every model, one key.
172 models behind one key: language, image, video, speech, and embedding. Provider list prices shown split by input and output.
Start here
The models most teams route first, with notes.
FrontierGemini 3.5 Flash
Google · 1M context · Proprietary API
The workhorse for high-volume routes.
$1.50 / M in · $9 / M outDetails →
FrontierDeepSeek V4
DeepSeek · 512K context · Proprietary API
Frontier-class reasoning at a mid-tier price.
$1.74 / M in · $3.48 / M outDetails →
FrontierGPT-5.5
OpenAI · 400K context · Proprietary API
Broad capability, strong tool use.
$5 / M in · $30 / M outDetails →
FrontierClaude Sonnet 5
Anthropic · 1M context · Proprietary API
Careful reasoning for judgment calls.
$3 / M in · $15 / M outDetails →
Fine-tunableLlama 4 Scout
Open weight · 1M context · Llama community
Open weights with a 1M-token window.
$0.18 / M in · $0.59 / M outDetails →
Fine-tunableQwen 3.5
Open weight · 256K context · Apache 2.0
Strong multilingual, Apache 2.0.
$0.60 / M in · $3.60 / M outDetails →
The full catalog
Provider list prices per unit · checked 2026-07-21 · one key, one route name.Language88
AArize AI Qwen 2 1.5B InstructOpenTogethercomputer32KNot listed$0.10$0.10Claude Opus 4.8Anthropic200KProprietary API$5$25Claude Sonnet 5Anthropic1MProprietary API$3$15CCogito v2.1 671BOpenDeepcogito160KNot listed$1.25$1.25Deepseek Coder 33B InstructOpenDeepseek16KCustom license$0.80$0.80DeepSeek R1 0528 NVFP4OpenDeepseek160KMIT$3$7DeepSeek R1 Distill Llama 70BOpenDeepSeek128KMIT$2$2DeepSeek R1 Distill Qwen 1.5BOpenDeepSeek128KMIT$0.18$0.18DeepSeek R1 Distill Qwen 14BOpenDeepSeek128KMIT$1.60$1.60Deepseek V3.1 NVFP4OpenDeepSeek128KMIT$0.60$1.70DeepSeek V4 FlashOpenDeepseek1MNot listed$0.14$0.28Deepseek V4 ProDeepseek512KProprietary API$1.74$3.48Gemini 3.1 ProGoogle1MProprietary API$2$12Gemini 3.5 FlashGoogle1MProprietary API$1.50$9Gemini 3.6 FlashGoogle1MProprietary API$1.50$7.50Gemma 3N E4B InstructOpenGoogle32KGemma terms$0.06$0.12Gemma 4 31B-it FP8OpenGoogle256KApache 2.0$0.39$0.97Gemma-2 Instruct (27B)OpenGoogle8KGemma terms$0.80$0.80GGLM 4.5 AirOpenZ.ai128KMIT$0.20$1.10GGlm 4.5 Air Fp8OpenZai Org128KMIT$0.20$1.10GGLM 4.6 Fp8OpenZai Org198KMIT$0.60$2.20GGLM 4.7 FP8OpenZai Org198KMIT$0.45$2GGLM 5 Fp4OpenZai Org198KNot listed$1$3.20GGLM 5.1 FP4OpenZai Org198KNot listed$1.40$4.40GGLM 5.2OpenZai Org256KNot listed$1.40$4.40GPT-5.5OpenAI400KProprietary API$5$30GPT-5.6 LunaOpenAI1MProprietary API$0.20$1.20
