Chat models under $1 per 1M tokens

Every chat model whose cheapest direct price blends to less than a dollar per million tokens, cheapest first. Price alone says nothing about quality: where Epoch AI publishes a Capabilities Index it is shown, and Quality against price plots the two together.

Rule: chat models attributed to a known creator, with a headline-eligible cheapest direct price (paid, not a gateway, not deprecated, not flagged by the price-sanity check) with both an input and an output price, that blends 3 input : 1 output to more than $0 and less than $1 per 1M tokens. Sorted by that blend. 617 models match; 68 of them have an Epoch Capabilities Index. Data generated 2026-10-20 03:37 UTC.

617 shown

Chat models under $1 per 1M tokens, cheapest first
#ModelBlended /1MIn /1MOut /1MCheapest atECI
1Ambient Smallambient$0.001$0.001$0.001Ambientnot evaluated
2flux-1-dev-controlnet-unionBlack Forest Labs$0.001$0.001$0.001Fireworks AInot evaluated
3qwen3.8-27b-4qUnsloth$0.001$0.001$0.001Ambientnot evaluated
4Qwen2.5-Coder 7B InstructAlibaba (Qwen)$0.015$0.01$0.03nscalenot evaluated
5Qwen2.5-Coder-3B-InstructAlibaba (Qwen)$0.015$0.01$0.03nscalenot evaluated
6Qwen2.5-Coder-7BAlibaba (Qwen)$0.015$0.01$0.03Nebius Token Factorynot evaluated
7Mistral NemoMistral AI$0.0178$0.0166$0.0216IO.NET118.7 ± 5.3
8Llama 3.2 1b InstructMeta$0.02$0.02$0.02Novita AInot evaluated
9Llama 3.2 3B InstructMeta$0.02$0.02$0.02Deep Infranot evaluated
10PaddleOCR VLBaidu$0.02$0.02$0.02Novita AInot evaluated
11qwen2-1-5b-instructAlibaba (Qwen)$0.02$0.02$0.02Together AInot evaluated
12Mistral Nemo Instruct 2407Mistral AI$0.0218$0.019$0.03Deep Infranot evaluated
13DeepSeek R1 Distill Llama 8BDeepSeek$0.025$0.025$0.025nscalenot evaluated
14Gemma 3n E4b ItGoogle$0.025$0.02$0.04Together AI (via Hugging Face)not evaluated
15Llama 3.1 8B InstructMeta$0.0275$0.02$0.05Novita AInot evaluated
16GPT OSS 20BOpenAI$0.0284$0.0145$0.07Darkbloom137.8 ± 3.3
17Gemma 2 2b ItGoogle$0.03$0.02$0.06Nebius Token Factory (via Hugging Face)not evaluated
18Llama 3.1 8B InstructMeta$0.035$0.03$0.05llamagatenot evaluated
19Llama 3.1 Instruct (8B)Meta$0.04$0.04$0.04Novita AI (via Hugging Face)not evaluated
20Ministral 3BMistral AI$0.04$0.04$0.04Mistral118.1 ± 8.3
21Voxtral Mini 3B 2507Mistral AI$0.04$0.04$0.04Amazon Bedrocknot evaluated
22Granite 4.0 H MicroIBM$0.0408$0.017$0.112Cloudflare Workers AInot evaluated
23Gemma 3 4B ITGoogle$0.0425$0.04$0.05Parasailnot evaluated
24gemma3-4bGoogle$0.0425$0.03$0.08llamagatenot evaluated
25L3-8B-Lunaris-v1Sao10K$0.0425$0.04$0.05Deep Infranot evaluated
26Llama 3 8B LunarisSao10K$0.0425$0.04$0.05Deep Infranot evaluated
27Nemotron 3 Nano Omni 30B TEENVIDIA$0.0428$0.0245$0.0978Chutesnot evaluated
28Nex-N2.5-MiniNex AGI$0.0438$0.025$0.10Nex AGInot evaluated
29Nova MicroAmazon$0.0475$0.03$0.10SAP AI Corenot evaluated
30Qwen3.5 4BAlibaba (Qwen)$0.0475$0.04$0.07EmpirioLabs AInot evaluated
31Nemotron 3.5 Lightning 30B A3BNVIDIA$0.0488$0.025$0.12Darkbloomnot evaluated
32Llama 3.2 11b Vision InstructMeta$0.049$0.049$0.049Deep Infranot evaluated
33Gemma 4 E2B ITGoogle$0.05$0.04$0.08Amazon Bedrocknot evaluated
34gemma-4-e2bGoogle$0.05$0.04$0.08Amazon Bedrock (mantle)not evaluated
35Llama-3.2-3BMeta$0.05$0.04$0.08llamagatenot evaluated
36Qwen2.5 7B InstructAlibaba (Qwen)$0.05$0.05$0.05SiliconFlownot evaluated
37Sao10K Stheno 8bSao10K$0.05$0.05$0.05Novita AInot evaluated
38Qwen-VL OCRAlibaba (Qwen)$0.0503$0.043$0.072Alibaba (China)not evaluated
39nemotron-3-5-lightning-30b-a3bPerplexity$0.0511$0.0115$0.17Perplexitynot evaluated
40Qwen3.7 FlashAlibaba (Qwen)$0.0518$0.0296$0.119Alibaba (China)144.6 ± 2.3
41LFM2 24B A2BLiquid AI$0.0525$0.03$0.12Together AInot evaluated
42Mistral Nemo 12B InstructMistral AI$0.0535$0.038$0.10Inferencenot evaluated
43qwen-2-7b-instructAlibaba (Qwen)$0.054$0.054$0.054Novita AInot evaluated
44Qwen TurboAlibaba (Qwen)$0.0548$0.044$0.087Alibaba (China)not evaluated
45Llama Guard 3 8BMeta$0.055$0.055$0.055Deep Infranot evaluated
46DeepSeek V4 Flash LatestDeepSeek$0.0563$0.045$0.09engy154.5 ± 2.1
47Meta Llama 3.1 8B InstantMeta$0.0575$0.05$0.08Groqnot evaluated
48Mistral Small 3Mistral AI$0.0575$0.05$0.08Mistralnot evaluated
49Mistral 7B InstructMistral AI$0.059$0.059$0.059Novita AInot evaluated
50GPT-OSS 120BOpenAI$0.06$0.03$0.15NEAR AI Cloud140 ± 3.2
51Qwen3 8BAlibaba (Qwen)$0.06$0.06$0.06SiliconFlow136.2 ± 3.7
52AutoGLM Phone 9B MultilingualZ.ai (Zhipu AI)$0.0608$0.035$0.138Novita AInot evaluated
53Gemma 3 12B ITGoogle$0.0625$0.05$0.10Novita AInot evaluated
54gemma-4-26bGoogle$0.0638$0.03$0.165Darkbloomnot evaluated
55Command R7BCohere$0.0656$0.0375$0.15Coherenot evaluated
56Command R7B ArabicCohere$0.0656$0.0375$0.15Coherenot evaluated
57DeepSeek R1 0528 Qwen3 8BDeepSeek$0.0675$0.06$0.09Novita AInot evaluated
58Mercury 2.5Inception$0.0675$0.04$0.15Inceptionnot evaluated
59Qwen 3.5 9B (Q4_K_M)Alibaba (Qwen)$0.0675$0.04$0.15CrofAI139.4 ± 2.5
60Baichuan M2 32BBaichuan AI$0.07$0.07$0.07Novita AInot evaluated
61DeepSeek R1 Distill Qwen 14BDeepSeek$0.07$0.07$0.07nscale135.4 ± 5.2
62gemma-7b-itGoogle$0.07$0.07$0.07Groqnot evaluated
63nvidia-nemotron-nano-9b-v2NVIDIA$0.07$0.04$0.16Deep Infranot evaluated
64Qwen FlashAlibaba (Qwen)$0.0705$0.022$0.216Alibaba (China)not evaluated
65Trinity MiniArcee AI$0.0713$0.045$0.15Together AInot evaluated
66Seed 1.6 FlashByteDance Seed$0.0724$0.0223$0.223Volcengine Arknot evaluated
67deepseek-coder-6-7bDeepSeek$0.075$0.06$0.12llamagatenot evaluated
