Models

Every model.
One key.

107 models routed through Plurence. Subscriptions cover all of them under a single monthly cap — no per-model contracts.

Rates below show the per-million-token list price. See Pricing for plan details.

Bedrock

47 models

amazon.nova-pro-v1:0 text image video frontier

Amazon Nova Pro V1 - professional model for complex tasks with long context.

Input

$0.480 /1M

Output

$3.84 /1M

expand_more

Context: 500,000 tokens

All rates

1M_cache_read_input_tokens flex $0.120 /1M

1M_cache_write_input_tokens flex $0.000 /1M

Input flex $0.480 /1M

Output flex $1.92 /1M

1M_cache_read_input_tokens priority $0.420 /1M

1M_cache_write_input_tokens priority $0.000 /1M

Input priority $1.68 /1M

Output priority $6.72 /1M

1M_cache_read_input_tokens $0.240 /1M

1M_cache_write_input_tokens $0.000 /1M

Input $0.480 /1M

Input $0.960 /1M

Input $1.20 /1M

Output $3.84 /1M

Output $4.80 /1M

Output $3.84 /1M

Output $1.92 /1M

amazon.nova-sonic-v1:0 text image frontier

Amazon Nova Sonic V1 - ultra-low latency model for real-time applications.

Input

$0.400 /1M

Output

$3.30 /1M

expand_more

Context: 200,000 tokens

All rates

Input $0.400 /1M

Input $3.60 /1M

Input $0.070 /1M

Input $4.08 /1M

Output $3.30 /1M

Output $0.290 /1M

Output $14.4 /1M

Output $16.3 /1M

mistral.pixtral-large-2502-v1:0 text image frontier

Mistral AI Pixtral Large (25.02)

Input

$2.40 /1M

Output

$7.20 /1M

expand_more

All rates

Input $2.40 /1M

Output $7.20 /1M

moonshotai.kimi-k2.5 text image frontier

Moonshot AI Kimi K2.5

Input

$0.720 /1M

Output

$3.60 /1M

expand_more

All rates

Input batch $0.360 /1M

Output batch $1.80 /1M

Input flex $0.360 /1M

Output flex $1.80 /1M

Input priority $1.26 /1M

Output priority $6.30 /1M

Input $0.720 /1M

Output $3.60 /1M

deepseek.r1-v1:0 text frontier

DeepSeek DeepSeek-R1

Input

$1.62 /1M

Output

$6.48 /1M

expand_more

All rates

Input $1.62 /1M

Output $6.48 /1M

zai.glm-5 text frontier

Z.AI GLM 5

Input

$1.20 /1M

Output

$3.84 /1M

expand_more

All rates

Input batch $0.600 /1M

Output batch $1.92 /1M

Input flex $0.600 /1M

Output flex $1.92 /1M

Input priority $2.10 /1M

Output priority $6.72 /1M

Input $1.20 /1M

Output $3.84 /1M

amazon.nova-lite-v1:0 text image video

Amazon Nova Lite

Input

$0.070 /1M

Output

$0.290 /1M

expand_more

All rates

1M_cache_read_input_tokens $0.020 /1M

1M_cache_write_input_tokens $0.000 /1M

Input $0.070 /1M

Input $0.040 /1M

Input $0.070 /1M

Output $0.290 /1M

Output $0.140 /1M

amazon.nova-micro-v1:0 text image

Amazon Nova Micro V1 - compact model for fast inference and cost efficiency.

Input

$0.040 /1M

Output

$0.170 /1M

expand_more

Context: 200,000 tokens

All rates

1M_cache_read_input_tokens $0.010 /1M

1M_cache_write_input_tokens $0.000 /1M

Input $0.040 /1M

Input $0.020 /1M

Output $0.170 /1M

Output $0.080 /1M

Output $0.170 /1M

amazon.titan-image-generator-v2:0 text image

Amazon Titan Image Generator V2 - advanced text-to-image generation.