Grok 4.20 Multi-agentSpaceXAI1MProprietary API$1.25$2.50Grok 4.20 Non-reasoningSpaceXAI1MProprietary API$1.25$2.50Grok 4.20 ReasoningSpaceXAI1MProprietary API$1.25$2.50Grok 4.3SpaceXAI1MProprietary API$1.25$2.50Grok 4.5SpaceXAI500KProprietary API$2$6Grok 4.6SpaceXAI500KProprietary API$2$6Grok Build 0.1SpaceXAI256KProprietary API$1$2
Inkling FP4OpenThinking Machines512KApache 2.0$1$4.05
Kimi K2.5 Fp4OpenTogethercomputer256KNot listed$0.50$2.80Kimi K2.6 Fp4OpenMoonshot AI256KNot listed$1.20$4.50Kimi K2.7 CodeOpenMoonshot AI256KNot listed$0.95$4Kimi K3OpenMoonshot AI1MNot listed$3$15LLFM2.5-8B-A1BOpenLiquidAI128KCustom license$0.03$0.12
Llama 3.1 Nemotron 70B Instruct HFOpennvidia32KLlama community$0.88$0.88Llama 4 Scout Instruct (17Bx16E)OpenMeta1MLlama community$0.18$0.59Llama Guard 4 12BOpenMeta1MLlama community$0.20$0.20Meta Llama 3 70B Instruct TurboOpenMeta8KLlama community$0.88$0.88Meta Llama 3 8B InstructOpenMeta8KLlama community$0.20$0.20Meta Llama 3 8B Instruct ReferenceOpenMeta8KLlama community$0.20$0.20Meta Llama 3.1 405B InstructOpenMeta4KLlama community$3.50$3.50Meta Llama 3.1 70B Instruct TurboOpenMeta128KLlama community$0.88$0.88Meta Llama 3.1 8BOpenMeta16KLlama community$0.20$0.20Meta Llama 3.1 8B Instruct TurboOpenMeta128KLlama community$0.18$0.18Meta Llama 3.2 1B InstructOpenMeta128KLlama community$0.06$0.06Meta Llama 3.2 3B InstructOpenMeta128KLlama community$0.06$0.06Meta Llama 3.3 70B Instruct TurboOpenMeta128KLlama community$1.04$1.04MMiniMax M2.7 FP4OpenMiniMaxAI192KNot listed$0.30$1.20MMiniMax M3MiniMaxAI512KProprietary API$0.30$1.20
Ministral 3 14B Instruct 2512OpenMistralai256KApache 2.0$0.20$0.20Mistral (7B) Instruct v0.1Openmistralai32KApache 2.0$0.20$0.20Mistral (7B) Instruct v0.3Openmistralai32KApache 2.0$0.20$0.20Mistral Small (24B) Instruct 25.01Openmistralai32KApache 2.0$0.10$0.30Mixtral-8x7B Instruct v0.1Openmistralai32KApache 2.0$0.60$0.60NNous Hermes 2 Mixtral 8X7B DpoOpenNousresearch32KApache 2.0$0.60$0.60NVIDIA Nemotron 3 Ultra 550B A55B NVFP4NVIDIA512KProprietary API$0.60$3.60Nvidia Nemotron Nano 9B V2OpenNvidia128KCustom license$0.06$0.25OpenAI GPT-OSS 120BOpenOpenAI128KCustom license$0.15$0.60OpenAI GPT-OSS 20BOpenOpenAI128KApache 2.0$0.05$0.20PPearl-ai Gemma-4-31B-it-pearlOpenpearl.ai256KNot listed$0.28$0.86Qwen 2 Instruct (1.5B)OpenQwen32KQwen license$0.02$0.02Qwen 2.5 14B InstructOpenQwen32KApache 2.0$0.80$0.80Qwen 2.5 Coder 32B InstructOpenQwen16KQwen license$0.80$0.80Qwen QwQ-32BOpenQwen128KQwen license$1.20$1.20Qwen2 72B InstructOpenTogethercomputer32KQwen license$0.90$0.90Qwen2-VL (72B) InstructOpenQwen32KQwen license$1.20$1.20Qwen2.5 72B