Back to home
LLM Model Pricing Comparison 2026
Input and output token costs per 1M tokens across 392 models from OpenAI, Anthropic, Google AI, Mistral, DeepSeek, and OpenRouter. Prices sourced from provider billing APIs.
Input tokens
Cost for the text you send to the model (your prompt + context).
Output tokens
Cost for text the model generates. Typically 3–5× more expensive than input.
Why LLMeter?
LLMeter tracks your actual spend across all providers automatically — no manual spreadsheets.
Showing 392 of 392 models
Anthropic(37 models)
| Model | Tier | Input / 1M tokens | Output / 1M tokens |
|---|---|---|---|
Claude Haiku 5.5 (batch) claude-haiku-5.5:batch | Budget | $0.050 | $0.250 |
Claude Haiku 5.5 claude-haiku-5.5 | Budget | $0.100 | $0.500 |
Claude 3 Haiku claude-3-haiku | Budget | $0.250 | $1.25 |
Claude Haiku 4.5 (batch) claude-haiku-4.5:batch | Budget | $0.500 | $2.50 |
Claude 3.5 Haiku claude-3.5-haiku | Budget | $0.800 | $4.00 |
Claude Haiku 4.5 claude-haiku-4.5 | Standard | $1.00 | $5.00 |
Claude Sonnet 5 (batch) claude-sonnet-5:batch | Standard | $1.00 | $5.00 |
Claude Sonnet 5.5 (batch) claude-sonnet-5.5:batch | Standard | $1.00 | $5.00 |
Claude Sonnet 4.5 (batch) claude-sonnet-4.5:batch | Standard | $1.50 | $7.50 |
Claude Sonnet 4.6 (batch) claude-sonnet-4.6:batch | Standard | $1.50 | $7.50 |
Claude Opus 5.5 (batch) claude-opus-5.5:batch | Standard | $2.00 | $10.00 |
Claude Sonnet 5 claude-sonnet-5 | Standard | $2.00 | $10.00 |
Claude Sonnet 5.5 claude-sonnet-5.5 | Standard | $2.00 | $10.00 |
Claude Opus 4.5 (batch) claude-opus-4.5:batch | Standard | $2.50 | $12.50 |
Claude Opus 4.6 (batch) claude-opus-4.6:batch | Standard | $2.50 | $12.50 |
Claude Opus 4.7 (batch) claude-opus-4.7:batch | Standard | $2.50 | $12.50 |
Claude Opus 4.8 (batch) claude-opus-4.8:batch | Standard | $2.50 | $12.50 |
Claude Opus 5 (batch) claude-opus-5:batch | Standard | $2.50 | $12.50 |
Claude Sonnet 4 claude-sonnet-4 | Standard | $3.00 | $15.00 |
Claude Sonnet 4.5 claude-sonnet-4.5 | Standard | $3.00 | $15.00 |
Claude Sonnet 4.6 claude-sonnet-4.6 | Standard | $3.00 | $15.00 |
Claude Opus 5.5 claude-opus-5.5 | Standard | $4.00 | $20.00 |
Claude Fable 5 (batch) claude-fable-5:batch | Standard | $5.00 | $25.00 |
Claude Fable 5.1 (batch) claude-fable-5.1:batch | Standard | $5.00 | $25.00 |
Claude Opus 4.5 claude-opus-4.5 | Standard | $5.00 | $25.00 |
Claude Opus 4.6 claude-opus-4.6 | Standard | $5.00 | $25.00 |
Claude Opus 4.7 claude-opus-4.7 | Standard | $5.00 | $25.00 |
Claude Opus 4.8 claude-opus-4.8 | Standard | $5.00 | $25.00 |
Claude Opus 5 claude-opus-5 | Standard | $5.00 | $25.00 |
Claude Opus 4.1 (batch) claude-opus-4.1:batch | Standard | $7.50 | $37.50 |
Claude Fable 5 claude-fable-5 | Premium | $10.00 | $50.00 |
Claude Fable 5.1 claude-fable-5.1 | Premium | $10.00 | $50.00 |
Claude Opus 4.8 (Fast) claude-opus-4.8-fast | Premium | $10.00 | $50.00 |
Claude Opus 4.1 claude-opus-4.1 | Premium | $15.00 | $75.00 |
Claude Opus 4 claude-opus-4 | Premium | $15.00 | $75.00 |
Claude Opus 4.6 (Fast) claude-opus-4.6-fast | Premium | $30.00 | $150.00 |
Claude Opus 4.7 (Fast) claude-opus-4.7-fast | Premium | $30.00 | $150.00 |
OpenAI(118 models)
| Model | Tier | Input / 1M tokens | Output / 1M tokens |
|---|---|---|---|
gpt-oss-120b (free) gpt-oss-120b:free | Budget | $0 | $0 |
gpt-oss-20b (free) gpt-oss-20b:free | Budget | $0 | $0 |
gpt-oss-20b gpt-oss-20b | Budget | $0.018 | $0.090 |
gpt-oss-20b (batch) gpt-oss-20b:batch | Budget | $0.024 | $0.112 |
GPT-5 Nano (batch) gpt-5-nano:batch | Budget | $0.025 | $0.200 |
gpt-oss-120b (batch) gpt-oss-120b:batch | Budget | $0.030 | $0.136 |
gpt-oss-120b gpt-oss-120b | Budget | $0.037 | $0.170 |