Input

— /1M

Output

— /1M

expand_more

All rates

image_custom_i2i_1024 priority $0.020 /1M

image_custom_i2i_512 priority $0.020 /1M

image_custom_t2i_1024 priority $0.020 /1M

image_custom_t2i_512 priority $0.020 /1M

image_i2i_1024 priority $0.010 /1M

image_i2i_512 priority $0.010 /1M

image_t2i_1024 priority $0.010 /1M

image_t2i_512 priority $0.010 /1M

image_custom_i2i_1024 $0.020 /1M

image_custom_i2i_512 $0.020 /1M

image_custom_t2i_1024 $0.020 /1M

image_custom_t2i_512 $0.020 /1M

image_i2i_1024 $0.010 /1M

image_i2i_512 $0.010 /1M

image_t2i_1024 $0.010 /1M

image_t2i_512 $0.010 /1M

anthropic.claude-3-haiku-20240307-v1:0 text image

Anthropic Claude 3 Haiku

Input

$0.300 /1M

Output

— /1M

expand_more

All rates

Input $0.300 /1M

anthropic.claude-3-sonnet-20240229-v1:0 text image

Anthropic Claude 3 Sonnet

Input

$3.60 /1M

Output

— /1M

expand_more

All rates

Input $3.60 /1M

cohere.embed-v4:0 text image

Cohere Embed v4

Input

$0.960 /1M

Output

— /1M

expand_more

All rates

Image input $0.000 /1M

Input $0.960 /1M

Input $0.020 /1M

Input $0.010 /1M

Input $0.120 /1M

Input $0.480 /1M

google.gemma-3-12b-it text image

Google Gemma 3 12B IT

Input

$0.110 /1M

Output

$0.180 /1M

expand_more

All rates

Input batch $0.060 /1M

Output batch $0.180 /1M

Input flex $0.060 /1M

Output flex $0.180 /1M

Input priority $0.190 /1M

Output priority $0.610 /1M

Input $0.110 /1M

Input $0.060 /1M

Input $0.110 /1M

Output $0.180 /1M

Output $0.350 /1M

google.gemma-3-27b-it text image

Google Gemma 3 27B PT

Input

$0.280 /1M

Output

$0.460 /1M

expand_more

All rates

Input batch $0.140 /1M

Output batch $0.230 /1M

Input flex $0.140 /1M

Output flex $0.230 /1M

Input priority $0.480 /1M

Output priority $0.800 /1M

Input $0.280 /1M

Input $0.140 /1M

Output $0.460 /1M

Output $0.230 /1M

Output $0.460 /1M

google.gemma-3-4b-it text image

Google Gemma 3 4B IT

Input

$0.050 /1M

Output

$0.100 /1M

expand_more

All rates

Input batch $0.020 /1M

Output batch $0.050 /1M

Input flex $0.020 /1M

Output flex $0.050 /1M

Input priority $0.080 /1M

Output priority $0.170 /1M

Input $0.050 /1M

Input $0.020 /1M

Input $0.050 /1M

Output $0.100 /1M

Output $0.050 /1M

Output $0.100 /1M

meta.llama4-maverick-17b-instruct-v1:0 text image

Meta Llama 4 Maverick 17B Instruct

Input

$0.140 /1M

Output

$0.590 /1M

expand_more

All rates

Input $0.140 /1M

Input $0.290 /1M

Output $0.590 /1M

Output $1.16 /1M

meta.llama4-scout-17b-instruct-v1:0 text image

Meta Llama 4 Scout 17B Instruct

Input

$0.200 /1M

Output

$0.790 /1M

expand_more

All rates

Input $0.200 /1M

Input $0.110 /1M

Output $0.790 /1M

Output $0.400 /1M

mistral.mistral-large-3-675b-instruct text image

Mistral AI Mistral Large 3

Input

$0.600 /1M

Output

$1.80 /1M

expand_more

All rates

Input batch $0.300 /1M

Output batch $0.900 /1M

Input flex $0.300 /1M

Output flex $0.900 /1M

Input priority $1.06 /1M

Output priority $3.16 /1M

Input $0.600 /1M

Input $0.300 /1M

Output $1.80 /1M

Output $0.900 /1M

Output $1.80 /1M

qwen.qwen3-vl-235b-a22b text image

Qwen Qwen3 VL 235B A22B

Input

$0.640 /1M

Output

$3.19 /1M

expand_more

All rates

Input batch $0.310 /1M