68Nemotron 3.5 Content SafetyNVIDIA$0.075$0.05$0.15Vultrnot evaluated
69Hy-MT2-1.8BTencent$0.0773$0.044$0.177Tencentnot evaluated
70Tongyi Intent Detect V3Alibaba (Qwen)$0.0795$0.058$0.144Alibaba (China)not evaluated
71granite-3-3-8b-instructIBM$0.085$0.03$0.25replicatenot evaluated
72Gemma 4 26B A4B ITGoogle$0.0865$0.042$0.22Darkbloomnot evaluated
73DeepSeek V4 FlashDeepSeek$0.0875$0.07$0.14StreamLake146.1 ± 2.2
74MythoMax 13Bgryphe$0.0875$0.08$0.11Parasailnot evaluated
75nemotron-3-nano-30b-a3bNVIDIA$0.0875$0.05$0.20Crusoenot evaluated
76nemotron-lightning-3p5-30b-a3bNVIDIA$0.0875$0.05$0.20Fireworks AInot evaluated
77Phi-4Microsoft$0.0875$0.07$0.14Deep Infranot evaluated
78DeepSeek R1 Distill Qwen 1.5BDeepSeek$0.09$0.09$0.09nscalenot evaluated
79DeepSeek R1 Distill Qwen 7BDeepSeek$0.09$0.072$0.144Alibaba (China)not evaluated
80Ling 3.0 FlashinclusionAI$0.09$0.06$0.18Deep Infranot evaluated
81Ling 3.0 Flash VLinclusionAI$0.09$0.06$0.18Deep Infranot evaluated
82ling-3-0-flash-fastinclusionAI$0.09$0.06$0.18Novita AInot evaluated
83Qwen 2.5 VL 32B InstructAlibaba (Qwen)$0.0925$0.05$0.22IO.NETnot evaluated
84Qwen3.5 FlashAlibaba (Qwen)$0.0935$0.029$0.287Alibaba (China)not evaluated
85Qwen2.5-Coder 32B InstructAlibaba (Qwen)$0.095$0.06$0.20nscalenot evaluated
86Seed 2.0 MiniByteDance Seed$0.0965$0.0297$0.297Volcengine Arknot evaluated
87deepseek-r1-7b-qwenDeepSeek$0.0975$0.08$0.15llamagatenot evaluated
88deepseek-coder-1b-baseDeepSeek$0.10$0.10$0.10Fireworks AInot evaluated
89ernie-4-5-300b-a47b-ptBaidu$0.10$0.10$0.10Fireworks AInot evaluated
90ERNIE-4.5-21B-A3B-PTBaidu$0.10$0.10$0.10Fireworks AInot evaluated
91Gemma 3 27BGoogle$0.10$0.08$0.16Deep Infranot evaluated
92gemma-2b-itGoogle$0.10$0.10$0.10Fireworks AInot evaluated
93GLM-4 32B (0414-128k)Z.ai (Zhipu AI)$0.10$0.10$0.10Z.AInot evaluated
94granite-guardian-3-2-2bIBM$0.10$0.10$0.10watsonx.ainot evaluated
95granite-vision-3-2-2bIBM$0.10$0.10$0.10watsonx.ainot evaluated
96llama-2-7bMeta$0.10$0.05$0.25replicate99.2 ± 8.6
97llama-3-8bMeta$0.10$0.05$0.25replicate116.5 ± 5.8
98llama-guard-3-1bMeta$0.10$0.10$0.10Fireworks AInot evaluated
99llama-v2-70bMeta$0.10$0.10$0.10Fireworks AInot evaluated
100llama-v3-1-405b-instruct-longMeta$0.10$0.10$0.10Fireworks AInot evaluated
101llama-v3-1-70b-instruct-1bMeta$0.10$0.10$0.10Fireworks AInot evaluated
102llama-v3-1-8b-instructMeta$0.10$0.10$0.10Fireworks AInot evaluated
103llama-v3-2-1bMeta$0.10$0.10$0.10Fireworks AInot evaluated
104llama-v3-2-1b-instructMeta$0.10$0.10$0.10Fireworks AInot evaluated
105llama-v3-2-3bMeta$0.10$0.10$0.10Fireworks AInot evaluated
106llama-v3-2-3b-instructMeta$0.10$0.10$0.10Fireworks AInot evaluated
107Ministral 3 3BMistral AI$0.10$0.10$0.10Mistralnot evaluated
108Ministral 8BMistral AI$0.10$0.10$0.10Mistralnot evaluated
109mistral-7b-instruct-v0.2Mistral AI$0.10$0.05$0.25replicatenot evaluated
110Mistral-7B-Instruct-v0.3Mistral AI$0.10$0.10$0.10OVHcloud AI Endpointsnot evaluated
111mistral-7b-v0-1Mistral AI$0.10$0.05$0.25replicate112.3 ± 6.6
112nemotron-nano-v2-12b-vlNVIDIA$0.10$0.10$0.10Fireworks AInot evaluated
113phi-2-3bMicrosoft$0.10$0.10$0.10Fireworks AInot evaluated
114Phi-3 Mini 128K InstructMicrosoft$0.10$0.10$0.10Fireworks AInot evaluated
115qwen-2-1-5b-instructArize AI$0.10$0.10$0.10Together AInot evaluated
116qwen2-5-0-5b-instructAlibaba (Qwen)$0.10$0.10$0.10Fireworks AInot evaluated
117qwen2-5-1-5b-instructAlibaba (Qwen)$0.10$0.10$0.10Fireworks AInot evaluated
118qwen2-5-coder-0-5b-instructAlibaba (Qwen)$0.10$0.10$0.10Fireworks AInot evaluated
119qwen2-5-coder-1-5bAlibaba (Qwen)$0.10$0.10$0.10Fireworks AInot evaluated
120qwen2-5-coder-1-5b-instructAlibaba (Qwen)$0.10$0.10$0.10Fireworks AInot evaluated
121qwen2-5-coder-3bAlibaba (Qwen)$0.10$0.10$0.10Fireworks AInot evaluated
122qwen2-vl-2b-instructAlibaba (Qwen)$0.10$0.10$0.10Fireworks AInot evaluated
123Qwen2.5-Coder-0.5BAlibaba (Qwen)$0.10$0.10$0.10Fireworks AInot evaluated
124qwen3-0-6bAlibaba (Qwen)$0.10$0.10$0.10Fireworks AInot evaluated
125qwen3-1-7bAlibaba (Qwen)$0.10$0.10$0.10Fireworks AInot evaluated
126qwen3-1-7b-fp8-draftAlibaba (Qwen)$0.10$0.10$0.10Fireworks AInot evaluated
127qwen3-1-7b-fp8-draft-131072Alibaba (Qwen)$0.10$0.10$0.10Fireworks AInot evaluated
128qwen3-1-7b-fp8-draft-40960Alibaba (Qwen)$0.10$0.10$0.10Fireworks AInot evaluated
129Reka EdgeReka$0.10$0.10$0.10Rekanot evaluated
130Qwen-Omni TurboAlibaba (Qwen)$0.101$0.058$0.23Alibaba (China)not evaluated
131Qwen3-Omni FlashAlibaba (Qwen)$0.101$0.058$0.23Alibaba (China)not evaluated
132Qwen Doc TurboAlibaba (Qwen)$0.101$0.087$0.144Alibaba (China)not evaluated
133GPT OSS Safeguard 20BOpenAI$0.103$0.07$0.20Amazon Bedrocknot evaluated
134NVIDIA-Nemotron-Nano-12B-v2NVIDIA$0.103$0.07$0.20Nebius Token Factory (via Hugging Face)not evaluated
135nemotron-3-nano-omniNVIDIA$0.105$0.06$0.24Nebius Token Factorynot evaluated
136Nova LiteAmazon$0.105$0.06$0.24Amazon Bedrocknot evaluated
137Mistral Small 3.2 24BMistral AI$0.106$0.075$0.20Mistralnot evaluated
138Granite 4.2 8BIBM$0.108$0.06$0.25Deep Infranot evaluated
139Ling 3.0 Flash FininclusionAI$0.111$0.075$0.22Novita AInot evaluated
140Ling 3.0 Flash SanteinclusionAI$0.111$0.075$0.22Novita AInot evaluated
141Laguna S 2.1Poolside$0.113$0.09$0.18Vultrnot evaluated
142mistral-7b-v0-3Mistral AI$0.113$0.10$0.15llamagate109.1 ± 7.7
143Qwen3.5-FlashAlibaba (Qwen)$0.114$0.065$0.26Alibabanot evaluated
144Granite-4.0-H-SmallIBM$0.114$0.0636$0.265watsonx.ainot evaluated
145Qwen3 30B A3b fp8Alibaba (Qwen)$0.118$0.09$0.20pinstripesnot evaluated