GPT-4.1 Nano (batch) gpt-4.1-nano:batch | Budget | $0.050 | $0.200 |
GPT-5 Nano gpt-5-nano | Budget | $0.050 | $0.400 |
GPT-6 Luna Pro (batch) gpt-6-luna-pro:batch | Budget | $0.050 | $0.250 |
GPT-6 Luna (batch) gpt-6-luna:batch | Budget | $0.050 | $0.250 |
GPT-4o-mini (batch) gpt-4o-mini:batch | Budget | $0.075 | $0.300 |
gpt-oss-safeguard-20b gpt-oss-safeguard-20b | Budget | $0.075 | $0.300 |
GPT-4.1 Nano gpt-4.1-nano | Budget | $0.100 | $0.400 |
GPT-5.4 Nano (batch) gpt-5.4-nano:batch | Budget | $0.100 | $0.625 |
GPT-5.6 Luna Pro (batch) gpt-5.6-luna-pro:batch | Budget | $0.100 | $0.600 |
GPT-5.6 Luna (batch) gpt-5.6-luna:batch | Budget | $0.100 | $0.600 |
GPT-6 Luna gpt-6-luna | Budget | $0.100 | $0.500 |
GPT-6 Luna Pro gpt-6-luna-pro | Budget | $0.100 | $0.500 |
GPT-5 Mini (batch) gpt-5-mini:batch | Budget | $0.125 | $1.00 |
GPT-4o-mini gpt-4o-mini | Budget | $0.150 | $0.600 |
GPT-4o-mini (2024-07-18) gpt-4o-mini-2024-07-18 | Budget | $0.150 | $0.600 |
GPT-4o-mini Search Preview gpt-4o-mini-search-preview | Budget | $0.150 | $0.600 |
GPT-4.1 Mini (batch) gpt-4.1-mini:batch | Budget | $0.200 | $0.800 |
GPT-5.4 Nano gpt-5.4-nano | Budget | $0.200 | $1.25 |
GPT-5.6 Luna gpt-5.6-luna | Budget | $0.200 | $1.20 |
GPT-5.6 Luna Pro gpt-5.6-luna-pro | Budget | $0.200 | $1.20 |
GPT-3.5 Turbo (batch) gpt-3.5-turbo:batch | Budget | $0.250 | $0.750 |
GPT-5 Mini gpt-5-mini | Budget | $0.250 | $2.00 |
GPT-5.1-Codex-Mini gpt-5.1-codex-mini | Budget | $0.250 | $2.00 |
GPT-5.4 Mini (batch) gpt-5.4-mini:batch | Budget | $0.375 | $2.25 |
GPT-4.1 Mini gpt-4.1-mini | Budget | $0.400 | $1.60 |
GPT-3.5 Turbo gpt-3.5-turbo | Budget | $0.500 | $1.50 |
o3 Mini (batch) o3-mini:batch | Budget | $0.550 | $2.20 |
o4 Mini (batch) o4-mini:batch | Budget | $0.550 | $2.20 |
GPT Audio Mini gpt-audio-mini | Budget | $0.600 | $2.40 |
GPT-5 (batch) gpt-5:batch | Budget | $0.625 | $5.00 |
GPT-5.1 (batch) gpt-5.1:batch | Budget | $0.625 | $5.00 |
GPT-5.4 Mini gpt-5.4-mini | Budget | $0.750 | $4.50 |
GPT-5.2 (batch) gpt-5.2:batch | Budget | $0.875 | $7.00 |
GPT-3.5 Turbo (older v0613) gpt-3.5-turbo-0613 | Standard | $1.00 | $2.00 |
GPT-4.1 (batch) gpt-4.1:batch | Standard | $1.00 | $4.00 |
GPT-5.6 Sol Pro (batch) gpt-5.6-sol-pro:batch | Standard | $1.00 | $5.00 |
GPT-5.6 Sol (batch) gpt-5.6-sol:batch | Standard | $1.00 | $5.00 |
GPT-5.6 Terra Pro (batch) gpt-5.6-terra-pro:batch | Standard | $1.00 | $6.00 |
GPT-5.6 Terra (batch) gpt-5.6-terra:batch | Standard | $1.00 | $6.00 |
GPT-6 Sol Pro (batch) gpt-6-sol-pro:batch | Standard | $1.00 | $5.00 |
GPT-6 Sol (batch) gpt-6-sol:batch | Standard | $1.00 | $5.00 |
GPT-6.1 Sol Pro (batch) gpt-6.1-sol-pro:batch | Standard | $1.00 | $5.00 |
GPT-6.1 Sol (batch) gpt-6.1-sol:batch | Standard | $1.00 | $5.00 |
o3 (batch) o3:batch | Standard | $1.00 | $4.00 |
o3 Mini o3-mini | Standard | $1.10 | $4.40 |
o3 Mini High o3-mini-high | Standard | $1.10 | $4.40 |
o4 Mini o4-mini | Standard | $1.10 | $4.40 |
o4 Mini High o4-mini-high | Standard | $1.10 | $4.40 |
GPT-4o (batch) gpt-4o:batch | Standard | $1.25 | $5.00 |
GPT-5 gpt-5 | Standard | $1.25 | $10.00 |
GPT-5.1 gpt-5.1 | Standard | $1.25 | $10.00 |
GPT-5.1-Codex gpt-5.1-codex | Standard | $1.25 | $10.00 |
GPT-5.1-Codex-Max gpt-5.1-codex-max | Standard | $1.25 | $10.00 |
GPT-5.4 (batch) gpt-5.4:batch | Standard | $1.25 | $7.50 |
GPT-5 Chat gpt-5-chat | Standard | $1.25 | $10.00 |
GPT-5 Codex gpt-5-codex | Standard | $1.25 | $10.00 |
GPT-5.1 Chat gpt-5.1-chat | Standard | $1.25 | $10.00 |
GPT-3.5 Turbo Instruct gpt-3.5-turbo-instruct | Standard | $1.50 | $2.00 |
GPT-5.2 gpt-5.2 | Standard | $1.75 | $14.00 |
GPT-5.2 Chat gpt-5.2-chat | Standard | $1.75 | $14.00 |
GPT-5.2-Codex gpt-5.2-codex | Standard | $1.75 | $14.00 |