InstructOpenQwen32KQwen license$1.20$1.20Qwen2.5 72B Instruct TurboOpenQwen128KQwen license$1.20$1.20Qwen2.5 7B Instruct TurboOpenQwen32KQwen license$0.30$0.30Qwen2.5-VL (72B) InstructOpenQwen32KQwen license$1.95$8Qwen3 Coder 480B A35B Instruct Fp8OpenQwen256KApache 2.0$2$2Qwen3 Coder Next Fp8OpenQwen256KApache 2.0$0.50$1.20Qwen3 Next 80B A3b InstructOpenQwen256KApache 2.0$0.15$1.50Qwen3 Next 80B A3b ThinkingOpenQwen256KApache 2.0$0.15$1.50Qwen3-VL-32B-InstructOpenQwen256KApache 2.0$0.50$1.50Qwen3-VL-8B-InstructOpenQwen256KApache 2.0$0.18$0.68Qwen3.5 397B A17bOpenQwen256KApache 2.0$0.60$3.60Qwen3.5 9B FP8OpenQwen256KNot listed$0.17$0.25Qwen3.6 PlusQwen1MProprietary API$0.50$3Qwen3.7 MaxQwen1MProprietary API$1.25$3.75Qwen3.7 PlusQwen1MProprietary API$0.32$1.28TTrinity MiniOpenArcee AI128KNot listed$0.045$0.15
Claude Opus 4.8Anthropic200KProprietary API$5$25Claude Sonnet 5Anthropic1MProprietary API$3$15CCogito v2.1 671BOpenDeepcogito160KNot listed$1.25$1.25Deepseek Coder 33B InstructOpenDeepseek16KCustom license$0.80$0.80DeepSeek R1 0528 NVFP4OpenDeepseek160KMIT$3$7DeepSeek R1 Distill Llama 70BOpenDeepSeek128KMIT$2$2DeepSeek R1 Distill Qwen 1.5BOpenDeepSeek128KMIT$0.18$0.18DeepSeek R1 Distill Qwen 14BOpenDeepSeek128KMIT$1.60$1.60Deepseek V3.1 NVFP4OpenDeepSeek128KMIT$0.60$1.70DeepSeek V4 FlashOpenDeepseek1MNot listed$0.14$0.28Deepseek V4 ProDeepseek512KProprietary API$1.74$3.48Gemini 3.1 ProGoogle1MProprietary API$2$12Gemini 3.5 FlashGoogle1MProprietary API$1.50$9Gemini 3.6 FlashGoogle1MProprietary API$1.50$7.50Gemma 3N E4B InstructOpenGoogle32KGemma terms$0.06$0.12Gemma 4 31B-it FP8OpenGoogle256KApache 2.0$0.39$0.97Gemma-2 Instruct (27B)OpenGoogle8KGemma terms$0.80$0.80GGLM 4.5 AirOpenZ.ai128KMIT$0.20$1.10GGlm 4.5 Air Fp8OpenZai Org128KMIT$0.20$1.10GGLM 4.6 Fp8OpenZai Org198KMIT$0.60$2.20GGLM 4.7 FP8OpenZai Org198KMIT$0.45$2GGLM 5 Fp4OpenZai Org198KNot listed$1$3.20GGLM 5.1 FP4OpenZai Org198KNot listed$1.40$4.40GGLM 5.2OpenZai Org256KNot listed$1.40$4.40GPT-5.5OpenAI400KProprietary API$5$30GPT-5.6 LunaOpenAI1MProprietary API$0.20$1.20Grok 4.20 Multi-agentSpaceXAI1MProprietary API$1.25$2.50Grok 4.20 Non-reasoningSpaceXAI1MProprietary API$1.25$2.50Grok 4.20 ReasoningSpaceXAI1MProprietary API$1.25$2.50Grok 4.3SpaceXAI1MProprietary API$1.25$2.50Grok 4.5SpaceXAI500KProprietary API$2$6Grok 4.6SpaceXAI500KProprietary API$2$6Grok Build 0.1SpaceXAI256KProprietary API$1$2Inkling FP4OpenThinking Machines512KApache 2.0$1$4.05Kimi K2.5 Fp4OpenTogethercomputer256KNot listed$0.50$2.80Kimi K2.6 Fp4OpenMoonshot AI256KNot