146Qwen3 32BAlibaba (Qwen)$0.118$0.08$0.23OVHcloud AI Endpoints138.5 ± 2.8
147Qwen3-Coder 30B-A3B InstructAlibaba (Qwen)$0.118$0.07$0.26OVHcloud AI Endpointsnot evaluated
148Nex-N2.5-ProNex AGI$0.119$0.075$0.25Nex AGInot evaluated
149Qwen3 14BAlibaba (Qwen)$0.12$0.08$0.24Nebius Token Factory138.2 ± 3.1
150qwen3-4bAlibaba (Qwen)$0.12$0.08$0.24Nebius Token Factorynot evaluated
151Baidu Ernie 4.5 21B A3B ThinkingBaidu$0.123$0.07$0.28Novita AInot evaluated
152ERNIE 4.5 21B A3BBaidu$0.123$0.07$0.28Novita AInot evaluated
153Mistral Small 4Mistral AI$0.123$0.07$0.28SAP AI Corenot evaluated
154pplx-7b-chatPerplexity$0.123$0.07$0.28Perplexitynot evaluated
155sonar-small-chatPerplexity$0.123$0.07$0.28Perplexitynot evaluated
156deepseek-r1-8bDeepSeek$0.125$0.10$0.20llamagatenot evaluated
157GPT-4.1 nanoOpenAI$0.125$0.08$0.26SAP AI Core129.6 ± 4.3
158Muse Spark 1.2 ContributorMeta$0.125$0.10$0.20Metanot evaluated
159Muse Spark 1.3 ContributorMeta$0.125$0.10$0.20Metanot evaluated
160Olmo-3-7B-InstructAi2 (Allen Institute for AI)$0.125$0.10$0.20huggingface_publicainot evaluated
161Qwen3.8 Flash NextAlibaba (Qwen)$0.125$0.10$0.20Vultrnot evaluated
162Reka Flash 3Reka$0.125$0.10$0.20Rekanot evaluated
163UI-TARS 7BByteDance Seed$0.125$0.10$0.20Parasailnot evaluated
164Qwen LongAlibaba (Qwen)$0.126$0.072$0.287Alibaba (China)not evaluated
165Hy-MT2-30B-A3BTencent$0.129$0.074$0.295Tencentnot evaluated
166Hy-MT2-7BTencent$0.129$0.074$0.295Tencentnot evaluated
167gemini 2.0 flash liteGoogle$0.131$0.075$0.30Googlenot evaluated
168Gemini 2.5 Flash-LiteGoogle$0.131$0.075$0.30OCI Generative AInot evaluated
169Phi-4-miniMicrosoft$0.131$0.075$0.30Azurenot evaluated
170Phi-4-MiniMicrosoft$0.131$0.075$0.30Azurenot evaluated
171Phi-4-mini-reasoningMicrosoft$0.131$0.075$0.30Azurenot evaluated
172GPT-5 NanoOpenAI$0.138$0.05$0.40OpenAI139.3 ± 3.3
173MiMo-V2.6-FlashXiaomi$0.138$0.10$0.25Vultrnot evaluated
174Nemotron 3 Nano OmniNVIDIA$0.138$0.10$0.25Vultrnot evaluated
175GLM-4-LongZ.ai (Zhipu AI)$0.138$0.138$0.138Zhipu AInot evaluated
176Hermes 2 Pro Llama 3 8BNous Research$0.14$0.14$0.14Novita AInot evaluated
177Llama-4-Scout-17B-16E-Instruct-FP8Meta$0.14$0.09$0.29nscalenot evaluated
178Phi 4 MultimodalMicrosoft$0.14$0.08$0.32Azurenot evaluated
179Phi-4-multimodalMicrosoft$0.14$0.08$0.32Azurenot evaluated
180DeepSeek V4.1 FlashDeepSeek$0.143$0.09$0.30sail155.6 ± 2
181Qwen3 30B A3B Instruct 2507Alibaba (Qwen)$0.143$0.09$0.30SiliconFlownot evaluated
182Step 3.5 FlashStepFun$0.143$0.09$0.30CommandCodenot evaluated
183GLM-4.7-FlashZ.ai (Zhipu AI)$0.145$0.06$0.40Venice AInot evaluated
184Qwen-MT TurboAlibaba (Qwen)$0.146$0.101$0.28Alibaba (China)not evaluated
185MiMo-V2.5Xiaomi$0.149$0.119$0.238GMI Cloudnot evaluated
186Command RCohere$0.15$0.15$0.15OCI Generative AInot evaluated
187cosmos3-super-reasonerNVIDIA$0.15$0.10$0.30Nebius Token Factorynot evaluated
188DeepSeek R1 Distill Qwen 32BDeepSeek$0.15$0.15$0.15nscale137.4 ± 4.7
189Devstral SmallMistral AI$0.15$0.10$0.30Mistralnot evaluated
190Gemma 4 12B ITGoogle$0.15$0.10$0.30SiliconFlownot evaluated
191Gemma-4-31B-ITGoogle$0.15$0.10$0.30CrofAI142.9 ± 2.4
192llama-2-7b-chat-hfMeta$0.15$0.15$0.15anyscalenot evaluated
193MiMo-V2-FlashXiaomi$0.15$0.10$0.30Novita AI (via Hugging Face)not evaluated
194Ministral 3 8BMistral AI$0.15$0.15$0.15Mistralnot evaluated
195Mistral Small 3.1Mistral AI$0.15$0.10$0.30Azurenot evaluated
196Mistral Small 3.1 24BMistral AI$0.15$0.10$0.30Vertexnot evaluated
197Mixtral 8x7B Instruct v0.1Mistral AI$0.15$0.15$0.15anyscalenot evaluated
198Qwen3 30b A3b Thinking 2507Alibaba (Qwen)$0.15$0.10$0.30Nebius Token Factory (via Hugging Face)not evaluated
199Rnj-1 InstructEssential AI$0.15$0.15$0.15Together AI (via Hugging Face)not evaluated
200solar-miniUpstage$0.15$0.15$0.15Upstagenot evaluated
201Step 3.5 Flash 2603StepFun$0.15$0.10$0.30StepFun (China)not evaluated
202Voxtral SmallMistral AI$0.15$0.10$0.30Mistralnot evaluated
203Voxtral Small 24B 2507Mistral AI$0.15$0.10$0.30Mistralnot evaluated
204zephyr-7b-betaHugging Face H4$0.15$0.15$0.15anyscalenot evaluated
205Qwen2.5-Omni 7BAlibaba (Qwen)$0.152$0.087$0.345Alibaba (China)not evaluated
206GLM-4.7-FlashXZ.ai (Zhipu AI)$0.153$0.07$0.40Z.AInot evaluated
207Qwen3 235B A22B Instruct 2507Alibaba (Qwen)$0.153$0.0875$0.35GMI Cloudnot evaluated
208Llama 3.3 70b InstructMeta$0.155$0.10$0.32Deep Infranot evaluated
209GPT OSS 120B High ThroughputOpenAI$0.158$0.09$0.36Clarifainot evaluated
210gpt-oss-120b-maasOpenAI$0.158$0.09$0.36Vertexnot evaluated
211Qwen PlusAlibaba (Qwen)$0.158$0.115$0.287Alibaba (China)not evaluated
212Qwen Plus CharacterAlibaba (Qwen)$0.158$0.115$0.287Alibaba (China)not evaluated
213Qwen-VL PlusAlibaba (Qwen)$0.158$0.115$0.287Alibaba (China)not evaluated
214GLM-5.3-FlashZ.ai (Zhipu AI)$0.162$0.099$0.35IteraCompute153.2 ± 2.2
215deepseek-v4-flash-0731Perplexity$0.163$0.13$0.26Perplexitynot evaluated
216Titan Text G1 - LiteAmazon$0.163$0.15$0.20Amazon Bedrocknot evaluated
217Seed CharacterByteDance Seed$0.163$0.119$0.297Volcengine Arknot evaluated
218Nemotron 3 Super 120BNVIDIA$0.164$0.085$0.40Deep Infranot evaluated
219Qwen2.5 72B InstructAlibaba (Qwen)$0.165$0.12$0.30hyperbolicnot evaluated
220DeepSeek V4 FlashDeepSeek$0.175$0.14$0.28DigitalOceannot evaluated
221DeepSeek V4 Flash Vision ExpDeepSeek$0.175$0.14$0.28AMDnot evaluated
222gemini 2.0 flashGoogle$0.175$0.10$0.40Googlenot evaluated
223gemini-2.5-flash-lite-preview-09-2025Google$0.175$0.10$0.40Vertexnot evaluated
224Llama 3.3 Nemotron Super 49B v1NVIDIA$0.175$0.10$0.40Nebius Token Factorynot evaluated