GPT-5.3-Codex gpt-5.3-codex | Standard | $1.75 | $14.00 |
GPT-5.3 Chat gpt-5.3-chat | Standard | $1.75 | $14.00 |
GPT-4.1 gpt-4.1 | Standard | $2.00 | $8.00 |
GPT-5.6 Sol gpt-5.6-sol | Standard | $2.00 | $10.00 |
GPT-5.6 Sol Pro gpt-5.6-sol-pro | Standard | $2.00 | $10.00 |
GPT-5.6 Terra gpt-5.6-terra | Standard | $2.00 | $12.00 |
GPT-5.6 Terra Pro gpt-5.6-terra-pro | Standard | $2.00 | $12.00 |
GPT-6 Sol gpt-6-sol | Standard | $2.00 | $10.00 |
GPT-6 Sol Pro gpt-6-sol-pro | Standard | $2.00 | $10.00 |
GPT-6.1 Sol gpt-6.1-sol | Standard | $2.00 | $10.00 |
GPT-6.1 Sol Pro gpt-6.1-sol-pro | Standard | $2.00 | $10.00 |
o3 o3 | Standard | $2.00 | $8.00 |
o4 Mini Deep Research o4-mini-deep-research | Standard | $2.00 | $8.00 |
GPT-4o gpt-4o | Standard | $2.50 | $10.00 |
GPT-4o (2024-08-06) gpt-4o-2024-08-06 | Standard | $2.50 | $10.00 |
GPT-4o (2024-11-20) gpt-4o-2024-11-20 | Standard | $2.50 | $10.00 |
GPT-5 Image Mini gpt-5-image-mini | Standard | $2.50 | $2.00 |
GPT-5.4 gpt-5.4 | Standard | $2.50 | $15.00 |
GPT-5.5 (batch) gpt-5.5:batch | Standard | $2.50 | $15.00 |
GPT Audio gpt-audio | Standard | $2.50 | $10.00 |
GPT-4o Search Preview gpt-4o-search-preview | Standard | $2.50 | $10.00 |
GPT-4o Audio gpt-4o-audio-preview | Standard | $2.50 | $10.00 |
GPT-3.5 Turbo 16k gpt-3.5-turbo-16k | Standard | $3.00 | $4.00 |
GPT-4 Turbo (batch) gpt-4-turbo:batch | Standard | $5.00 | $15.00 |
GPT-4o (2024-05-13) gpt-4o-2024-05-13 | Standard | $5.00 | $15.00 |
GPT-5.5 gpt-5.5 | Standard | $5.00 | $30.00 |
GPT-6 Astra Pro (batch) gpt-6-astra-pro:batch | Standard | $5.00 | $25.00 |
GPT-6 Astra (batch) gpt-6-astra:batch | Standard | $5.00 | $25.00 |
GPT Chat Latest gpt-chat-latest | Standard | $5.00 | $30.00 |
GPT-5 Pro (batch) gpt-5-pro:batch | Standard | $7.50 | $60.00 |
GPT-5.4 Image 2 gpt-5.4-image-2 | Standard | $8.00 | $15.00 |
GPT-4 Turbo gpt-4-turbo | Premium | $10.00 | $30.00 |
GPT-5 Image gpt-5-image | Premium | $10.00 | $10.00 |
GPT-6 Astra gpt-6-astra | Premium | $10.00 | $50.00 |
GPT-6 Astra Pro gpt-6-astra-pro | Premium | $10.00 | $50.00 |
GPT-4 Turbo Preview gpt-4-turbo-preview | Premium | $10.00 | $30.00 |
o3 Deep Research o3-deep-research | Premium | $10.00 | $40.00 |
GPT-4 Turbo (older v1106) gpt-4-1106-preview | Premium | $10.00 | $30.00 |
GPT-5.2 Pro (batch) gpt-5.2-pro:batch | Premium | $10.50 | $84.00 |
GPT-5 Pro gpt-5-pro | Premium | $15.00 | $120.00 |
GPT-5.4 Pro (batch) gpt-5.4-pro:batch | Premium | $15.00 | $90.00 |
GPT-5.5 Pro (batch) gpt-5.5-pro:batch | Premium | $15.00 | $90.00 |
o1 o1 | Premium | $15.00 | $60.00 |
o3 Pro o3-pro | Premium | $20.00 | $80.00 |
GPT-5.2 Pro gpt-5.2-pro | Premium | $21.00 | $168.00 |
GPT-4 gpt-4 | Premium | $30.00 | $60.00 |
GPT-5.4 Pro gpt-5.4-pro | Premium | $30.00 | $180.00 |
GPT-5.5 Pro gpt-5.5-pro | Premium | $30.00 | $180.00 |
GPT-4 (older v0314) gpt-4-0314 | Premium | $30.00 | $60.00 |
o1-pro o1-pro | Premium | $150.00 | $600.00 |
DeepSeek(18 models)
| Model | Tier | Input / 1M tokens | Output / 1M tokens |
|---|---|---|---|
DeepSeek V4 Flash 0731 deepseek-v4-flash-0731 | Budget | $0.016 | $0.640 |
DeepSeek V4 Flash 0423 deepseek-v4-flash | Budget | $0.030 | $1.28 |
DeepSeek V4.1 Flash (batch) deepseek-v4.1-flash:batch | Budget | $0.112 | $0.336 |
DeepSeek V4.1 Flash deepseek-v4.1-flash | Budget | $0.150 | $0.600 |
DeepSeek V4 Flash Vision Exp deepseek-v4-flash-vision-exp | Budget | $0.216 | $0.647 |
DeepSeek V3.1 deepseek-chat-v3.1 | Budget | $0.250 | $0.950 |
DeepSeek V3.2 deepseek-v3.2 | Budget | $0.259 | $0.800 |
DeepSeek V3.1 Terminus deepseek-v3.1-terminus | Budget | $0.270 | $1.00 |
DeepSeek V3.2 Exp deepseek-v3.2-exp | Budget | $0.270 | $0.410 |
DeepSeek V3.2 Speciale deepseek-v3.2-speciale | Budget | $0.287 | $0.431 |
