Deals of the day
26 models, one provider far cheaper
Every model at least three providers sell where the cheapest is 25% or more below what the others typically charge. Read across a row to see each provider's price. See all models for the rest.
| Model | Typical | OpenRouter | DeepInfra | Experiential | Bedrock | Together | DashScope | Fireworks | Volcengine | Zhipu | Azure | Cerebras | Groq | Mistral | Moonshot | DeepSeek | Vertex |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 0731DeepSeek · text.chat, text.reasoning, code | $0.660 | $0.113−83% | $0.090−86% | $0.660typical | $0.668+1% | ||||||||||||
| Llama 3.3 70B Instruct (US)Meta · text.chat | $0.710 | $0.749+5% | $0.155−78% | $0.710typical | |||||||||||||
| GLM-5.3-FlashZhipu AI (Z.ai) · text.chat, text.reasoning, code, vision.understand, vision.extract | $0.237 | $0.052−78% | $0.237typical | $0.237typical | $0.237typical | $0.237typical | $0.193−19% | $0.194−18% | $0.237typical | ||||||||
| gpt-oss-120bOpenAI · text.chat, text.reasoning, code | $0.263 | $0.277+6% | $0.070−73% | $0.158−40% | $0.263typical | $0.263typical | $0.450+71% | $0.263typical | $0.158−40% | ||||||||
| gpt-oss-20bOpenAI · text.chat, text.reasoning, code | $0.058 | $0.058typical | $0.058−1% | $0.018−69% | $0.128+120% | $0.131+126% | |||||||||||
| DeepSeek V4 FlashDeepSeek · text.chat, text.reasoning, code | $0.270 | $0.119−56% | $0.113−58% | $0.270typical | $0.270typical | ||||||||||||
| Qwen3.5 9BAlibaba (Qwen) · text.chat, text.reasoning, code, vision.understand, vision.extract | $0.098 | $0.098typical | $0.113+15% | $0.046−53% | |||||||||||||
| GLM-4.6VZhipu AI (Z.ai) · text.chat, text.reasoning, code, vision.understand, vision.extract | $0.450 | $0.475+5% | $0.450typical | $0.224−50% | |||||||||||||
| GLM-5.3Zhipu AI (Z.ai) · text.chat, text.reasoning, code | $1.94 | $1.02−48% | $1.68−14% | $2.69+38% | $2.58+33% | $2.15+11% | $1.79−8% | $1.50−23% | $1.94typical | $2.15+11% | |||||||
| GLM-5.2Zhipu AI (Z.ai) · text.chat, text.reasoning, code | $2.15 | $1.80−16% | $1.16−46% | $2.15typical | $2.15typical | $2.15typical | $1.93−10% | ||||||||||
| Seed 2.0 MiniByteDance Seed · text.chat, text.reasoning, code, vision.understand, vision.extract | $0.175 | $0.185+6% | $0.175typical | $0.096−45% | |||||||||||||
| Qwen3 VL 235B A22B InstructAlibaba (Qwen) · text.chat, vision.understand, vision.extract | $0.667 | $0.667typical | $0.370−45% | $1.06+59% | |||||||||||||
| DeepSeek V4.1 FlashDeepSeek · text.chat, text.reasoning, code, vision.understand, vision.extract | $0.525 | $0.554+5% | $0.300−43% | $0.525typical | $0.525typical | $0.521−1% | $0.367−30% | ||||||||||
| DeepSeek V4 ProDeepSeek · text.chat, text.reasoning, code | $2.17 | $1.26−42% | $1.63−25% | $2.17typical | $2.17typical | ||||||||||||
| Kimi K3.1 Pro Highspeed (US)Moonshot AI · text.chat, text.reasoning, code, vision.understand, vision.extract | $4.00 | $2.41−40% | $4.00typical | $8.00+100% | $4.00typical | $4.00typical | $4.00typical | ||||||||||
| Gemma 4 31B ITGoogle · text.chat, text.reasoning, code, vision.understand, vision.extract | $0.250 | $0.264+5% | $0.250typical | $0.152−39% | $0.205−18% | ||||||||||||
| Qwen3.7 MaxAlibaba (Qwen) · text.chat, text.reasoning, code | $3.75 | $2.33−38% | $3.75typical | $3.75typical | $3.75typical | ||||||||||||
| Qwen3 235B-A22B Instruct 2507Alibaba (Qwen) · text.chat | $0.322 | $0.322typical | $0.205−36% | $0.385+20% | |||||||||||||
| Gemma 3 27B ITGoogle · text.chat, vision.understand, vision.extract | $0.156 | $0.156typical | $0.100−36% | $0.172+11% | |||||||||||||