listed$1.20$4.50Kimi K2.7 CodeOpenMoonshot AI256KNot listed$0.95$4Kimi K3OpenMoonshot AI1MNot listed$3$15LLFM2.5-8B-A1BOpenLiquidAI128KCustom license$0.03$0.12Llama 3.1 Nemotron 70B Instruct HFOpennvidia32KLlama community$0.88$0.88Llama 4 Scout Instruct (17Bx16E)OpenMeta1MLlama community$0.18$0.59Llama Guard 4 12BOpenMeta1MLlama community$0.20$0.20Meta Llama 3 70B Instruct TurboOpenMeta8KLlama community$0.88$0.88Meta Llama 3 8B InstructOpenMeta8KLlama community$0.20$0.20Meta Llama 3 8B Instruct ReferenceOpenMeta8KLlama community$0.20$0.20Meta Llama 3.1 405B InstructOpenMeta4KLlama community$3.50$3.50Meta Llama 3.1 70B Instruct TurboOpenMeta128KLlama community$0.88$0.88Meta Llama 3.1 8BOpenMeta16KLlama community$0.20$0.20Meta Llama 3.1 8B Instruct TurboOpenMeta128KLlama community$0.18$0.18Meta Llama 3.2 1B InstructOpenMeta128KLlama community$0.06$0.06Meta Llama 3.2 3B InstructOpenMeta128KLlama community$0.06$0.06Meta Llama 3.3 70B Instruct TurboOpenMeta128KLlama community$1.04$1.04MMiniMax M2.7 FP4OpenMiniMaxAI192KNot listed$0.30$1.20MMiniMax M3MiniMaxAI512KProprietary API$0.30$1.20Ministral 3 14B Instruct 2512OpenMistralai256KApache 2.0$0.20$0.20Mistral (7B) Instruct v0.1Openmistralai32KApache 2.0$0.20$0.20Mistral (7B) Instruct v0.3Openmistralai32KApache 2.0$0.20$0.20Mistral Small (24B) Instruct 25.01Openmistralai32KApache 2.0$0.10$0.30Mixtral-8x7B Instruct v0.1Openmistralai32KApache 2.0$0.60$0.60NNous Hermes 2 Mixtral 8X7B DpoOpenNousresearch32KApache 2.0$0.60$0.60NVIDIA Nemotron 3 Ultra 550B A55B NVFP4NVIDIA512KProprietary API$0.60$3.60Nvidia Nemotron Nano 9B V2OpenNvidia128KCustom license$0.06$0.25OpenAI GPT-OSS 120BOpenOpenAI128KCustom license$0.15$0.60OpenAI GPT-OSS 20BOpenOpenAI128KApache 2.0$0.05$0.20PPearl-ai Gemma-4-31B-it-pearlOpenpearl.ai256KNot listed$0.28$0.86Qwen 2 Instruct (1.5B)OpenQwen32KQwen license$0.02$0.02Qwen 2.5 14B InstructOpenQwen32KApache 2.0$0.80$0.80Qwen 2.5 Coder 32B InstructOpenQwen16KQwen license$0.80$0.80Qwen QwQ-32BOpenQwen128KQwen license$1.20$1.20Qwen2 72B InstructOpenTogethercomputer32KQwen license$0.90$0.90Qwen2-VL (72B) InstructOpenQwen32KQwen license$1.20$1.20Qwen2.5 72B InstructOpenQwen32KQwen license$1.20$1.20Qwen2.5 72B Instruct TurboOpenQwen128KQwen license$1.20$1.20Qwen2.5 7B Instruct TurboOpenQwen32KQwen license$0.30$0.30Qwen2.5-VL (72B) InstructOpenQwen32KQwen license$1.95$8Qwen3 Coder 480B A35B Instruct Fp8OpenQwen256KApache 2.0$2$2Qwen3 Coder Next Fp8OpenQwen256KApache 2.0$0.50$1.20Qwen3 Next 80B A3b InstructOpenQwen256KApache 2.0$0.15$1.50Qwen3 Next 80B A3b