DeepSeek V3 0324 deepseek-chat-v3-0324 | Budget | $0.290 | $1.14 |
R1 Distill Qwen 32B deepseek-r1-distill-qwen-32b | Budget | $0.290 | $0.290 |
DeepSeek V3 deepseek-chat | Budget | $0.320 | $0.890 |
DeepSeek V4 Pro 0423 deepseek-v4-pro | Budget | $0.434 | $0.869 |
R1 0528 deepseek-r1-0528 | Budget | $0.500 | $2.15 |
DeepSeek V4 Pro 0813 deepseek-v4-pro-0813 | Budget | $0.660 | $1.98 |
R1 deepseek-r1 | Budget | $0.700 | $2.50 |
R1 Distill Llama 70B deepseek-r1-distill-llama-70b | Budget | $0.800 | $0.800 |
Google AI(47 models)
| Model | Tier | Input / 1M tokens | Output / 1M tokens |
|---|---|---|---|
Gemma 4 26B A4B (free) gemma-4-26b-a4b-it:free | Budget | $0 | $0 |
Gemma 4 31B (free) gemma-4-31b-it:free | Budget | $0 | $0 |
Lyria 3 Clip Preview lyria-3-clip-preview | Budget | $0 | $0 |
Lyria 3 Pro Preview lyria-3-pro-preview | Budget | $0 | $0 |
Gemini 2.5 Flash Lite (batch) gemini-2.5-flash-lite:batch | Budget | $0.050 | $0.200 |
Gemma 3 12B gemma-3-12b-it | Budget | $0.050 | $0.150 |
Gemma 3 4B gemma-3-4b-it | Budget | $0.050 | $0.100 |
Gemma 3n 4B gemma-3n-e4b-it | Budget | $0.060 | $0.120 |
Gemini 2.0 Flash Lite gemini-2.0-flash-lite-001 | Budget | $0.075 | $0.300 |
Gemma 3 27B gemma-3-27b-it | Budget | $0.080 | $0.450 |
Gemma 4 26B A4B gemma-4-26b-a4b-it | Budget | $0.090 | $0.300 |
Gemma 4 31B gemma-4-31b-it | Budget | $0.090 | $0.340 |
Gemini 2.5 Flash Lite gemini-2.5-flash-lite | Budget | $0.100 | $0.400 |
Gemini 2.5 Flash Lite Preview 09-2025 gemini-2.5-flash-lite-preview-09-2025 | Budget | $0.100 | $0.400 |
Gemini 2.0 Flash gemini-2.0-flash-001 | Budget | $0.100 | $0.400 |
Gemini 3.1 Flash Lite (batch) gemini-3.1-flash-lite:batch | Budget | $0.125 | $0.750 |
Gemini 2.5 Flash (batch) gemini-2.5-flash:batch | Budget | $0.150 | $1.25 |
Gemini 3.5 Flash Lite (batch) gemini-3.5-flash-lite:batch | Budget | $0.150 | $1.25 |
Gemini 3 Flash Preview (batch) gemini-3-flash-preview:batch | Budget | $0.250 | $1.50 |
Gemini 3.1 Flash Lite gemini-3.1-flash-lite | Budget | $0.250 | $1.50 |
Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) gemini-3.1-flash-lite-image | Budget | $0.250 | $1.50 |
Gemini 3.1 Flash Lite Preview gemini-3.1-flash-lite-preview | Budget | $0.250 | $1.50 |
Gemini 2.5 Flash gemini-2.5-flash | Budget | $0.300 | $2.50 |
Nano Banana (Gemini 2.5 Flash Image) gemini-2.5-flash-image | Budget | $0.300 | $2.50 |
Gemini 3.5 Flash Lite gemini-3.5-flash-lite | Budget | $0.300 | $2.50 |
Gemini 3.6 Flash (batch) gemini-3.6-flash:batch | Budget | $0.375 | $1.88 |
Gemini 3.7 Flash (batch) gemini-3.7-flash:batch | Budget | $0.375 | $1.88 |
Gemini 3.8 Flash (batch) gemini-3.8-flash:batch | Budget | $0.375 | $1.88 |
Gemini 3 Flash Preview gemini-3-flash-preview | Budget | $0.500 | $3.00 |
Nano Banana 2 (Gemini 3.1 Flash Image) gemini-3.1-flash-image | Budget | $0.500 | $3.00 |
Nano Banana 2 (Gemini 3.1 Flash Image Preview) gemini-3.1-flash-image-preview | Budget | $0.500 | $3.00 |
Gemini 2.5 Pro (batch) gemini-2.5-pro:batch | Budget | $0.625 | $5.00 |
Gemma 2 27B gemma-2-27b-it | Budget | $0.650 | $0.650 |
Gemini 3.5 Flash (batch) gemini-3.5-flash:batch | Budget | $0.750 | $4.50 |
Gemini 3.6 Flash gemini-3.6-flash | Budget | $0.750 | $3.75 |
Gemini 3.7 Flash gemini-3.7-flash | Budget | $0.750 | $3.75 |
Gemini 3.8 Flash gemini-3.8-flash | Budget | $0.750 | $3.75 |
Gemini 3.1 Pro Preview (batch) gemini-3.1-pro-preview:batch | Standard | $1.00 | $6.00 |
Gemini 2.5 Pro gemini-2.5-pro | Standard | $1.25 | $10.00 |
Gemini 2.5 Pro Preview 06-05 gemini-2.5-pro-preview | Standard | $1.25 | $10.00 |
Gemini 2.5 Pro Preview 05-06 gemini-2.5-pro-preview-05-06 | Standard | $1.25 | $10.00 |
Gemini 3.5 Flash gemini-3.5-flash | Standard | $1.50 | $9.00 |