| Gemma 4 26B A4B ITGoogle · text.chat, text.reasoning, code, vision.understand, vision.extract | $0.198 | $0.128−35% | $0.138−30% | $0.263+33% | $0.198typical | ||||||||||||
| DeepSeek V4 ProDeepSeek · text.chat, text.reasoning, code | $1.78 | $1.26−29% | $1.63−9% | $1.78typical | $1.98+11% | $2.00+12% | $1.20−33% | ||||||||||
| Qwen3.6 PlusAlibaba (Qwen) · text.chat, text.reasoning, code, vision.understand, vision.extract | $1.13 | $0.771−31% | $1.13typical | $1.13typical | |||||||||||||
| GLM-5V-TurboZhipu AI (Z.ai) · text.chat, text.reasoning, code, vision.understand, vision.extract | $1.90 | $2.00+6% | $1.90typical | $1.38−27% | |||||||||||||
| Kimi K3Moonshot AI · text.chat, text.reasoning, code, vision.understand, vision.extract | $6.00 | $4.37−27% | $5.70−5% | $6.00typical | $6.00typical | $6.00typical | $6.00typical | $6.00typical | $6.00typical | ||||||||
| Qwen3.8 27BAlibaba (Qwen) · text.chat, text.reasoning, code, vision.understand, vision.extract | $0.840 | $0.613−27% | $0.775−8% | $0.840typical | $1.11+33% | ||||||||||||
| GLM-4.7Zhipu AI (Z.ai) · text.chat, text.reasoning, code | $1.00 | $1.05+5% | $0.738−26% | $1.00typical |
- DeepSeek V4 Flash 0731DeepSeek · text.chat, text.reasoning, codetypical $0.660
- DeepInfra$0.090−86%
- OpenRouter$0.113−83%
- Experiential$0.660typical
- Volcengine$0.668+1%
- Llama 3.3 70B Instruct (US)Meta · text.chattypical $0.710
- DeepInfra$0.155−78%
- Azure$0.710typical
- OpenRouter$0.749+5%
- GLM-5.3-FlashZhipu AI (Z.ai) · text.chat, text.reasoning, code, vision.understand, vision.extracttypical $0.237
- OpenRouter$0.052−78%
- Volcengine$0.193−19%
- Zhipu$0.194−18%
- DeepInfra$0.237typical
- Experiential$0.237typical
- Fireworks$0.237typical
- Mistral$0.237typical
- Together$0.237typical
- gpt-oss-120bOpenAI · text.chat, text.reasoning, codetypical $0.263
- DeepInfra$0.070−73%
- Experiential$0.158−40%
- Vertex$0.158−40%
- Bedrock$0.263typical
- Groq$0.263typical
- Together$0.263typical
- OpenRouter$0.277+6%
- Cerebras$0.450+71%
- gpt-oss-20bOpenAI · text.chat, text.reasoning, codetypical $0.058
- Experiential$0.018−69%
- DeepInfra$0.058−1%
- OpenRouter$0.058typical
- Bedrock$0.128+120%
- Groq$0.131+126%
- DeepSeek V4 FlashDeepSeek · text.chat, text.reasoning, codetypical $0.270
- DeepInfra$0.113−58%
- OpenRouter$0.119−56%
- Azure$0.270typical
- Experiential$0.270typical
- Qwen3.5 9BAlibaba (Qwen) · text.chat, text.reasoning, code, vision.understand, vision.extracttypical $0.098
- Experiential$0.046−53%
- OpenRouter$0.098typical
- DeepInfra$0.113+15%
- GLM-4.6VZhipu AI (Z.ai) · text.chat, text.reasoning, code, vision.understand, vision.extracttypical $0.450
- Zhipu$0.224−50%
- Experiential$0.450typical
- OpenRouter$0.475+5%
- GLM-5.3Zhipu AI (Z.ai) · text.chat, text.reasoning, codetypical $1.94
- OpenRouter$1.02−48%
- Fireworks$1.50−23%
- DeepInfra$1.68−14%
- DashScope$1.79−8%
- Zhipu$1.94typical
- Mistral$2.15+11%
- Together$2.15+11%
- Bedrock$2.58+33%
- Experiential$2.69+38%
- GLM-5.2Zhipu AI (Z.ai) · text.chat, text.reasoning, codetypical $2.15
- DeepInfra$1.16−46%
- OpenRouter$1.80−16%
- Volcengine$1.93−10%
- DashScope$2.15typical
- Experiential$2.15typical
- Together$2.15typical
- Seed 2.0 MiniByteDance Seed · text.chat, text.reasoning, code, vision.understand, vision.extracttypical $0.175
- Volcengine$0.096−45%
- DeepInfra$0.175typical
- OpenRouter$0.185+6%
- Qwen3 VL 235B A22B InstructAlibaba (Qwen) · text.chat, vision.understand, vision.extracttypical $0.667
