Home / Pricing / Long replies

Cheapest models for long replies

Ranked by output rate per 1M tokens. The example uses 1000 input tokens and 2000 output tokens, which is closer to support chat and writing than a short completion.

135 models · rates checked . Price rank only, not a quality score.

Cheapest models for long replies: ranked rates

#ModelProviderContextInput / 1MOutput / 1MLong example10k requests
1Llama 3.2 1B (Groq)Groq128K$0.040/1M$0.040/1M$0.00012$1.2Cost
2Llama 3.2 3B (Groq)Groq128K$0.060/1M$0.060/1M$0.00018$1.8Cost
3Llama 3.2 3B (Together)Together AI128K$0.060/1M$0.060/1M$0.00018$1.8Cost
4Gemma 7B (Groq)Groq8K$0.070/1M$0.070/1M$0.00021$2.1Cost
5Llama 3.1 8B Instant (Groq)Groq128K$0.050/1M$0.080/1M$0.00021$2.1Cost
6Llama 3.2 3B (Fireworks)Fireworks128K$0.100/1M$0.100/1M$0.0003$3.00Cost
7Gemini 1.5 Flash-8BGoogle1M$0.037/1M$0.150/1M$0.000337$3.37Cost
8Command R7BCohere128K$0.037/1M$0.150/1M$0.000337$3.37Cost
9Ministral 8BMistral128K$0.150/1M$0.150/1M$0.00045$4.5Cost
10Mistral NemoMistral128K$0.150/1M$0.150/1M$0.00045$4.5Cost
11Pixtral 12BMistral128K$0.150/1M$0.150/1M$0.00045$4.5Cost
12Llama 3.2 11B Vision (Groq)Groq128K$0.180/1M$0.180/1M$0.00054$5.4Cost
13Llama 3.1 8B (Together)Together AI128K$0.180/1M$0.180/1M$0.00054$5.4Cost
14Gemma 2 9B (Groq)Groq8K$0.200/1M$0.200/1M$0.0006$6.00Cost
15Llama Guard 3 8B (Groq)Groq8K$0.200/1M$0.200/1M$0.0006$6.00Cost
16Mistral 7B (Together)Together AI33K$0.200/1M$0.200/1M$0.0006$6.00Cost
17Llama 3.1 8B (Fireworks)Fireworks128K$0.200/1M$0.200/1M$0.0006$6.00Cost
18MythoMax L2 13B (Fireworks)Fireworks4K$0.200/1M$0.200/1M$0.0006$6.00Cost
19Mixtral 8x7B (Groq)Groq33K$0.240/1M$0.240/1M$0.00072$7.2Cost
20Mistral TinyMistral33K$0.250/1M$0.250/1M$0.00075$7.5Cost
21DeepSeek CoderDeepSeek128K$0.140/1M$0.280/1M$0.0007$7.00Cost
22DeepSeek VLDeepSeek4K$0.140/1M$0.280/1M$0.0007$7.00Cost
23Gemini 1.5 FlashGoogle1M$0.075/1M$0.300/1M$0.000675$6.75Cost
24Gemini 2.0 Flash-LiteGoogle1M$0.075/1M$0.300/1M$0.000675$6.75Cost
25Qwen2.5 7B (Together)Together AI33K$0.300/1M$0.300/1M$0.0009$9.00Cost
26Llama 4 Scout (Groq)Groq128K$0.110/1M$0.340/1M$0.00079$7.9Cost
27QwQ 32B (Groq)Groq128K$0.290/1M$0.390/1M$0.00107$10.7Cost
28GPT-5 NanoOpenAI128K$0.050/1M$0.400/1M$0.00085$8.5Cost
29GPT-4.1 NanoOpenAI1M$0.100/1M$0.400/1M$0.0009$9.00Cost
30Gemini 2.0 FlashGoogle1M$0.100/1M$0.400/1M$0.0009$9.00Cost
31Gemini 2.5 Flash-LiteGoogle1M$0.100/1M$0.400/1M$0.0009$9.00Cost