Nano Banana 2.1 gemini-nano-banana-2.1 | Standard | $1.50 | $7.50 |
Nano Banana Pro (Gemini 3 Pro Image) gemini-3-pro-image | Standard | $2.00 | $12.00 |
Nano Banana Pro (Gemini 3 Pro Image Preview) gemini-3-pro-image-preview | Standard | $2.00 | $12.00 |
Gemini 3.1 Pro Preview gemini-3.1-pro-preview | Standard | $2.00 | $12.00 |
Gemini 3.1 Pro Preview Custom Tools gemini-3.1-pro-preview-customtools | Standard | $2.00 | $12.00 |
xai(6 models)
| Model | Tier | Input / 1M tokens | Output / 1M tokens |
|---|---|---|---|
Grok 3 Mini grok-3-mini | Budget | $0.300 | $0.500 |
Grok 3 Mini Fast grok-3-mini-fast | Budget | $0.600 | $4.00 |
Grok 2 grok-2-1212 | Standard | $2.00 | $10.00 |
Grok 2 Vision grok-2-vision-1212 | Standard | $2.00 | $10.00 |
Grok 3 grok-3 | Premium | $3.00 | $15.00 |
Grok 3 Fast grok-3-fast | Standard | $5.00 | $25.00 |
groq(10 models)
| Model | Tier | Input / 1M tokens | Output / 1M tokens |
|---|---|---|---|
Llama 3.1 8B Instant llama-3.1-8b-instant | Budget | $0.050 | $0.080 |
Llama 3 8B llama3-8b-8192 | Budget | $0.050 | $0.080 |
Llama 4 Scout meta-llama/llama-4-scout-17b-16e-instruct | Standard | $0.110 | $0.340 |
Llama 3.2 11B Vision llama-3.2-11b-vision-preview | Budget | $0.180 | $0.180 |
Llama 4 Maverick meta-llama/llama-4-maverick-17b-128e-instruct | Premium | $0.200 | $0.600 |
Gemma 2 9B gemma2-9b-it | Budget | $0.200 | $0.200 |
Mixtral 8x7B mixtral-8x7b-32768 | Standard | $0.240 | $0.240 |
Llama 3.3 70B Versatile llama-3.3-70b-versatile | Standard | $0.590 | $0.790 |
Llama 3 70B llama3-70b-8192 | Standard | $0.590 | $0.790 |
Llama 3.2 90B Vision llama-3.2-90b-vision-preview | Premium | $0.900 | $0.900 |
cohere(8 models)
| Model | Tier | Input / 1M tokens | Output / 1M tokens |
|---|---|---|---|
Embed English v3 embed-english-v3.0 | Budget | $0.100 | $0 |
Embed Multilingual v3 embed-multilingual-v3.0 | Budget | $0.100 | $0 |
Command R command-r | Standard | $0.150 | $0.600 |
Command R (Aug 2024) command-r-08-2024 | Standard | $0.150 | $0.600 |
Command Light command-light | Budget | $0.300 | $0.600 |
Command command | Standard | $1.00 | $2.00 |
Command R+ command-r-plus | Premium | $2.50 | $10.00 |
Command R+ (Aug 2024) command-r-plus-08-2024 | Premium | $2.50 | $10.00 |
together(12 models)
| Model | Tier | Input / 1M tokens | Output / 1M tokens |
|---|---|---|---|
Llama 4 Scout 17B meta-llama/llama-4-scout-17b-16e-instruct | Standard | $0.180 | $0.590 |
Llama 3.1 8B Turbo meta-llama/meta-llama-3.1-8b-instruct-turbo | Budget | $0.180 | $0.180 |
Mistral 7B Instruct mistralai/mistral-7b-instruct-v0.3 | Budget | $0.200 | $0.200 |
Llama 4 Maverick 17B meta-llama/llama-4-maverick-17b-128e-instruct-fp8 | Standard | $0.270 | $0.850 |
Qwen 2.5 7B Turbo qwen/qwen2.5-7b-instruct-turbo | Budget | $0.300 | $0.300 |
Mixtral 8x7B Instruct mistralai/mixtral-8x7b-instruct-v0.1 | Standard | $0.540 | $0.540 |
Llama 3.3 70B Turbo meta-llama/llama-3.3-70b-instruct-turbo | Standard | $0.880 | $0.880 |
Llama 3.1 70B Turbo meta-llama/meta-llama-3.1-70b-instruct-turbo | Standard | $0.880 | $0.880 |
Qwen 2.5 72B Turbo qwen/qwen2.5-72b-instruct-turbo | Standard | $1.20 | $1.20 |
DeepSeek V3 deepseek-ai/deepseek-v3 | Standard | $1.25 | $1.25 |
Llama 3.1 405B Turbo meta-llama/meta-llama-3.1-405b-instruct-turbo | Premium | $3.50 | $3.50 |
DeepSeek R1 deepseek-ai/deepseek-r1 | Premium | $7.00 | $7.00 |
fireworks(13 models)
| Model | Tier | Input / 1M tokens | Output / 1M tokens |
|---|---|---|---|
Llama 4 Scout accounts/fireworks/models/llama4-scout-instruct-basic | Budget | $0.150 | $0.600 |
Llama 3.1 8B Instruct accounts/fireworks/models/llama-v3p1-8b-instruct | Budget | $0.200 | $0.200 |