Output batch $1.60 /1M

Input flex $0.310 /1M

Output flex $1.60 /1M

Input priority $1.12 /1M

Output priority $5.59 /1M

Input $0.640 /1M

Input $0.310 /1M

Output $3.19 /1M

Output $1.60 /1M

writer.palmyra-vision-7b text image

Writer Writer Palmyra Vision 7B

Input

$0.180 /1M

Output

$0.720 /1M

expand_more

All rates

Input batch $0.100 /1M

Output batch $0.360 /1M

Input flex $0.100 /1M

Output flex $0.360 /1M

Input priority $0.310 /1M

Output priority $1.26 /1M

Input $0.180 /1M

Output $0.720 /1M

deepseek.v3.2 text

DeepSeek DeepSeek V3.2

Input

$0.740 /1M

Output

$2.22 /1M

expand_more

All rates

Input batch $0.370 /1M

Output batch $1.12 /1M

Input flex $0.370 /1M

Output flex $1.12 /1M

Input priority $1.31 /1M

Output priority $3.89 /1M

Input $0.740 /1M

Output $2.22 /1M

meta.llama3-1-70b-instruct-v1:0 text

Meta Llama 3.1 70B Instruct

Input

$0.860 /1M

Output

$0.430 /1M

expand_more

All rates

Input $0.860 /1M

Input $0.430 /1M

Output $0.430 /1M

Output $0.860 /1M

meta.llama3-1-8b-instruct-v1:0 text

Meta Llama 3.1 8B Instruct

Input

$0.260 /1M

Output

$0.130 /1M

expand_more

All rates

Input $0.260 /1M

Input $0.130 /1M

Output $0.130 /1M

Output $0.260 /1M

meta.llama3-3-70b-instruct-v1:0 text

Meta Llama 3.3 70B Instruct

Input

$0.430 /1M

Output

$0.430 /1M

expand_more

All rates

Input $0.430 /1M

Input $0.860 /1M

Output $0.430 /1M

Output $0.860 /1M

meta.llama3-70b-instruct-v1:0 text

Meta Llama 3 70B Instruct

Input

$3.18 /1M

Output

$4.20 /1M

expand_more

All rates

Input $3.18 /1M

Output $4.20 /1M

meta.llama3-8b-instruct-v1:0 text

Meta Llama 3 8B Instruct

Input

$0.360 /1M

Output

$0.720 /1M

expand_more

All rates

Input $0.360 /1M

Output $0.720 /1M

minimax.minimax-m2 text

MiniMax MiniMax M2

Input

$0.360 /1M

Output

$0.720 /1M

expand_more

All rates

Input batch $0.180 /1M

Output batch $0.720 /1M

Input flex $0.180 /1M

Output flex $0.720 /1M

Input priority $0.620 /1M

Output priority $2.52 /1M

Input $0.360 /1M

Input $0.180 /1M

Output $0.720 /1M

Output $1.44 /1M

minimax.minimax-m2.1 text

MiniMax MiniMax M2.1

Input

$0.360 /1M

Output

$1.44 /1M

expand_more

All rates

Input batch $0.180 /1M

Output batch $0.720 /1M

Input flex $0.180 /1M

Output flex $0.720 /1M

Input priority $0.640 /1M

Output priority $2.52 /1M

Input $0.360 /1M

Output $1.44 /1M

minimax.minimax-m2.5 text

MiniMax MiniMax M2.5

Input

$0.360 /1M

Output

$1.44 /1M

expand_more

All rates

Input batch $0.180 /1M

Output batch $0.720 /1M

Input flex $0.180 /1M

Output flex $0.720 /1M

Input priority $0.640 /1M

Output priority $2.52 /1M

Input $0.360 /1M

Output $1.44 /1M

mistral.devstral-2-123b text

Mistral AI Devstral 2 123B

Input

$0.480 /1M

Output

$2.40 /1M

expand_more

All rates

Input batch $0.240 /1M

Output batch $1.20 /1M

Input flex $0.240 /1M

Output flex $1.20 /1M

Input priority $0.840 /1M

Output priority $4.20 /1M

Input $0.480 /1M

Output $2.40 /1M

mistral.mistral-7b-instruct-v0:2 text

Mistral AI Mistral 7B Instruct

Input

$0.180 /1M

Output

$0.240 /1M

expand_more

All rates

Input $0.180 /1M

Output $0.240 /1M

mistral.mistral-small-2402-v1:0 text

Mistral AI Mistral Small (24.02)