32Gemma 3 27BGoogle128K$0.200/1M$0.400/1M$0.001$10.00Cost
33DeepSeek ChatDeepSeek128K$0.280/1M$0.420/1M$0.00112$11.2Cost
34GPT-6 LunaOpenAI1.1M$0.100/1M$0.500/1M$0.0011$11.00Cost
35Claude Haiku 5.5Anthropic1M$0.100/1M$0.500/1M$0.0011$11.00Cost
36Grok 2 MinixAI131K$0.200/1M$0.500/1M$0.0012$12.00Cost
37Grok 3 MinixAI131K$0.300/1M$0.500/1M$0.0013$13.00Cost
38Qwen3 32B (Groq)Groq131K$0.290/1M$0.590/1M$0.00147$14.7Cost
39GPT-4o miniOpenAI128K$0.150/1M$0.600/1M$0.00135$13.5Cost
40Mistral SmallMistral128K$0.150/1M$0.600/1M$0.00135$13.5Cost
41Command RCohere128K$0.150/1M$0.600/1M$0.00135$13.5Cost
42Command R (08-2024)Cohere128K$0.150/1M$0.600/1M$0.00135$13.5Cost
43Mistral SabaMistral33K$0.200/1M$0.600/1M$0.0014$14.00Cost
44DeepSeek R1 Distill Qwen 32BDeepSeek128K$0.300/1M$0.600/1M$0.0015$15.00Cost
45Command LightCohere4K$0.300/1M$0.600/1M$0.0015$15.00Cost
46Open Mixtral 8x7BMistral33K$0.700/1M$0.700/1M$0.0021$21.00Cost
47Llama 3.3 70B (Groq)Groq128K$0.590/1M$0.790/1M$0.00217$21.7Cost
48Qwen2.5 Coder 32B (Together)Together AI33K$0.800/1M$0.800/1M$0.0024$24.00Cost
49Llama 4 Maverick (Together)Together AI1M$0.270/1M$0.850/1M$0.00197$19.7Cost
50Llama 4 Maverick (Fireworks)Fireworks1M$0.220/1M$0.880/1M$0.00198$19.8Cost
51Llama 3.1 70B (Together)Together AI128K$0.880/1M$0.880/1M$0.00264$26.4Cost
52Llama 3.3 70B (Together)Together AI128K$0.880/1M$0.880/1M$0.00264$26.4Cost
53CodestralMistral256K$0.300/1M$0.900/1M$0.0021$21.00Cost
54DeepSeek R1 (Fireworks)Fireworks128K$0.900/1M$0.900/1M$0.0027$27.00Cost
55DeepSeek V3 (Fireworks)Fireworks128K$0.900/1M$0.900/1M$0.0027$27.00Cost
56Llama 3.1 70B (Fireworks)Fireworks128K$0.900/1M$0.900/1M$0.0027$27.00Cost
57Llama 3.3 70B (Fireworks)Fireworks128K$0.900/1M$0.900/1M$0.0027$27.00Cost
58Mixtral 8x22B (Fireworks)Fireworks66K$0.900/1M$0.900/1M$0.0027$27.00Cost
59Qwen2.5 32B (Fireworks)Fireworks33K$0.900/1M$0.900/1M$0.0027$27.00Cost
60Qwen2.5 72B (Fireworks)Fireworks33K$0.900/1M$0.900/1M$0.0027$27.00Cost
61Llama 3.3 70B SpecDec (Groq)Groq8K$0.590/1M$0.990/1M$0.00257$25.7Cost
62DeepSeek R1 Distill Llama 70B (Groq)Groq128K$0.750/1M$0.990/1M$0.00273$27.3Cost
63DeepSeek V3DeepSeek128K$0.270/1M$1.10/1M$0.00247$24.7Cost
64GPT-5.6 LunaOpenAI1.1M$0.200/1M$1.20/1M$0.0026$26.00Cost
65DeepSeek V4 FlashDeepSeek1M$0.300/1M$1.20/1M$0.0027$27.00Cost
66Mixtral 8x22B (Together)Together AI66K$1.20/1M$1.20/1M$0.0036$36.00Cost
67Qwen2.5 72B (Together)Together AI33K$1.20/1M$1.20/1M$0.0036$36.00Cost