225Nemotron 3.5 Super VL 120B A12BNVIDIA$0.175$0.10$0.40Crusoenot evaluated
226Ornith 1.5 35B A3BOrnith AI$0.175$0.10$0.40RunInfranot evaluated
227Seed 2.0 MiniByteDance Seed$0.175$0.10$0.40Deep Infranot evaluated
228Solar Mini 4Upstage$0.175$0.10$0.40Upstagenot evaluated
229Voxtral SmallMistral AI$0.175$0.10$0.40Mistralnot evaluated
230Qwen2.5-Math 7B InstructAlibaba (Qwen)$0.18$0.144$0.287Alibaba (China)not evaluated
231Llama Guard 4 12BMeta$0.18$0.18$0.18Deep Infranot evaluated
232Qwen3.8 FlashAlibaba (Qwen)$0.18$0.113$0.382Deep Infranot evaluated
233Qwen3.8 Omni FlashAlibaba (Qwen)$0.18$0.113$0.382Alibaba (China)not evaluated
234Ternary Bonsai 2 27BPrismML$0.181$0.075$0.50Darkbloomnot evaluated
235DeepSeek V4.1 Flash 1017DeepSeek$0.185$0.08$0.50Inferencenot evaluated
236Qwen3 VL 8B InstructAlibaba (Qwen)$0.185$0.08$0.50Novita AInot evaluated
237QwQ 32BAlibaba (Qwen)$0.185$0.18$0.20nscale137.6 ± 4.7
238Google Gemma 3Google$0.188$0.15$0.30Inferencenot evaluated
239Qwen3-VL 30B-A3BAlibaba (Qwen)$0.189$0.108$0.431Alibaba (China)not evaluated
240gemma-4-26b-a4bGoogle$0.198$0.13$0.40Amazon Bedrock (mantle)141.8 ± 2.4
241Hermes-4-70BNous Research$0.198$0.13$0.40Nebius Token Factorynot evaluated
242qwen2-vl-72b-instructAlibaba (Qwen)$0.198$0.13$0.40Nebius Token Factorynot evaluated
243Claude Haiku 5.5Anthropic$0.20$0.10$0.50Anthropic159 ± 2.7
244deepseek-coder-7b-baseDeepSeek$0.20$0.20$0.20Fireworks AInot evaluated
245deepseek-coder-7b-base-v1-5DeepSeek$0.20$0.20$0.20Fireworks AInot evaluated
246deepseek-coder-7b-instruct-v1-5DeepSeek$0.20$0.20$0.20Fireworks AInot evaluated
247deepseek-r1-0528-distill-qwen3-8bDeepSeek$0.20$0.20$0.20Fireworks AInot evaluated
248gemma-7bGoogle$0.20$0.20$0.20Fireworks AI112.1 ± 7
249GPT-6 LunaOpenAI$0.20$0.10$0.50OpenAI156.3 ± 2.4
250GPT-6 Luna ProOpenAI$0.20$0.10$0.50Azurenot evaluated
251granite-3-8b-instructIBM$0.20$0.20$0.20watsonx.ainot evaluated
252granite-guardian-3-3-8bIBM$0.20$0.20$0.20watsonx.ainot evaluated
253llama-2-13bMeta$0.20$0.10$0.50replicate106.3 ± 7.4
254llama-2-13b-chatMeta$0.20$0.10$0.50replicatenot evaluated
255llama-guard-2-8bMeta$0.20$0.20$0.20Fireworks AInot evaluated
256llama-v2-13bMeta$0.20$0.20$0.20Fireworks AInot evaluated
257llama-v2-13b-chatMeta$0.20$0.20$0.20Fireworks AInot evaluated
258llama-v2-7bMeta$0.20$0.20$0.20Fireworks AInot evaluated
259llama-v2-7b-chatMeta$0.20$0.20$0.20Fireworks AInot evaluated
260llama-v3-2-11b-vision-instructMeta$0.20$0.20$0.20Fireworks AInot evaluated
261llama-v3-8bMeta$0.20$0.20$0.20Fireworks AInot evaluated
262llama-v3-8b-instruct-hfMeta$0.20$0.20$0.20Fireworks AInot evaluated
263llamaguard-7bMeta$0.20$0.20$0.20Fireworks AInot evaluated
264Ministral 14BMistral AI$0.20$0.20$0.20Mistralnot evaluated
265Ministral 3 14BMistral AI$0.20$0.20$0.20Mistralnot evaluated
266Ministral 3 14BMistral AI$0.20$0.20$0.20DigitalOceannot evaluated
267Mistral 7BMistral AI$0.20$0.20$0.20Fireworks AInot evaluated
268mistral-7b-instruct-4kMistral AI$0.20$0.20$0.20Fireworks AInot evaluated
269mistral-7b-instruct-v3Mistral AI$0.20$0.20$0.20Fireworks AInot evaluated
270mistral-7b-v0-2Mistral AI$0.20$0.20$0.20Fireworks AInot evaluated
271mistral-nemo-base-2407Mistral AI$0.20$0.20$0.20Fireworks AInot evaluated
272nemotron-content-safety-3-5NVIDIA$0.20$0.20$0.20Deep Infranot evaluated
273Osmosis Structure 0.6BOsmosis$0.20$0.10$0.50Inferencenot evaluated
274phi-3-vision-128k-instructMicrosoft$0.20$0.20$0.20Fireworks AInot evaluated
275Qwen 2.5 7B Vision InstructAlibaba (Qwen)$0.20$0.20$0.20Inferencenot evaluated
276qwen-v2-5-14b-instructAlibaba (Qwen)$0.20$0.20$0.20Fireworks AInot evaluated
277qwen-v2-5-7bAlibaba (Qwen)$0.20$0.20$0.20Fireworks AInot evaluated
278qwen2-5-14bAlibaba (Qwen)$0.20$0.20$0.20Fireworks AInot evaluated
279qwen2-5-coder-14bAlibaba (Qwen)$0.20$0.20$0.20Fireworks AInot evaluated
280qwen2-5-coder-14b-instructAlibaba (Qwen)$0.20$0.20$0.20Fireworks AInot evaluated
281qwen2-5-vl-3b-instructAlibaba (Qwen)$0.20$0.20$0.20Fireworks AInot evaluated
282qwen2-vl-7b-instructAlibaba (Qwen)$0.20$0.20$0.20Fireworks AInot evaluated
283Qwen2.5-VL 7B InstructAlibaba (Qwen)$0.20$0.20$0.20Fireworks AInot evaluated
284Qwen3 4B InstructAlibaba (Qwen)$0.20$0.20$0.20Fireworks AInot evaluated
285yi-6b01.AI$0.20$0.20$0.20Fireworks AInot evaluated
286Seed 2.0 LiteByteDance Seed$0.20$0.0891$0.534Volcengine Arknot evaluated
287gemma-4-31b-itNVIDIA$0.205$0.14$0.40sailnot evaluated
288gemma4:31bGoogle$0.205$0.14$0.40Amazon Bedrock (mantle)not evaluated
289Qwen3 235B-A22B Instruct 2507Alibaba (Qwen)$0.205$0.09$0.55Deep Infranot evaluated
290gemma-4-31b-it-thinkingGoogle$0.213$0.15$0.40libertainot evaluated
291LFM2.5-24B-A2BLiquid AI$0.213$0.05$0.70Liquidnot evaluated
292Qwen2.5 14B InstructAlibaba (Qwen)$0.216$0.144$0.431Alibaba (China)not evaluated
293Phi-4-reasoningMicrosoft$0.219$0.125$0.50Azurenot evaluated
294Phi-4-reasoning-plusMicrosoft$0.219$0.125$0.50Azurenot evaluated
295deepseek-v3.2DeepSeek$0.223$0.18$0.35CrofAI146.1 ± 1.4
296Ling 3.1 FlashinclusionAI$0.225$0.15$0.45Deep Infranot evaluated
297llama-2-13b-chat-hfMeta$0.225$0.225$0.225Together AInot evaluated
298Hy3Tencent$0.231$0.132$0.528SiliconFlownot evaluated
299Qwen 3 235B ThinkingAlibaba (Qwen)$0.233$0.11$0.60IO.NETnot evaluated
300DeepSeek ChatDeepSeek$0.238$0.19$0.38inferenceapisnot evaluated
301DeepSeek R1DeepSeek$0.238$0.19$0.38inferenceapisnot evaluated
302DeepSeek V3DeepSeek$0.238$0.19$0.38inferenceapis132.3 ± 4.2
303Gemma 3 12BGoogle$0.238$0.15$0.50Neon123.5 ± 6.6