Input

$0.600 /1M

Output

$1.80 /1M

expand_more

All rates

Input $0.600 /1M

Input $1.20 /1M

Output $1.80 /1M

Output $3.60 /1M

mistral.mixtral-8x7b-instruct-v0:1 text

Mistral AI Mixtral 8x7B Instruct

Input

$0.540 /1M

Output

$0.840 /1M

expand_more

All rates

Input $0.540 /1M

Output $0.840 /1M

moonshot.kimi-k2-thinking text

Moonshot AI Kimi K2 Thinking

Input

$0.360 /1M

Output

$3.00 /1M

expand_more

All rates

Input batch $0.360 /1M

Output batch $1.50 /1M

Input flex $0.360 /1M

Output flex $1.50 /1M

Input priority $1.26 /1M

Output priority $5.26 /1M

Input $0.360 /1M

Input $0.720 /1M

Output $3.00 /1M

Output $1.50 /1M

Output $3.00 /1M

nvidia.nemotron-nano-3-30b text

NVIDIA Nemotron Nano 3 30B

Input

$0.070 /1M

Output

$0.290 /1M

expand_more

All rates

Input batch $0.040 /1M

Output batch $0.140 /1M

Input flex $0.040 /1M

Output flex $0.140 /1M

Input priority $0.130 /1M

Output priority $0.500 /1M

Input $0.070 /1M

Input $0.040 /1M

Input $0.070 /1M

Output $0.290 /1M

Output $0.140 /1M

openai.gpt-oss-120b-1:0 text

OpenAI GPT-OSS 120B - large open source model with 120 billion parameters.

Input

$0.180 /1M

Output

$0.360 /1M

expand_more

Context: 256,000 tokens

All rates

Input batch $0.100 /1M

Output batch $0.360 /1M

Input flex $0.100 /1M

Output flex $0.360 /1M

Input priority $0.310 /1M

Output priority $1.26 /1M

Input $0.180 /1M

Input $0.100 /1M

Input $0.180 /1M

Output $0.360 /1M

Output $0.720 /1M

openai.gpt-oss-20b-1:0 text

OpenAI GPT-OSS 20B - open source model with 20 billion parameters.

Input

$0.080 /1M

Output

$0.360 /1M

expand_more

Context: 128,000 tokens

All rates

Input batch $0.040 /1M

Output batch $0.180 /1M

Input flex $0.040 /1M

Output flex $0.180 /1M

Input priority $0.140 /1M

Output priority $0.640 /1M

Input $0.080 /1M

Input $0.040 /1M

Input $0.080 /1M

Output $0.360 /1M

Output $0.180 /1M

Output $0.360 /1M

openai.gpt-oss-safeguard-120b text

OpenAI GPT OSS Safeguard 120B

Input

$0.080 /1M

Output

$0.360 /1M

expand_more

All rates

Input batch $0.080 /1M

Output batch $0.360 /1M

Input flex $0.080 /1M

Output flex $0.360 /1M

Input priority $0.310 /1M

Output priority $1.26 /1M

Input $0.080 /1M

Input $0.180 /1M

Output $0.360 /1M

Output $0.720 /1M

openai.gpt-oss-safeguard-20b text

OpenAI GPT OSS Safeguard 20B

Input

$0.080 /1M

Output

$0.240 /1M

expand_more

All rates

Input batch $0.040 /1M

Output batch $0.120 /1M

Input flex $0.040 /1M

Output flex $0.120 /1M

Input priority $0.140 /1M

Output priority $0.420 /1M

Input $0.080 /1M

Input $0.040 /1M

Input $0.080 /1M

Output $0.240 /1M

Output $0.120 /1M

qwen.qwen3-235b-a22b-2507-v1:0 text

Qwen Qwen3 235B A22B 2507

Input

$0.260 /1M

Output

$1.06 /1M

expand_more

All rates

Input batch $0.130 /1M

Output batch $0.530 /1M

Input flex $0.130 /1M

Output flex $0.530 /1M

Input priority $0.460 /1M

Output priority $1.85 /1M

Input $0.260 /1M

Output $1.06 /1M

qwen.qwen3-32b-v1:0 text

Qwen Qwen3 32B (dense)