ThinkingOpenQwen256KApache 2.0$0.15$1.50Qwen3-VL-32B-InstructOpenQwen256KApache 2.0$0.50$1.50Qwen3-VL-8B-InstructOpenQwen256KApache 2.0$0.18$0.68Qwen3.5 397B A17bOpenQwen256KApache 2.0$0.60$3.60Qwen3.5 9B FP8OpenQwen256KNot listed$0.17$0.25Qwen3.6 PlusQwen1MProprietary API$0.50$3Qwen3.7 MaxQwen1MProprietary API$1.25$3.75Qwen3.7 PlusQwen1MProprietary API$0.32$1.28TTrinity MiniOpenArcee AI128KNot listed$0.045$0.15Image31
ByteDance Seedream 3.0ByteDancen/aProprietary API$0.018/ itemByteDance Seedream 4.0ByteDancen/aProprietary API$0.03/ itemByteDance Seedream 5.0 LiteByteDancen/aProprietary API$0.035/ itemFFLUX.1 Kontext [max]Black Forest Labsn/aProprietary API$0.08/ megapixelFFLUX.1 Kontext [pro]Black Forest Labsn/aProprietary API$0.04/ megapixelFFLUX.1 SchnellOpenBlack Forest Labsn/aNot listed$0.0027/ megapixelFFLUX.2 [dev]Black Forest Labsn/aProprietary API$0.015/ itemFFLUX.2 [flex]Black Forest Labsn/aProprietary API$0.03/ itemFFLUX.2 [max]Black Forest Labsn/aProprietary API$0.07/ megapixelFFLUX.2 [pro]Black Forest Labsn/aProprietary API$0.03/ itemFFLUX1.1 [pro]OpenBlack Forest Labsn/aNot listed$0.04/ megapixelGemini 3 (Nano Banana Pro)Googlen/aProprietary API$0.13/ itemGemini 3.1 Flash Image (Nano Banana 2)Googlen/aProprietary API$0.047/ itemGemini 3.1 Flash-Lite Image (Nano Banana 2 Lite)Googlen/aProprietary API$0.069/ itemGemini Flash Image 2.5 (Nano Banana)Googlen/aProprietary API$0.039/ itemGoogle Imagen 4.0 FastGooglen/aProprietary API$0.02/ itemGoogle Imagen 4.0 PreviewGooglen/aProprietary API$0.04/ itemGoogle Imagen 4.0 UltraGooglen/aProprietary API$0.06/ itemGPT Image 1.5OpenAIn/aProprietary API$0.034/ itemGPT Image 2OpenAIn/aProprietary API$0.053/ itemGrok Imagine ImageSpaceXAIn/aProprietary API$0.02/ itemGrok Imagine Image 2.0SpaceXAIn/aProprietary API$0.04/ itemIIdeogram 3.0ideogramn/aProprietary API$0.06/ itemIIdeogram 4.0ideogramn/aProprietary API$0.06/ itemJJuggernaut Lightning Flux by RunDiffusionRunDiffusionn/aProprietary API$0.0017/ itemJJuggernaut Pro Flux by RunDiffusion 1.0.0RunDiffusionn/aProprietary API$0.0049/ itemQwen ImageQwenn/aProprietary API$0.0058/ itemQwen Image 2.0Qwenn/aProprietary API$0.035/ itemQwen Image 2.0 ProQwenn/aProprietary API$0.075/ itemSSD XLstabilityain/aProprietary API$0.0019/ itemWWan 2.6 ImageWan-AIn/aProprietary API$0.03/ itemVideo37