304glm-5-3-flashPerplexity$0.238$0.15$0.50Perplexitynot evaluated
305glm-5p3-flashZ.ai (Zhipu AI)$0.238$0.15$0.50Fireworks AInot evaluated
306qwen3-6-27b-thinkingAlibaba (Qwen)$0.238$0.15$0.50libertainot evaluated
307qwen3-6-35b-a3b-thinkingAlibaba (Qwen)$0.238$0.15$0.50libertainot evaluated
308ernie-4-5-vl-28b-a3bBaidu$0.245$0.14$0.56Novita AInot evaluated
309Gemma 4 UncensoredGoogle$0.247$0.163$0.50Venice AInot evaluated
310Hunyuan A13B InstructTencent$0.248$0.14$0.57SiliconFlownot evaluated
311Ling-flash-2.0inclusionAI$0.248$0.14$0.57SiliconFlownot evaluated
312codestral-mambaMistral AI$0.25$0.25$0.25Mistralnot evaluated
313Gemma Sea Lion V4 27B ItAI Singapore$0.25$0.20$0.40huggingface_publicainot evaluated
314Jamba MiniAI21 Labs$0.25$0.20$0.40AI21 Labsnot evaluated
315jamba-1-5AI21 Labs$0.25$0.20$0.40AI21 Labsnot evaluated
316jamba-1-5-miniAI21 Labs$0.25$0.20$0.40AI21 Labsnot evaluated
317jamba-mini-1-6AI21 Labs$0.25$0.20$0.40AI21 Labsnot evaluated
318jamba-mini-1-7AI21 Labs$0.25$0.20$0.40AI21 Labsnot evaluated
319Qwen3 VL 30B A3B InstructAlibaba (Qwen)$0.25$0.15$0.55NEAR AI Cloudnot evaluated
320qwen3-vl-8bAlibaba (Qwen)$0.25$0.15$0.55llamagatenot evaluated
321solar-pro2Upstage$0.25$0.25$0.25Upstagenot evaluated
322solar-pro3Upstage$0.25$0.25$0.25Upstagenot evaluated
323Qwen3 Coder FlashAlibaba (Qwen)$0.252$0.144$0.574Alibaba (China)not evaluated
324Qwen3-Next 80B-A3B InstructAlibaba (Qwen)$0.252$0.144$0.574Alibaba (China)not evaluated
325Qwen3.5 PlusAlibaba (Qwen)$0.258$0.115$0.688Alibaba (China)not evaluated
326Command RCohere$0.263$0.15$0.60Coherenot evaluated
327Gemini 2.5 FlashGoogle$0.263$0.15$0.60OCI Generative AInot evaluated
328gemma-4-26b-a4b-it-maasGoogle$0.263$0.15$0.60Vertexnot evaluated
329gpt 4o mini audio previewOpenAI$0.263$0.15$0.60OpenAInot evaluated
330GPT OSS Safeguard 120BOpenAI$0.263$0.15$0.60Amazon Bedrocknot evaluated
331GPT-4o miniOpenAI$0.263$0.15$0.60OpenAI126.6 ± 4.5
332gpt-4o-mini-search-previewOpenAI$0.263$0.15$0.60OpenAInot evaluated
333gpt-oss-120b-turboOpenAI$0.263$0.15$0.60Deep Infranot evaluated
334Llama 4 Maverick 17b 128e InstructMeta$0.263$0.15$0.60IO.NETnot evaluated
335llama4-scout-instruct-basicMeta$0.263$0.15$0.60Fireworks AInot evaluated
336Magistral SmallMistral AI$0.263$0.15$0.60Mistralnot evaluated
337MiniMax-M3.1-FlashMiniMax$0.263$0.15$0.60MiniMax (minimax.io)not evaluated
338Mistral SmallMistral AI$0.263$0.15$0.60Mistralnot evaluated
339mistral-vibe-cli-fastMistral AI$0.263$0.15$0.60Mistralnot evaluated
340palmyra-vision-7bWriter$0.263$0.15$0.60Amazon Bedrocknot evaluated
341Qwen3-Vl 30b A3b ThinkingAlibaba (Qwen)$0.263$0.15$0.60Fireworks AInot evaluated
342Qwen3 235B-A22BAlibaba (Qwen)$0.27$0.18$0.54Deep Infra139.4 ± 2.8
343Grok 4 Fast Non-ReasoningxAI$0.275$0.20$0.50xAInot evaluated
344Grok 4 Fast ReasoningxAI$0.275$0.20$0.50xAInot evaluated
345Grok 4.1 Fast Non-ReasoningxAI$0.275$0.20$0.50xAInot evaluated
346Grok 4.1 Fast ReasoningxAI$0.275$0.20$0.50xAInot evaluated
347Llama 3.3 70BMeta$0.275$0.20$0.50inferenceapis127.3 ± 3.9
348Meta Llama 3.3 70B VersatileMeta$0.275$0.20$0.50inferenceapisnot evaluated
349MiniCPM5-2BOpenBMB$0.279$0.124$0.743AMDnot evaluated
350Qwen3-VL-32B-InstructAlibaba (Qwen)$0.28$0.16$0.64Alibabanot evaluated
351Hy3 PreviewTencent$0.285$0.18$0.60GMI Cloudnot evaluated
352Pixtral 12B 2409Mistral AI$0.285$0.285$0.285GreenPTnot evaluated
353Qwen3 Coder NextAlibaba (Qwen)$0.29$0.12$0.80Parasailnot evaluated
354CodestralMistral AI$0.30$0.20$0.60Vertexnot evaluated
355Codestral 25.01Mistral AI$0.30$0.20$0.60Vertexnot evaluated
356DeepSeek R1 Distill Llama 70BDeepSeek$0.30$0.20$0.60Deep Infranot evaluated
357Mistral SabaMistral AI$0.30$0.20$0.60Mistralnot evaluated
358Nemotron Nano 12B v2 VLNVIDIA$0.30$0.20$0.60Amazon Bedrocknot evaluated
359r1v4-liteSkywork AI$0.30$0.20$0.60Novita AInot evaluated
360ReMM SLERP 13Bundi95$0.30$0.30$0.30Together AInot evaluated
361Seed-OSS-36B-InstructByteDance Seed$0.30$0.21$0.57SiliconFlownot evaluated
362Titan Text G1 - ExpressAmazon$0.30$0.20$0.60Amazon Bedrocknot evaluated
363DeepSeek V3.2 ExpDeepSeek$0.303$0.27$0.40Meganova145 ± 2.3
364GLM-4.5-AirZ.ai (Zhipu AI)$0.31$0.13$0.85Novita AInot evaluated
365Qwen-SEA-LION-v4-32B-ITAI Singapore$0.313$0.25$0.50huggingface_publicainot evaluated
366Qwen3.6 35B-A3BAlibaba (Qwen)$0.313$0.10$0.95Deep Infra144.1 ± 2.4
367Qwen-VL MaxAlibaba (Qwen)$0.316$0.23$0.574Alibaba (China)not evaluated
368QwQ PlusAlibaba (Qwen)$0.316$0.23$0.574Alibaba (China)not evaluated
369DeepSeek V3.1DeepSeek$0.32$0.19$0.71TokenGo139.9 ± 3.7
370DeepSeek OCRDeepSeek$0.325$0.20$0.70Clarifainot evaluated
371Cydonia 24B V4.1TheDrummer$0.35$0.30$0.50Parasailnot evaluated
372deepseek-v3-0324DeepSeek$0.35$0.20$0.80submodelnot evaluated
373ft-gpt-4-1-nanoOpenAI$0.35$0.20$0.80OpenAInot evaluated
374Grok 3 MinixAI$0.35$0.30$0.50xAI140.3 ± 2.3
375llama-guard-3-11b-visionMeta$0.35$0.35$0.35watsonx.ainot evaluated
376Muse Glimmer 30BMeta$0.35$0.20$0.80EmpirioLabs AInot evaluated
377Llama 3.1 70b InstructMeta$0.353$0.34$0.39Novita AInot evaluated
378Qwen3.5 35B-A3BAlibaba (Qwen)$0.355$0.14$1.00Deep Infra142.5 ± 2.4
379glm-5-3-flash-usZ.ai (Zhipu AI)$0.356$0.225$0.75Fireworks AInot evaluated
380glm-5p3-flash-usZ.ai (Zhipu AI)$0.356$0.225$0.75Fireworks AInot evaluated
381llama-4-scout-17b-128e-instruct-maasMeta$0.363$0.25$0.70Vertexnot evaluated
382llama-4-scout-17b-16e-instruct-maasMeta$0.363$0.25$0.70Vertexnot evaluated
383Qwen3.8-27BAlibaba (Qwen)$0.363$0.15$1.00Vultrnot evaluated