Input

$0.180 /1M

Output

$0.720 /1M

expand_more

All rates

Input batch $0.100 /1M

Output batch $0.360 /1M

Input flex $0.100 /1M

Output flex $0.360 /1M

Input priority $0.310 /1M

Output priority $1.26 /1M

Input $0.180 /1M

Input $0.100 /1M

Input $0.180 /1M

Output $0.720 /1M

Output $0.360 /1M

qwen.qwen3-coder-30b-a3b-v1:0 text

Qwen Qwen3-Coder-30B-A3B-Instruct

Input

$0.100 /1M

Output

$0.720 /1M

expand_more

All rates

Input batch $0.100 /1M

Output batch $0.360 /1M

Input flex $0.100 /1M

Output flex $0.360 /1M

Input priority $0.310 /1M

Output priority $1.26 /1M

Input $0.100 /1M

Input $0.180 /1M

Output $0.720 /1M

Output $0.360 /1M

Output $0.720 /1M

qwen.qwen3-coder-480b-a35b-v1:0 text

Qwen Qwen3 Coder 480B A35B Instruct

Input

$0.540 /1M

Output

$2.16 /1M

expand_more

All rates

Input batch $0.280 /1M

Output batch $1.08 /1M

Input flex $0.280 /1M

Output flex $1.08 /1M

Input priority $0.950 /1M

Output priority $3.78 /1M

Input $0.540 /1M

Output $2.16 /1M

qwen.qwen3-coder-next text

Qwen Qwen3 Coder Next

Input

$0.600 /1M

Output

$1.44 /1M

expand_more

All rates

Input batch $0.300 /1M

Output batch $0.720 /1M

Input flex $0.300 /1M

Output flex $0.720 /1M

Input priority $1.06 /1M

Output priority $2.52 /1M

Input $0.600 /1M

Output $1.44 /1M

qwen.qwen3-next-80b-a3b text

Qwen Qwen3 Next 80B A3B

Input

$0.170 /1M

Output

$1.44 /1M

expand_more

All rates

Input batch $0.080 /1M

Output batch $0.720 /1M

Input flex $0.080 /1M

Output flex $0.720 /1M

Input priority $0.310 /1M

Output priority $2.52 /1M

Input $0.170 /1M

Output $1.44 /1M

zai.glm-4.7 text

Z.AI GLM 4.7

Input

$0.720 /1M

Output

$2.64 /1M

expand_more

All rates

Input batch $0.360 /1M

Output batch $1.32 /1M

Input flex $0.360 /1M

Output flex $1.32 /1M

Input priority $1.26 /1M

Output priority $4.62 /1M

Input $0.720 /1M

Output $2.64 /1M

zai.glm-4.7-flash text

Z.AI GLM 4.7 Flash

Input

$0.080 /1M

Output

$0.480 /1M

expand_more

All rates

Input batch $0.040 /1M

Output batch $0.240 /1M

Input flex $0.040 /1M

Output flex $0.240 /1M

Input priority $0.140 /1M

Output priority $0.840 /1M

Input $0.080 /1M

Output $0.480 /1M

OpenAI

41 models

gpt-4o text image audio frontier

OpenAI GPT-4o - Omni model with native multimodal capabilities.

Input

$3.00 /1M

Output

$12.0 /1M

expand_more

Context: 128,000 tokens

All rates

1M_cached_input_tokens short $1.50 /1M

Input short $3.00 /1M

Output short $12.0 /1M

gpt-realtime text image audio frontier

OpenAI GPT Realtime model - for real-time audio and voice applications.