- DeepInfra$0.370−45%
- OpenRouter$0.667typical
- Bedrock$1.06+59%
- DeepSeek V4.1 FlashDeepSeek · text.chat, text.reasoning, code, vision.understand, vision.extracttypical $0.525
- DeepInfra$0.300−43%
- Fireworks$0.367−30%
- DashScope$0.521−1%
- Experiential$0.525typical
- Together$0.525typical
- OpenRouter$0.554+5%
- DeepSeek V4 ProDeepSeek · text.chat, text.reasoning, codetypical $2.17
- OpenRouter$1.26−42%
- DeepInfra$1.63−25%
- Azure$2.17typical
- Experiential$2.17typical
- Kimi K3.1 Pro Highspeed (US)Moonshot AI · text.chat, text.reasoning, code, vision.understand, vision.extracttypical $4.00
- OpenRouter$2.41−40%
- DeepInfra$4.00typical
- Fireworks$4.00typical
- Moonshot$4.00typical
- Together$4.00typical
- Bedrock$8.00+100%
- Gemma 4 31B ITGoogle · text.chat, text.reasoning, code, vision.understand, vision.extracttypical $0.250
- Experiential$0.152−39%
- Bedrock$0.205−18%
- DeepInfra$0.250typical
- OpenRouter$0.264+5%
- Qwen3.7 MaxAlibaba (Qwen) · text.chat, text.reasoning, codetypical $3.75
- OpenRouter$2.33−38%
- DashScope$3.75typical
- DeepInfra$3.75typical
- Experiential$3.75typical
- Qwen3 235B-A22B Instruct 2507Alibaba (Qwen) · text.chattypical $0.322
- DeepInfra$0.205−36%
- OpenRouter$0.322typical
- Bedrock$0.385+20%
- Gemma 3 27B ITGoogle · text.chat, vision.understand, vision.extracttypical $0.156
- DeepInfra$0.100−36%
- OpenRouter$0.156typical
- Experiential$0.172+11%
- Gemma 4 26B A4B ITGoogle · text.chat, text.reasoning, code, vision.understand, vision.extracttypical $0.198
- OpenRouter$0.128−35%
- DeepInfra$0.138−30%
- Bedrock$0.198typical
- Experiential$0.263+33%
- DeepSeek V4 ProDeepSeek · text.chat, text.reasoning, codetypical $1.78
- DeepSeek$1.20−33%
- OpenRouter$1.26−29%
- DeepInfra$1.63−9%
- Experiential$1.78typical
- Together$1.98+11%
- Volcengine$2.00+12%
- Qwen3.6 PlusAlibaba (Qwen) · text.chat, text.reasoning, code, vision.understand, vision.extracttypical $1.13
- OpenRouter$0.771−31%
- DashScope$1.13typical
- Together$1.13typical
- GLM-5V-TurboZhipu AI (Z.ai) · text.chat, text.reasoning, code, vision.understand, vision.extracttypical $1.90
- Zhipu$1.38−27%
- Experiential$1.90typical
- OpenRouter$2.00+6%
- Kimi K3Moonshot AI · text.chat, text.reasoning, code, vision.understand, vision.extracttypical $6.00
- OpenRouter$4.37−27%
- DeepInfra$5.70−5%
- Bedrock$6.00typical
- DashScope$6.00typical
- Experiential$6.00typical
- Fireworks$6.00typical
- Moonshot$6.00typical
- Together$6.00typical
- Qwen3.8 27BAlibaba (Qwen) · text.chat, text.reasoning, code, vision.understand, vision.extracttypical $0.840
- OpenRouter$0.613−27%
- DeepInfra$0.775−8%
- Experiential$0.840typical
- Cerebras$1.11+33%
- GLM-4.7Zhipu AI (Z.ai) · text.chat, text.reasoning, codetypical $1.00
- DeepInfra$0.738−26%
- Experiential$1.00typical
- OpenRouter$1.05+5%
No deal matches that filter.
- Cheapest provider
- −23%Below typical
- +33%Above typical
- Not sold there
Prices are US dollars per 1M tokens at 3 input to 1 output, with each provider's fees included. Typical is the median of every provider except the cheapest, the lower of the two middle prices when their number is even. Only metered, generally available prices count; trial, free and unverified ones never do, and neither does a discount over 90%, which is more often a source's mistake than an offer.
Built from catalog version 2026-11-13.1 of . Prices are list prices per 1M tokens unless marked otherwise; every score shows its source's notice (see Attributions).