68Claude 3 HaikuAnthropic200K$0.250/1M$1.25/1M$0.00275$27.5Cost
69DeepSeek V3 (Together)Together AI128K$1.25/1M$1.25/1M$0.00375$37.5Cost
70Gemini 3.1 Flash-LiteGoogle1M$0.250/1M$1.50/1M$0.00325$32.5Cost
71GPT-3.5 TurboOpenAI16K$0.500/1M$1.50/1M$0.0035$35.00Cost
72Gemini 1.0 ProGoogle33K$0.500/1M$1.50/1M$0.0035$35.00Cost
73Mistral Large 3Mistral128K$0.500/1M$1.50/1M$0.0035$35.00Cost
74GPT-4.1 MiniOpenAI1M$0.400/1M$1.60/1M$0.0036$36.00Cost
75GPT-5 MiniOpenAI128K$0.250/1M$2.00/1M$0.00425$42.5Cost
76Command NightlyCohere128K$1.00/1M$2.00/1M$0.005$50.00Cost
77DeepSeek R1DeepSeek128K$0.550/1M$2.19/1M$0.00493$49.3Cost
78DeepSeek ReasonerDeepSeek128K$0.550/1M$2.19/1M$0.00493$49.3Cost
79Gemini 2.5 FlashGoogle1M$0.300/1M$2.50/1M$0.0053$53.00Cost
80Grok 3xAI131K$1.25/1M$2.50/1M$0.00625$62.5Cost
81Grok 4xAI256K$1.25/1M$2.50/1M$0.00625$62.5Cost
82Grok 4 FastxAI256K$1.25/1M$2.50/1M$0.00625$62.5Cost
83Gemini 3 FlashGoogle1M$0.500/1M$3.00/1M$0.0065$65.00Cost
84Gemini 3.8 FlashGoogle1.0M$0.750/1M$3.75/1M$0.00825$82.5Cost
85DeepSeek V4 ProDeepSeek1M$1.32/1M$3.96/1M$0.00924$92.4Cost
86Claude 3.5 HaikuAnthropic200K$0.800/1M$4.00/1M$0.0088$88.00Cost
87o1-miniOpenAI128K$1.10/1M$4.40/1M$0.0099$99.00Cost
88o3-miniOpenAI200K$1.10/1M$4.40/1M$0.0099$99.00Cost
89o4-miniOpenAI200K$1.10/1M$4.40/1M$0.0099$99.00Cost
90Claude Haiku 4.5Anthropic200K$1.00/1M$5.00/1M$0.011$110.00Cost
91Gemini 1.5 ProGoogle2M$1.25/1M$5.00/1M$0.01125$112.5Cost
92Gemini 2.0 Pro ExpGoogle2M$1.25/1M$5.00/1M$0.01125$112.5Cost
93Grok 4.7xAI500K$2.00/1M$6.00/1M$0.014$140.00Cost
94Grok 4.6xAI500K$2.00/1M$6.00/1M$0.014$140.00Cost
95Mistral Large (2407)Mistral128K$2.00/1M$6.00/1M$0.014$140.00Cost
96Open Mixtral 8x22BMistral66K$2.00/1M$6.00/1M$0.014$140.00Cost
97DeepSeek R1 (Together)Together AI128K$3.00/1M$7.00/1M$0.017$170.00Cost
98Mistral Medium 3Mistral128K$1.50/1M$7.50/1M$0.0165$165.00Cost
99GPT-4.1OpenAI1M$2.00/1M$8.00/1M$0.018$180.00Cost
100GPT-4.1 (2025-04-14)OpenAI1M$2.00/1M$8.00/1M$0.018$180.00Cost
101o3OpenAI200K$2.00/1M$8.00/1M$0.018$180.00Cost
102GPT-5OpenAI400K$1.25/1M$10.00/1M$0.02125$212.5Cost
103Gemini 2.5 ProGoogle1M$1.25/1M$10.00/1M$0.02125$212.5Cost
104GPT-6.1 SolOpenAI1.1M$2.00/1M$10.00/1M$0.022$220.00Cost
105Claude Sonnet 5.5Anthropic1M$2.00/1M$10.00/1M$0.022$220.00Cost
106Claude Sonnet 5Anthropic1M$2.00/1M$10.00/1M$0.022$220.00Cost
107Gemini 4 ArgonGoogle1.0M$2.00/1M$10.00/1M$0.022$220.00Cost
108Grok 2xAI131K$2.00/1M$10.00/1M$0.022$220.00Cost