384Qwen3 VL 235B A22B InstructAlibaba (Qwen)$0.37$0.20$0.88Deep Infranot evaluated
385Mercury 2Inception$0.375$0.25$0.75Inceptionnot evaluated
386Mercury Edit 2Inception$0.375$0.25$0.75Inceptionnot evaluated
387MiniMax-M3MiniMax$0.375$0.20$0.90Vultr147.1 ± 3.6
388Qwen 3 Coder 30B A3B InstructAlibaba (Qwen)$0.375$0.30$0.60pinstripesnot evaluated
389Qwen-MT PlusAlibaba (Qwen)$0.375$0.25$0.75Novita AInot evaluated
390Qwen2.5-VL 72B InstructAlibaba (Qwen)$0.375$0.25$0.75Nebius Token Factorynot evaluated
391UncensoredCognitive Computations$0.375$0.20$0.90Venice AInot evaluated
392granite-ttm-1024-96-r2IBM$0.38$0.38$0.38watsonx.ainot evaluated
393granite-ttm-1536-96-r2IBM$0.38$0.38$0.38watsonx.ainot evaluated
394granite-ttm-512-96-r2IBM$0.38$0.38$0.38watsonx.ainot evaluated
395MiMo-V2.5-ProXiaomi$0.381$0.305$0.609GMI Cloudnot evaluated
396Llama 4 Maverick Instruct (Basic)Meta$0.385$0.22$0.88Fireworks AInot evaluated
397MiniMax-M2.5MiniMax$0.385$0.22$0.88DInference146.7 ± 2.7
398Qwen3 235B A22B InstructAlibaba (Qwen)$0.385$0.22$0.88Vertex (Qwen models)not evaluated
399Qwen3 VL 235B A22B ThinkingAlibaba (Qwen)$0.385$0.22$0.88Fireworks AInot evaluated
400Seed 1.6ByteDance Seed$0.386$0.119$1.19Volcengine Arknot evaluated
401Seed 1.6 VisionByteDance Seed$0.386$0.119$1.19Volcengine Arknot evaluated
402Seed 1.8ByteDance Seed$0.386$0.119$1.19Volcengine Arknot evaluated
403Qwen3.5 397B-A17BAlibaba (Qwen)$0.387$0.172$1.03Alibaba (China)146.7 ± 1.7
404gpt-oss-120b-ultraOpenAI$0.388$0.20$0.95Deep Infranot evaluated
405Trinity Large ThinkingArcee AI$0.388$0.25$0.80Arceenot evaluated
406ernie-4-5-vl-28b-a3b-thinkingBaidu$0.39$0.39$0.39Novita AInot evaluated
407gemma-4-31b-it-ultraGoogle$0.393$0.27$0.76Deep Infranot evaluated
408Qwen3.6 FlashAlibaba (Qwen)$0.393$0.18$1.03Moarknot evaluated
409UnslopNemo 12BTheDrummer$0.40$0.40$0.40Parasailnot evaluated
410Qwen-Omni Turbo RealtimeAlibaba (Qwen)$0.402$0.23$0.918Alibaba (China)not evaluated
411Qwen3-Omni Flash RealtimeAlibaba (Qwen)$0.402$0.23$0.918Alibaba (China)not evaluated
412Qwen 3 Coder 480BIntel$0.403$0.22$0.95IO.NETnot evaluated
413Llama 4 MaverickMeta$0.405$0.25$0.87DigitalOcean132.2 ± 3.2
414Qwen3-Next 80B-A3B (Thinking)Alibaba (Qwen)$0.413$0.15$1.20Nebius Token Factorynot evaluated
415qwen3-next-80b-a3b-instruct-maasAlibaba (Qwen)$0.413$0.15$1.20Vertex (Qwen models)not evaluated
416qwen3-next-80b-a3b-thinking-maasAlibaba (Qwen)$0.413$0.15$1.20Vertex (Qwen models)not evaluated
417Step 3.7 FlashStepFun$0.416$0.185$1.11StepFun (China)not evaluated
418DeepSeek V3.1DeepSeek$0.425$0.25$0.95Deep Infranot evaluated
419MiniMax-01MiniMax$0.425$0.20$1.10MiniMax (minimax.io)not evaluated
420Qwen3 Omni 30B A3B ThinkingAlibaba (Qwen)$0.43$0.25$0.97Novita AInot evaluated
421qwen3-omni-30b-a3b-instructAlibaba (Qwen)$0.43$0.25$0.97Novita AInot evaluated
422Qwen Math TurboAlibaba (Qwen)$0.43$0.287$0.861Alibaba (China)not evaluated
423Qwen2.5 32B InstructAlibaba (Qwen)$0.43$0.287$0.861Alibaba (China)not evaluated
424Beam 1.0Reflection$0.438$0.25$1.00Nebius Token Factorynot evaluated
425Beam 1.0 501B A23BReflection$0.438$0.25$1.00Nebius Token Factorynot evaluated
426DeepSeek V3 0324DeepSeek$0.438$0.25$1.00SiliconFlownot evaluated
427Qwen3-Coder 480B-A35B InstructAlibaba (Qwen)$0.438$0.25$1.00SiliconFlownot evaluated
428Mistral Small 3.2Mistral AI$0.442$0.285$0.912GreenPTnot evaluated
429Codestral 25.08Mistral AI$0.45$0.30$0.90Mistralnot evaluated
430codestral-2Mistral AI$0.45$0.30$0.90Vertexnot evaluated
431GLM-4.6VZ.ai (Zhipu AI)$0.45$0.30$0.90Z.AInot evaluated
432GLM-4.6V-FlashZ.ai (Zhipu AI)$0.45$0.30$0.90Novita AI (via Hugging Face)not evaluated
433GPT-5.6 LunaOpenAI$0.45$0.20$1.20OpenAI156.3 ± 2.6
434Mistral Code LatestMistral AI$0.45$0.30$0.90Mistralnot evaluated
435mistral-code-fimMistral AI$0.45$0.30$0.90Mistralnot evaluated
436deepseek-v3.1-terminusDeepSeek$0.453$0.27$1.00Deep Infranot evaluated
437GPT-5.4 nanoOpenAI$0.463$0.20$1.25OpenAI146.1 ± 2.4
438Qwen3-VL PlusAlibaba (Qwen)$0.466$0.143$1.43Alibaba (China)not evaluated
439Qwen3 CoderAlibaba (Qwen)$0.475$0.30$1.00Deep Infranot evaluated
440WizardLM-2 8x22BMicrosoft$0.48$0.48$0.48Deep Infranot evaluated
441qwen3-vlAlibaba (Qwen)$0.483$0.26$1.15inferenceapisnot evaluated
442qwen3-vl-235bAlibaba (Qwen)$0.483$0.26$1.15inferenceapisnot evaluated
443ERNIE 4.5 300B A47BBaidu$0.485$0.28$1.10Novita AInot evaluated
444Perceptron Mk1perceptron$0.488$0.15$1.50Perceptronnot evaluated
445Perceptron Mk1.5perceptron$0.488$0.15$1.50Perceptronnot evaluated
446WeaverMancer$0.488$0.40$0.75Mancer 2not evaluated
447CoBuddyBaidu$0.493$0.28$1.13Novita AInot evaluated
448Claude Haiku 3Anthropic$0.50$0.25$1.25SAP AI Core118.4 ± 5.7
449deepseek-coder-v2-lite-instructDeepSeek$0.50$0.50$0.50Fireworks AInot evaluated
450deepseek-v2-lite-chatDeepSeek$0.50$0.50$0.50Fireworks AInot evaluated
451MiMo-V2.6-ProXiaomi$0.50$0.40$0.80Vultrnot evaluated
452Mixtral 8x7BMistral AI$0.50$0.50$0.50Fireworks AI118.5 ± 5.2
453Mixtral 8x7B InstructMistral AI$0.50$0.50$0.50Fireworks AInot evaluated
454mixtral-8x7b-instruct-hfMistral AI$0.50$0.50$0.50Fireworks AInot evaluated
455nous-hermes-2-mixtral-8x7b-dpoNous Research$0.50$0.50$0.50Fireworks AInot evaluated
456Qwen3-VL 235B-A22BAlibaba (Qwen)$0.502$0.287$1.15Alibaba (China)not evaluated
457MiniMax-M2.1MiniMax$0.51$0.28$1.20Meganovanot evaluated
458MiniMax-M2.7MiniMax$0.518$0.29$1.20Moark145.9 ± 4.8
459Qwen3 235B A22B Thinking 2507 TEEAlibaba (Qwen)$0.523$0.299$1.20Chutesnot evaluated