Gemma 2 9B IT accounts/fireworks/models/gemma2-9b-it | Budget | $0.200 | $0.200 |
Llama 3 8B Instruct accounts/fireworks/models/llama-v3-8b-instruct | Budget | $0.200 | $0.200 |
Llama 4 Maverick accounts/fireworks/models/llama4-maverick-instruct-basic | Standard | $0.220 | $0.880 |
Mixtral 8x7B Instruct accounts/fireworks/models/mixtral-8x7b-instruct | Standard | $0.500 | $0.500 |
Llama 3.3 70B Instruct accounts/fireworks/models/llama-v3p3-70b-instruct | Standard | $0.900 | $0.900 |
Llama 3.1 70B Instruct accounts/fireworks/models/llama-v3p1-70b-instruct | Standard | $0.900 | $0.900 |
DeepSeek V3 accounts/fireworks/models/deepseek-v3 | Standard | $0.900 | $0.900 |
Qwen 2.5 72B Instruct accounts/fireworks/models/qwen2p5-72b-instruct | Standard | $0.900 | $0.900 |
Llama 3 70B Instruct accounts/fireworks/models/llama-v3-70b-instruct | Standard | $0.900 | $0.900 |
Llama 3.1 405B Instruct accounts/fireworks/models/llama-v3p1-405b-instruct | Premium | $3.00 | $3.00 |
DeepSeek R1 accounts/fireworks/models/deepseek-r1 | Premium | $8.00 | $8.00 |
perplexity(6 models)
| Model | Tier | Input / 1M tokens | Output / 1M tokens |
|---|---|---|---|
Sonar sonar | Budget | $1.00 | $1.00 |
Sonar Reasoning sonar-reasoning | Standard | $1.00 | $5.00 |
Sonar Reasoning Pro sonar-reasoning-pro | Premium | $2.00 | $8.00 |
Sonar Deep Research sonar-deep-research | Premium | $2.00 | $8.00 |
R1 1776 r1-1776 | Standard | $2.00 | $8.00 |
Sonar Pro sonar-pro | Premium | $3.00 | $15.00 |
cerebras(5 models)
| Model | Tier | Input / 1M tokens | Output / 1M tokens |
|---|---|---|---|
Llama 3.1 8B llama3.1-8b | Budget | $0.100 | $0.100 |
Qwen 3 32B qwen-3-32b | Standard | $0.400 | $0.400 |
Llama 3.1 70B llama3.1-70b | Standard | $0.600 | $0.600 |
DeepSeek R1 Distill Llama 70B deepseek-r1-distill-llama-70b | Standard | $0.600 | $0.600 |
Llama 3.3 70B llama-3.3-70b | Standard | $0.850 | $0.850 |
ai21(4 models)
| Model | Tier | Input / 1M tokens | Output / 1M tokens |
|---|---|---|---|
Jamba 1.5 Mini jamba-1.5-mini | Budget | $0.200 | $0.400 |
Jamba 1.6 Mini jamba-1.6-mini | Budget | $0.200 | $0.400 |
Jamba 1.5 Large jamba-1.5-large | Premium | $2.00 | $8.00 |
Jamba 1.6 Large jamba-1.6-large | Premium | $2.00 | $8.00 |
deepinfra(12 models)
| Model | Tier | Input / 1M tokens | Output / 1M tokens |
|---|---|---|---|
Llama 3.1 8B meta-llama/Meta-Llama-3.1-8B-Instruct | Budget | $0.030 | $0.050 |
Llama 4 Scout 17B meta-llama/Llama-4-Scout-17B-16E-Instruct | Budget | $0.070 | $0.110 |
Phi-4 microsoft/Phi-4 | Budget | $0.070 | $0.140 |
QwQ 32B Qwen/QwQ-32B | Standard | $0.120 | $0.180 |
Llama 3.1 Nemotron 70B nvidia/Llama-3.1-Nemotron-70B-Instruct | Standard | $0.120 | $0.300 |
Llama 4 Maverick 17B meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 | Standard | $0.180 | $0.540 |
Llama 3.3 70B meta-llama/Llama-3.3-70B-Instruct | Standard | $0.220 | $0.590 |
Mixtral 8x7B mistralai/Mixtral-8x7B-Instruct-v0.1 | Standard | $0.240 | $0.240 |
Llama 3.1 70B meta-llama/Meta-Llama-3.1-70B-Instruct | Standard | $0.350 | $0.390 |
Qwen 2.5 72B Qwen/Qwen2.5-72B-Instruct | Standard | $0.350 | $0.390 |
DeepSeek V3 deepseek-ai/DeepSeek-V3 | Standard | $0.420 | $0.850 |
DeepSeek R1 deepseek-ai/DeepSeek-R1 | Premium | $0.550 | $2.19 |
novita(10 models)
| Model | Tier | Input / 1M tokens | Output / 1M tokens |
|---|---|---|---|
Mistral 7B mistralai/mistral-7b-instruct-v0.3 | Budget | $0.030 | $0.030 |
Llama 3.1 8B meta-llama/llama-3.1-8b-instruct | Budget | $0.060 | $0.060 |
Qwen 2.5 7B Qwen/Qwen2.5-7B-Instruct | Budget | $0.070 | $0.070 |
QwQ 32B Qwen/QwQ-32B | Standard | $0.120 | $0.180 |
Gemma 2 27B google/gemma-2-27b-it | Standard | $0.200 | $0.200 |
Qwen 2.5 72B Qwen/Qwen2.5-72B-Instruct | Standard | $0.350 | $0.350 |