ByteDance Seedance 1.0 LiteByteDancen/aProprietary API$0.14/ videoByteDance Seedance 1.0 ProByteDancen/aProprietary API$0.56/ videoByteDance Seedance 2.0ByteDancen/aProprietary API$0.16/ videoDuplicate TestGooglen/aProprietary API$0.08/ videoGoogle Veo 2.0Googlen/aProprietary API$2.50/ videoGoogle Veo 3.0 + AudioGooglen/aProprietary API$3.20/ videoGoogle Veo 3.0 FastGooglen/aProprietary API$0.80/ videoGoogle Veo 3.0 Fast + AudioGooglen/aProprietary API$1.20/ videoGrok Imagine VideoSpaceXAIn/aProprietary API$0.05/ videoGrok Imagine Video 1.5SpaceXAIn/aProprietary API$0.08/ video
HappyHorse 1.0 I2VAlibaban/aProprietary API$0.24/ videoHappyHorse 1.0 R2VAlibaban/aProprietary API$0.24/ videoHappyHorse 1.0 T2VAlibaban/aProprietary API$0.24/ videoHappyHorse 1.1 I2VAlibaban/aProprietary API$0.14/ videoHappyHorse 1.1 R2VAlibaban/aProprietary API$0.14/ videoHappyHorse 1.1 T2VAlibaban/aProprietary API$0.14/ videoHHappyHorse-1.0-T2Vhappyhorsen/aProprietary API$0.10/ video
Kling 1.6 StandardkwaivgIn/aProprietary API$0.18/ videoKling 2.1 MasterkwaivgIn/aProprietary API$0.92/ videoKling 2.1 ProkwaivgIn/aProprietary API$0.32/ videoKling 2.1 StandardkwaivgIn/aProprietary API$0.18/ videoMMiniMax Hailuo 02MiniMaxAIn/aProprietary API$0.56/ videoPPixVerse v5PixVersen/aProprietary API$0.30/ videoPPixVerse v5.6PixVersen/aProprietary API$0.13/ videoPPixVerse v6PixVersen/aProprietary API$0.09/ videoSora 2OpenAIn/aProprietary API$0.80/ videoSora 2 ProOpenAIn/aProprietary API$3/ videoVeo 3.1Googlen/aProprietary API$0.08/ videoVeo 3.1 Debug TestGooglen/aProprietary API$0.08/ videoVeo 3.1 LiteGooglen/aProprietary API$0.05/ videoVVidu 2.0Vidun/aProprietary API$0.80/ videoVVidu Q1Vidun/aProprietary API$0.22/ videoVVidu Q3Vidun/aProprietary API$0.098/ videoVVidu Q3 TurboVidun/aProprietary API$0.20/ videoWWan 2.7 I2VWan-AIn/aProprietary API$0.10/ videoWWan 2.7 R2VWan-AIn/aProprietary API$0.10/ videoWWan 2.7 T2VWan-AIn/aProprietary API$0.10/ videoSpeech6
CCartesia SonicCartesian/aProprietary API$65/ M charactersCCartesia Sonic 2Cartesia448Proprietary API$65/ M charactersCCartesia Sonic 3Cartesia448Proprietary API$65/ M charactersKKokoro 82MOpenHexgradn/aApache 2.0$4/ M charactersOOrpheus 3B 0.1 FTOpenCanopy Labsn/aApache 2.0$15/ M charactersRRime Labs Arcana v2Rime Labsn/aProprietary API$0.27/ M characters
Transcription7
Deepgram FluxDeepgram448Proprietary API$0.0015/ minuteDeepgram Nova 3Deepgram448Proprietary API$0.0015/ minuteDeepgram Nova 3 MultilingualDeepgram448Proprietary API$0.0015/ minuteNvidia Nemotron 3 ASR Streaming 0.6BOpenNvidia448Apache 2.0$0.0015/ minuteNvidia Nemotron 3.5 ASR Streaming 0.6BOpenNvidia448Apache 2.0$0.0015/ minuteNvidia Parakeet TDT 0.6B V3OpenNvidia448Not listed$0.0015/ minuteWhisper large-v3OpenOpenAIn/aApache 2.0$0.0015/ minute