460deepseek-v4-1-flash-maasDeepSeek$0.525$0.30$1.20Vertexnot evaluated
461deepseek-v4p1-flashDeepSeek$0.525$0.30$1.20Fireworks AInot evaluated
462ft-gpt-4o-miniOpenAI$0.525$0.30$1.20OpenAInot evaluated
463gemini-gemma-2-27b-itGoogle$0.525$0.35$1.05Googlenot evaluated
464gemini-gemma-2-9b-itGoogle$0.525$0.35$1.05Googlenot evaluated
465GPT-5 MiniOpenAI$0.525$0.30$1.20Snowflake Cortex145.4 ± 1.7
466Grok Code Fast 1xAI$0.525$0.20$1.50Azurenot evaluated
467kat-coder-proKwaipilot$0.525$0.30$1.20Novita AInot evaluated
468LongCat-2.0Meituan$0.525$0.30$1.20AtlasCloudnot evaluated
469MiniMax M3 PreviewMiniMax$0.525$0.30$1.20Venice AInot evaluated
470MiniMax-M2MiniMax$0.525$0.30$1.20MiniMax (minimax.io)not evaluated
471MiniMax-M2 HerMiniMax$0.525$0.30$1.20MiniMax (minimax.io)not evaluated
472minimax-m2-maasMiniMax$0.525$0.30$1.20Vertexnot evaluated
473MiniMax-M2.5 High ThroughputMiniMax$0.525$0.30$1.20Clarifainot evaluated
474minimax-m2p1MiniMax$0.525$0.30$1.20Fireworks AInot evaluated
475Qwen3-VL-32B-ThinkingAlibaba (Qwen)$0.525$0.20$1.50SiliconFlownot evaluated
476Solar Pro 4Upstage$0.525$0.30$1.20Upstagenot evaluated
477glm-5-3-flashoi$0.536$0.195$1.56openinfernot evaluated
478qwen3-5-27boi$0.536$0.195$1.56openinfernot evaluated
479Macaron V1 TallMindLab AI$0.543$0.248$1.43Novita AInot evaluated
480jamba-instructAI21 Labs$0.55$0.50$0.70Amazon Bedrocknot evaluated
481Llama 4 Maverick 17B 128E InstructMeta$0.55$0.35$1.15Vertexnot evaluated
482llama-4-maverick-17b-16e-instruct-maasMeta$0.55$0.35$1.15Vertexnot evaluated
483Qwen3.7 PlusAlibaba (Qwen)$0.56$0.32$1.28Together AI147.3 ± 1.6
484Gemini 3.1 Flash LiteGoogle$0.563$0.25$1.50Google144.5 ± 1.9
485Gemini 3.1 Flash Lite PreviewGoogle$0.563$0.25$1.50Vertexnot evaluated
486Llama 3 70B InstructMeta$0.568$0.51$0.74Novita AI (via Hugging Face)not evaluated
487Mistral Medium 3Mistral AI$0.575$0.36$1.22SAP AI Corenot evaluated
488olmocr-7b-0725Ai2 (Allen Institute for AI)$0.578$0.27$1.50Deep Infranot evaluated
489Qwen3.5 Plus 2026-02-15Alibaba (Qwen)$0.585$0.26$1.56Alibabanot evaluated
490Qwen3.6 27BAlibaba (Qwen)$0.588$0.53$0.76STACKIT146.5 ± 1.8
491GLM 5.3 FlashXZ.ai (Zhipu AI)$0.59$0.37$1.25Zhipu AInot evaluated
492Command A+Cohere$0.60$0.30$1.50Coherenot evaluated
493flan-t5-xl-3bGoogle$0.60$0.60$0.60watsonx.ainot evaluated
494granite-13b-chat-v2IBM$0.60$0.60$0.60watsonx.ainot evaluated
495granite-13b-instruct-v2IBM$0.60$0.60$0.60watsonx.ainot evaluated
496Llama 3.1 70B InstructMeta$0.60$0.60$0.60Cerebrasnot evaluated
497Llama 3.1 Nemotron 70B InstructNVIDIA$0.60$0.60$0.60Deep Infranot evaluated
498Mixtral 8x22BMistral AI$0.60$0.60$0.60nscalenot evaluated
499qwen-coderAlibaba (Qwen)$0.60$0.30$1.50Alibabanot evaluated
500Qwen MaxAlibaba (Qwen)$0.603$0.345$1.38Alibaba (China)not evaluated
501codellama-34b-instructPerplexity$0.613$0.35$1.40Perplexitynot evaluated
502Skyfall 36B V2TheDrummer$0.613$0.55$0.80Parasailnot evaluated
503qwen3-coder-480b-a35b-instruct-maasAlibaba (Qwen)$0.615$0.22$1.80Vertex (Qwen models)not evaluated
504deepseek-v4-flash-thinkingDeepSeek$0.625$0.25$1.75libertainot evaluated
505qwen3-5-122b-a10b-thinkingAlibaba (Qwen)$0.625$0.25$1.75libertainot evaluated
506ERNIE 4.5 VL 424B A47BBaidu$0.628$0.42$1.25Novita AInot evaluated
507Qwen3 MaxAlibaba (Qwen)$0.628$0.359$1.43Alibaba (China)142.3 ± 2.2
508Inkling SmallThinking Machines$0.638$0.45$1.20Deep Infra150.2 ± 2.4
509llama-4-maverick-17bMeta$0.649$0.371$1.48watsonx.ainot evaluated
510Gemma 2 27BGoogle$0.65$0.65$0.65Googlenot evaluated
511Moonshot V1 8KMoonshot AI$0.65$0.20$2.00Moonshot AInot evaluated
512moonshot-v1-8k-vision-previewMoonshot AI$0.65$0.20$2.00Moonshot AInot evaluated
513Bielik 11B v3.0 InstructSpeakLeash$0.67$0.67$0.67CloudFerro Sherlocknot evaluated
514Llama 3.3 70B EuryaleSao10K$0.675$0.65$0.75Deep Infranot evaluated
515GPT-5.1 Codex MiniOpenAI$0.688$0.25$2.00Azurenot evaluated
516Qwen3.5 27BAlibaba (Qwen)$0.688$0.25$2.00SiliconFlownot evaluated
517Seed 2.0 LiteByteDance Seed$0.688$0.25$2.00Seednot evaluated
518seed-1.8ByteDance Seed$0.688$0.25$2.00Deep Infranot evaluated
519GLM-4.5Z.ai (Zhipu AI)$0.70$0.40$1.60Deep Infranot evaluated
520GPT-4.1 miniOpenAI$0.70$0.40$1.60OpenAI135 ± 2.7
521Hermes 3 70B InstructNous Research$0.70$0.70$0.70Deep Infranot evaluated
522qwen3p7-plusAlibaba (Qwen)$0.70$0.40$1.60Fireworks AInot evaluated
523Qwen3.5 122B-A10BAlibaba (Qwen)$0.715$0.26$2.08SiliconFlownot evaluated
524Qwen Plus Character (Japanese)Alibaba (Qwen)$0.725$0.50$1.40Alibabanot evaluated
525GLM-4.6Z.ai (Zhipu AI)$0.738$0.40$1.75IO.NETnot evaluated
526GLM-4.7Z.ai (Zhipu AI)$0.738$0.40$1.75Deep Infra143.8 ± 2.2
527GLM-5Z.ai (Zhipu AI)$0.738$0.40$1.75Vultr145.8 ± 1.9
528Qwen 3 Next 80bAlibaba (Qwen)$0.738$0.35$1.90Venice AInot evaluated
529Aya Expanse 32BCohere$0.75$0.50$1.50Coherenot evaluated
530GPT-3.5 Turbo 0125OpenAI$0.75$0.50$1.50OpenAInot evaluated
531GPT-3.5-turboOpenAI$0.75$0.50$1.50Azurenot evaluated
532Magistral Small 1.2Mistral AI$0.75$0.50$1.50Amazon Bedrocknot evaluated
533Magistral Small 2506Mistral AI$0.75$0.50$1.50IO.NETnot evaluated
534Mistral LargeMistral AI$0.75$0.50$1.50Mistral122 ± 5.3
535Mistral Large 3Mistral AI$0.75$0.50$1.50Mistralnot evaluated
536Mistral Large 3 675B Instruct 2512Mistral AI$0.75$0.50$1.50Mistralnot evaluated
537mistral-large-3:675bMistral AI$0.75$0.50$1.50Ollama Cloudnot evaluated
538titan-text-premierAmazon$0.75$0.50$1.50Amazon Bedrocknot evaluated
539Kimi K2 InstructMoonshot AI$0.768$0.39$1.90IO.NETnot evaluated
540minicpm-v-4.5OpenBMB$0.771$0.658$1.11Nebius Token Factorynot evaluated