109Grok 2 VisionxAI33K$2.00/1M$10.00/1M$0.022$220.00Cost
110GPT-4oOpenAI128K$2.50/1M$10.00/1M$0.0225$225.00Cost
111GPT-4o (2024-08-06)OpenAI128K$2.50/1M$10.00/1M$0.0225$225.00Cost
112Command ACohere256K$2.50/1M$10.00/1M$0.0225$225.00Cost
113Command R+Cohere128K$2.50/1M$10.00/1M$0.0225$225.00Cost
114Command R+ (08-2024)Cohere128K$2.50/1M$10.00/1M$0.0225$225.00Cost
115GPT-5.6 TerraOpenAI1.1M$2.00/1M$12.00/1M$0.026$260.00Cost
116Gemini 3.1 ProGoogle1M$2.00/1M$12.00/1M$0.026$260.00Cost
117Claude 3.5 SonnetAnthropic200K$3.00/1M$15.00/1M$0.033$330.00Cost
118Claude 3 SonnetAnthropic200K$3.00/1M$15.00/1M$0.033$330.00Cost
119Claude Sonnet 4.6Anthropic1M$3.00/1M$15.00/1M$0.033$330.00Cost
120ChatGPT-4o LatestOpenAI128K$5.00/1M$15.00/1M$0.035$350.00Cost
121Grok BetaxAI131K$5.00/1M$15.00/1M$0.035$350.00Cost
122Grok Vision BetaxAI8K$5.00/1M$15.00/1M$0.035$350.00Cost
123GPT-5.6 SolOpenAI1.1M$4.00/1M$20.00/1M$0.044$440.00Cost
124Claude Opus 5.5Anthropic1M$4.00/1M$20.00/1M$0.044$440.00Cost
125Claude 2.1Anthropic200K$8.00/1M$24.00/1M$0.056$560.00Cost
126Claude Opus 5Anthropic1M$5.00/1M$25.00/1M$0.055$550.00Cost
127Claude Opus 4.6Anthropic1M$5.00/1M$25.00/1M$0.055$550.00Cost
128Claude Opus 4.8Anthropic1M$5.00/1M$25.00/1M$0.055$550.00Cost
129GPT-4 TurboOpenAI128K$10.00/1M$30.00/1M$0.07$700.00Cost
130GPT-6 AstraOpenAI1.1M$10.00/1M$50.00/1M$0.11$1100.00Cost
131Claude Fable 5.1Anthropic1M$10.00/1M$50.00/1M$0.11$1100.00Cost
132o1OpenAI200K$15.00/1M$60.00/1M$0.135$1350.00Cost
133o1-previewOpenAI128K$15.00/1M$60.00/1M$0.135$1350.00Cost
134GPT-4OpenAI8K$30.00/1M$60.00/1M$0.15$1500.00Cost
135Claude 3 OpusAnthropic200K$15.00/1M$75.00/1M$0.165$1650.00Cost

More Cheapest models for long replies tools

LLM cost calculator · Cheapest LLM API · Compare model prices · Cache savings · Batch pricing

Related guides

How LLM API pricing works · Prompt caching explained · Exact vs Approx

Sources and references

Official documentation used for definitions, counting methods, or rate cards. Always confirm critical budgets on the provider page.

Pricing rank FAQ

Why rank by output?
Long answers are billed on output tokens, which are usually more expensive than input. A cheap input rate can still be a costly chat model.
What is the long example?
1000 input tokens and 2000 output tokens at standard rates, no cache and no batch.
Can I change the mix?
Yes. Open Cost on any row and set your own output size and monthly volume.