DeepSeek V3 deepseek/deepseek_v3_0324 | Standard | $0.380 | $0.380 |
Llama 3.1 70B meta-llama/llama-3.1-70b-instruct | Standard | $0.400 | $0.400 |
Llama 3.3 70B meta-llama/llama-3.3-70b-instruct | Standard | $0.400 | $0.400 |
DeepSeek R1 deepseek/deepseek_r1 | Premium | $0.550 | $2.19 |
hyperbolic(9 models)
| Model | Tier | Input / 1M tokens | Output / 1M tokens |
|---|---|---|---|
Llama 3.1 8B meta-llama/Meta-Llama-3.1-8B-Instruct | Budget | $0.080 | $0.080 |
Llama 4 Scout meta-llama/Llama-4-Scout-17B-16E-Instruct | Budget | $0.100 | $0.300 |
Mistral 7B mistralai/Mistral-7B-Instruct-v0.3 | Budget | $0.110 | $0.110 |
Llama 3.3 70B meta-llama/Meta-Llama-3.3-70B-Instruct | Standard | $0.400 | $0.400 |
Llama 3.1 70B meta-llama/Meta-Llama-3.1-70B-Instruct | Standard | $0.400 | $0.400 |
DeepSeek V3 deepseek-ai/DeepSeek-V3 | Standard | $0.400 | $0.400 |
Qwen 2.5 72B Qwen/Qwen2.5-72B-Instruct | Standard | $0.400 | $0.400 |
Llama 4 Maverick meta-llama/Llama-4-Maverick-17B-128E-Instruct | Standard | $0.500 | $1.50 |
DeepSeek R1 deepseek-ai/DeepSeek-R1 | Premium | $0.500 | $2.18 |
sambanova(10 models)
| Model | Tier | Input / 1M tokens | Output / 1M tokens |
|---|---|---|---|
Llama 3.2 1B Meta-Llama-3.2-1B-Instruct | Budget | $0.040 | $0.040 |
Llama 3.2 3B Meta-Llama-3.2-3B-Instruct | Budget | $0.080 | $0.080 |
Llama 3.1 8B Meta-Llama-3.1-8B-Instruct | Budget | $0.100 | $0.100 |
Qwen 2.5 Coder 32B Qwen2.5-Coder-32B-Instruct | Standard | $0.400 | $0.800 |
Llama 3.1 70B Meta-Llama-3.1-70B-Instruct | Standard | $0.600 | $1.20 |
Llama 3.3 70B Meta-Llama-3.3-70B-Instruct | Standard | $0.600 | $1.20 |
Qwen 2.5 72B Qwen2.5-72B-Instruct | Standard | $0.600 | $1.20 |
DeepSeek V3 DeepSeek-V3-0324 | Standard | $0.700 | $1.40 |
Llama 3.1 405B Meta-Llama-3.1-405B-Instruct | Premium | $2.00 | $2.00 |
DeepSeek R1 DeepSeek-R1 | Premium | $3.00 | $10.00 |
lambdalabs(9 models)
| Model | Tier | Input / 1M tokens | Output / 1M tokens |
|---|---|---|---|
Llama 3.1 8B meta-llama/Llama-3.1-8B-Instruct | Budget | $0.018 | $0.018 |
Hermes 3 8B hermes3-8b | Budget | $0.018 | $0.018 |
Qwen 2.5 Coder 32B Qwen/Qwen2.5-Coder-32B-Instruct | Standard | $0.040 | $0.040 |
Liquid LFM 40B MoE lfm-40b | Standard | $0.040 | $0.040 |
Llama 3.3 70B meta-llama/Llama-3.3-70B-Instruct-FP8 | Standard | $0.060 | $0.090 |
Llama 3.1 70B meta-llama/Llama-3.1-70B-Instruct-FP8 | Standard | $0.060 | $0.090 |
Hermes 3 70B hermes3-70b | Standard | $0.060 | $0.090 |
Llama 3.1 405B meta-llama/Llama-3.1-405B-Instruct-FP8 | Premium | $0.530 | $0.530 |
Hermes 3 405B hermes3-405b | Premium | $0.530 | $0.530 |
inferencenet(10 models)
| Model | Tier | Input / 1M tokens | Output / 1M tokens |
|---|---|---|---|
Llama 3.1 8B meta-llama/llama-3.1-8b-instruct/fp-8 | Budget | $0.040 | $0.040 |
Mistral 7B mistralai/mistral-7b-instruct/fp-8 | Budget | $0.040 | $0.040 |
Gemma 2 9B google/gemma-2-9b-it/fp-8 | Budget | $0.050 | $0.050 |
Phi 4 microsoft/phi-4/fp-8 | Budget | $0.080 | $0.080 |
Mixtral 8x7B mistralai/mixtral-8x7b-instruct/fp-8 | Standard | $0.120 | $0.120 |
Llama 3.3 70B meta-llama/llama-3.3-70b-instruct/fp-8 | Standard | $0.200 | $0.200 |
Llama 3.1 70B meta-llama/llama-3.1-70b-instruct/fp-8 | Standard | $0.200 | $0.200 |
Qwen 2.5 72B qwen/qwen2.5-72b-instruct/fp-8 | Standard | $0.200 | $0.200 |
DeepSeek V3 deepseek/deepseek-v3/fp-8 | Standard | $0.250 | $0.250 |
DeepSeek R1 deepseek/deepseek-r1/fp-8 | Premium | $0.800 | $0.800 |
lepton(8 models)
| Model | Tier | Input / 1M tokens | Output / 1M tokens |
|---|---|---|---|
Llama 3 8B llama3-8b | Budget | $0.060 | $0.060 |
Mistral 7B mistral-7b | Budget | $0.060 | $0.060 |
Llama 3.1 8B llama3-1-8b | Budget | $0.070 | $0.070 |
Mixtral 8x7B mixtral-8x7b | Standard | $0.300 | $0.300 |