541MM Poly 8BClarifai$0.771$0.658$1.11Clarifainot evaluated
542DeepSeek 3.2DeepSeek$0.775$0.50$1.60DigitalOceannot evaluated
543codellama-34b-instruct-hfMeta$0.776$0.776$0.776Together AInot evaluated
544llama-3-3-70b-instruct-fp8-fastMeta$0.783$0.293$2.25Cloudflare Workers AInot evaluated
545deepseek-v4-1-flash-usDeepSeek$0.788$0.45$1.80Fireworks AInot evaluated
546deepseek-v4p1-flash-usDeepSeek$0.788$0.45$1.80Fireworks AInot evaluated
547mistral-saba-24bMistral AI$0.79$0.79$0.79Groqnot evaluated
548Devstral 2Mistral AI$0.80$0.40$2.00Amazon Bedrocknot evaluated
549Mistral Code Agent LatestMistral AI$0.80$0.40$2.00Mistralnot evaluated
550Mistral Medium 3Mistral AI$0.80$0.40$2.00Vertex134.1 ± 2.8
551Mistral Medium 3.1Mistral AI$0.80$0.40$2.00Mistralnot evaluated
552nous-hermes-2-yi-34bNous Research$0.80$0.80$0.80Together AInot evaluated
553yi-34b01.AI$0.80$0.80$0.80Together AInot evaluated
554llama2-13b-chat-v1Meta$0.813$0.75$1.00Amazon Bedrocknot evaluated
555nemotron-3-ultra-550b-a55bPerplexity$0.813$0.25$2.50Perplexitynot evaluated
556Kimi K2.6Moonshot AI$0.825$0.45$1.95Chutes150.9 ± 1.8
557MiniMax M2.1 LightningMiniMax$0.825$0.30$2.40MiniMax (minimax.io)not evaluated
558MiniMax M2.5 highspeedMiniMax$0.825$0.30$2.40MiniMax (minimax.io)not evaluated
559GLM 4 32B 0414Z.ai (Zhipu AI)$0.828$0.55$1.66Novita AInot evaluated
560Gemini 3.5 Flash LiteGoogle$0.85$0.30$2.50Google145.2 ± 2
561Gemini Flash-Lite LatestGoogle$0.85$0.30$2.50Googlenot evaluated
562gemini-2.5-flash-preview-09-2025Google$0.85$0.30$2.50Vertexnot evaluated
563gemini-robotics-er-1-5-previewGoogle$0.85$0.30$2.50Vertexnot evaluated
564Llama 3.1 70B EuryaleSao10K$0.85$0.85$0.85Deep Infranot evaluated
565Llama 3.1 Euryale 70B v2.2Sao10K$0.85$0.85$0.85Deep Infranot evaluated
566MiniMax M1MiniMax$0.85$0.40$2.20MiniMax (minimax.io)not evaluated
567Moondream 3 PreviewMoondream$0.85$0.30$2.50PrimeIntellectnot evaluated
568Moondream 3.1Moondream$0.85$0.30$2.50PrimeIntellectnot evaluated
569DeepSeek-V3.2-SpecialeDeepSeek$0.855$0.58$1.68Azurenot evaluated
570Qwen Math PlusAlibaba (Qwen)$0.861$0.574$1.72Alibaba (China)not evaluated
571Qwen2.5-Math 72B InstructAlibaba (Qwen)$0.861$0.574$1.72Alibaba (China)not evaluated
572Aion 3.0 MiniAion Labs$0.875$0.70$1.40AionLabsnot evaluated
573Aion 3.5 MiniAion Labs$0.875$0.70$1.40AionLabsnot evaluated
574Moonshot Kimi K2 InstructMoonshot AI$0.875$0.50$2.00Deep Infranot evaluated
575Seed 2.1 TurboByteDance Seed$0.891$0.445$2.23Volcengine Arknot evaluated
576codellama-70b-instruct-hfMeta$0.90$0.90$0.90Together AInot evaluated
577Cogito v1 Preview Qwen 32BDeep Cogito$0.90$0.90$0.90Fireworks AInot evaluated
578deepseek-coder-33b-instructDeepSeek$0.90$0.90$0.90Fireworks AInot evaluated
579Devstral Small 2505Mistral AI$0.90$0.90$0.90Fireworks AInot evaluated
580GLM-4.5VZ.ai (Zhipu AI)$0.90$0.60$1.80Z.AInot evaluated
581Llama 3.1 Nemotron Ultra 253BNVIDIA$0.90$0.60$1.80Nebius Token Factorynot evaluated
582llama-2-70b-chat-hfMeta$0.90$0.90$0.90Together AInot evaluated
583llama-v2-70b-chatMeta$0.90$0.90$0.90Fireworks AInot evaluated
584llama-v3-1-70b-instructMeta$0.90$0.90$0.90Fireworks AInot evaluated
585llama-v3-1-nemotron-70b-instructMeta$0.90$0.90$0.90Fireworks AInot evaluated
586llama-v3-2-90b-vision-instructMeta$0.90$0.90$0.90Fireworks AInot evaluated
587llama-v3-3-70b-instructMeta$0.90$0.90$0.90Fireworks AInot evaluated
588llama-v3-70b-instructMeta$0.90$0.90$0.90Fireworks AInot evaluated
589llama-v3-70b-instruct-hfMeta$0.90$0.90$0.90Fireworks AInot evaluated
590Moonshot Kimi K2.5Moonshot AI$0.90$0.45$2.25SiliconFlow148 ± 1.5
591Morph v3 FastMorph$0.90$0.80$1.20Morphnot evaluated
592Qwen 2.5 Coder 32BAlibaba (Qwen)$0.90$0.90$0.90Fireworks AInot evaluated
593qwen1-5-72b-chatAlibaba (Qwen)$0.90$0.90$0.90Fireworks AInot evaluated
594qwen2-5-32bAlibaba (Qwen)$0.90$0.90$0.90Fireworks AI128.5 ± 3.8
595qwen2-5-72bAlibaba (Qwen)$0.90$0.90$0.90Fireworks AI129 ± 3.6
596qwen2-5-coder-32b-instruct-128kAlibaba (Qwen)$0.90$0.90$0.90Fireworks AInot evaluated
597qwen2-5-coder-32b-instruct-32k-ropeAlibaba (Qwen)$0.90$0.90$0.90Fireworks AInot evaluated
598qwen2-5-coder-32b-instruct-64kAlibaba (Qwen)$0.90$0.90$0.90Fireworks AInot evaluated
599qwen2-72b-instructAlibaba (Qwen)$0.90$0.90$0.90Fireworks AInot evaluated
600qwen3-coder-480b-instructAlibaba (Qwen)$0.90$0.90$0.90Fireworks AInot evaluated
601qwq-32b-previewAlibaba (Qwen)$0.90$0.90$0.90Fireworks AInot evaluated
602Seed 2.0 CodeByteDance Seed$0.90$0.40$2.40EmpirioLabs AInot evaluated
603sonar-medium-chatPerplexity$0.90$0.60$1.80Perplexitynot evaluated
604DeepSeek R1 0528DeepSeek$0.913$0.50$2.15Deep Infra141.3 ± 2.1
605Nemotron 3 Ultra 550B A55BNVIDIA$0.913$0.50$2.15CoreWeavenot evaluated
606Ministral 3 3B Reasoning 2512Mistral AI$0.916$1.04$0.548Clarifainot evaluated
607DeepSeek R1DeepSeek$0.92$0.50$2.18SiliconFlow139 ± 2.1
608Llama 3.3 Euryale 70BSao10K$0.928$0.894$1.03AI/ML APInot evaluated
609Nova 2 LiteAmazon$0.935$0.33$2.75Amazon Bedrocknot evaluated
610Seed 2.0 CodeByteDance Seed$0.95$0.475$2.37Volcengine Arknot evaluated
611Seed 2.0 ProByteDance Seed$0.95$0.475$2.37Volcengine Arknot evaluated
612Apertus 70B InstructSwiss AI$0.95$0.46$2.42Regolo AInot evaluated
613Relace Apply 3Relace$0.95$0.85$1.25Relacenot evaluated
614Nova ProAmazon$0.953$0.56$2.13SAP AI Core123.8 ± 8.7
615deepseek-r1-basicDeepSeek$0.96$0.55$2.19Fireworks AInot evaluated
616MiniMax M1MiniMax$0.963$0.55$2.20Novita AInot evaluated
617Moonshot Kimi K2 ThinkingMoonshot AI$0.975$0.55$2.25IO.NET146 ± 2