Qwen 2.5 72B qwen2-5-72b | Standard | $0.600 | $0.600 |
Llama 3 70B llama3-70b | Standard | $0.700 | $0.700 |
Llama 3.1 70B llama3-1-70b | Standard | $0.800 | $0.800 |
Llama 3.1 405B llama3-1-405b | Premium | $2.80 | $2.80 |
nvidia(10 models)
| Model | Tier | Input / 1M tokens | Output / 1M tokens |
|---|---|---|---|
Llama 3.1 8B Instruct meta/llama-3.1-8b-instruct | Budget | $0.050 | $0.050 |
Mistral 7B Instruct mistralai/mistral-7b-instruct-v0.3 | Budget | $0.080 | $0.080 |
Gemma 2 9B IT google/gemma-2-9b-it | Budget | $0.090 | $0.090 |
Llama 3.3 70B Instruct meta/llama-3.3-70b-instruct | Standard | $0.230 | $0.230 |
Phi 3 Medium 128K microsoft/phi-3-medium-128k-instruct | Budget | $0.250 | $0.250 |
Mixtral 8x7B Instruct mistralai/mixtral-8x7b-instruct-v0.1 | Standard | $0.300 | $0.300 |
Llama 3.1 70B Instruct meta/llama-3.1-70b-instruct | Standard | $0.350 | $0.400 |
DeepSeek R1 deepseek-ai/deepseek-r1 | Standard | $0.800 | $2.40 |
Llama 3.1 405B Instruct meta/llama-3.1-405b-instruct | Premium | $2.99 | $2.99 |
Nemotron 4 340B Instruct nvidia/nemotron-4-340b-instruct | Premium | $4.20 | $4.20 |
cloudflare(10 models)
| Model | Tier | Input / 1M tokens | Output / 1M tokens |
|---|---|---|---|
Llama 3.2 1B Instruct @cf/meta/llama-3.2-1b-instruct | Budget | $0.060 | $0.060 |
Llama 3.2 3B Instruct @cf/meta/llama-3.2-3b-instruct | Budget | $0.080 | $0.080 |
Gemma 2B IT @cf/google/gemma-2b-it | Budget | $0.080 | $0.080 |
Phi-2 @cf/microsoft/phi-2 | Budget | $0.080 | $0.080 |
Llama 3.1 8B Instruct (Fast) @cf/meta/llama-3.1-8b-instruct-fast | Budget | $0.100 | $0.100 |
Mistral 7B Instruct v0.1 @cf/mistral/mistral-7b-instruct-v0.1 | Budget | $0.110 | $0.110 |
Gemma 7B IT @cf/google/gemma-7b-it | Budget | $0.110 | $0.110 |
Llama 3.2 11B Vision Instruct @cf/meta/llama-3.2-11b-vision-instruct | Standard | $0.140 | $0.140 |
Qwen 1.5 14B Chat (AWQ) @cf/qwen/qwen1.5-14b-chat-awq | Standard | $0.180 | $0.180 |
Llama 3.3 70B Instruct (Fast) @cf/meta/llama-3.3-70b-instruct-fp8-fast | Standard | $0.560 | $0.560 |
nebius(10 models)
| Model | Tier | Input / 1M tokens | Output / 1M tokens |
|---|---|---|---|
Mistral Nemo mistralai/Mistral-Nemo-Instruct-2407 | Budget | $0.040 | $0.040 |
Phi-3 Mini (128k) microsoft/Phi-3-mini-128k-instruct | Budget | $0.040 | $0.040 |
Gemma 2 9B google/gemma-2-9b-it | Budget | $0.040 | $0.040 |
Llama 3.1 8B Instruct meta-llama/Llama-3.1-8B-Instruct | Budget | $0.060 | $0.060 |
Qwen 2.5 7B Instruct Qwen/Qwen2.5-7B-Instruct | Budget | $0.060 | $0.060 |
Llama 3.3 70B Instruct meta-llama/Llama-3.3-70B-Instruct | Standard | $0.130 | $0.400 |
Llama 3.1 70B Instruct meta-llama/Llama-3.1-70B-Instruct | Standard | $0.130 | $0.400 |
Qwen 2.5 72B Instruct Qwen/Qwen2.5-72B-Instruct | Standard | $0.130 | $0.400 |
DeepSeek V3 deepseek-ai/DeepSeek-V3 | Standard | $0.280 | $1.10 |
DeepSeek R1 deepseek-ai/DeepSeek-R1 | Premium | $0.550 | $2.19 |
replicate(10 models)
| Model | Tier | Input / 1M tokens | Output / 1M tokens |
|---|---|---|---|
Llama 3.1 8B meta/llama-3.1-8b-instruct | Budget | $0.050 | $0.050 |
Llama 3.2 11B Vision meta/llama-3.2-11b-vision-instruct | Budget | $0.055 | $0.055 |
Gemma 2 9B google-deepmind/gemma-2-9b-it | Budget | $0.060 | $0.060 |
DeepSeek V3 deepseek-ai/deepseek-v3 | Standard | $0.270 | $1.10 |
Mixtral 8x7B mistralai/mixtral-8x7b-instruct-v0.1 | Standard | $0.300 | $0.300 |
Qwen 2.5 72B qwen/qwen2.5-72b-instruct | Standard | $0.350 | $0.400 |
Llama 3.1 70B meta/llama-3.1-70b-instruct | Standard | $0.650 | $0.650 |
Llama 3.3 70B meta/llama-3.3-70b-instruct | Standard | $0.900 | $0.900 |
DeepSeek R1 deepseek-ai/deepseek-r1 | Premium | $3.00 | $8.00 |
Llama 3.1 405B meta/llama-3.1-405b-instruct | Premium | $9.50 | $9.50 |