Input

$4.80 /1M

Output

$0.040 /1M

expand_more

Context: 128,000 tokens

All rates

Output $0.040 /1M

1M_cached_input_tokens short $0.480 /1M

Input short $4.80 /1M

Output short $19.2 /1M

gpt-realtime-1.5 text image audio frontier

GPT-Reatime-1.5 is our flagship audio model for voice agents & customer support.

Input

$38.4 /1M

Output

$76.8 /1M

expand_more

Context: 32,000 tokens

All rates

1M_cached_input_tokens $0.480 /1M

Input $38.4 /1M

Output $76.8 /1M

1M_cached_input_tokens short $0.480 /1M

Input short $4.80 /1M

Output short $19.2 /1M

gpt-realtime-2 text image audio frontier

GPT Realtime 2 is our most capable realtime voice model. It supports speech-to-speech interactions with configurable reasoning effort, stronger instruction following, and more reliable tool use for complex voice-agent workflows.

Input

$38.4 /1M

Output

$76.8 /1M

expand_more

Context: 128,000 tokens

All rates

1M_cached_input_tokens $0.480 /1M

Input $38.4 /1M

Output $76.8 /1M

1M_cached_input_tokens short $0.480 /1M

Input short $4.80 /1M

Output short $28.8 /1M

gpt-realtime-mini text image audio frontier

OpenAI GPT Realtime Mini - compact model for real-time audio applications.

Input

$12.0 /1M

Output

$24.0 /1M

expand_more

Context: 65,000 tokens

All rates

1M_cached_input_tokens $0.360 /1M

Input $12.0 /1M

Output $24.0 /1M

1M_cached_input_tokens short $0.070 /1M

Input short $0.720 /1M

Output short $2.88 /1M

gpt-4o-mini-transcribe text audio frontier

OpenAI GPT-4o Mini Transcribe - efficient speech-to-text model.

Input

$1.50 /1M

Output

$6.00 /1M

expand_more

Context: 200,000 tokens

All rates

Audio input short $1.50 /1M

Audio output short $6.00 /1M

Input $1.50 /1M

Output $6.00 /1M

gpt-4o-mini-tts text audio frontier

OpenAI GPT-4o Mini TTS - text-to-speech voice generation.

Input

$0.720 /1M

Output

$14.4 /1M

expand_more

Context: 200,000 tokens

All rates

Input short $0.720 /1M

Output short $14.4 /1M

gpt-4o-realtime-preview text audio frontier

This is a preview release of the GPT-4o Realtime model, capable of responding to audio and text inputs in realtime over WebRTC or a WebSocket interface.

Input

$6.00 /1M

Output

$24.0 /1M

expand_more

Context: 32,000 tokens

All rates

1M_cached_input_tokens short $3.00 /1M

Input short $6.00 /1M

Output short $24.0 /1M

gpt-4o-transcribe text audio frontier

OpenAI GPT-4o Transcribe - speech-to-text transcription model.

Input

$3.00 /1M

Output

$12.0 /1M

expand_more

Context: 200,000 tokens

All rates

Audio input short $3.00 /1M

Audio output short $12.0 /1M

Input $3.00 /1M

Output $12.0 /1M

gpt-audio text audio frontier

OpenAI GPT Audio model - specialized for speech understanding and audio processing.

Input

$3.00 /1M

Output

$12.0 /1M

expand_more

Context: 65,000 tokens

All rates

Input short $3.00 /1M

Output short $12.0 /1M

gpt-audio-1.5 text audio frontier

The gpt-audio model is our first generally available audio model. It accepts audio inputs and outputs, and can be used in the Chat Completions REST API.

Input

$3.00 /1M

Output

$12.0 /1M

expand_more

Context: 128,000 tokens

All rates

Input short $3.00 /1M

Output short $12.0 /1M

chat-latest text image frontier

chat-latest points to the latest Instant model currently used in ChatGPT. We recommend leveraging GPT-5.5 for production API usage. Learn more in our latest model guide. The underlying model snapshot will be regularly updated.

Input

$6.00 /1M

Output

$36.0 /1M

expand_more

Context: 400,000 tokens

All rates

1M_cached_input_tokens $0.600 /1M

1M_cached_input_tokens short $0.600 /1M

Input $6.00 /1M

Input short $6.00 /1M

Output $36.0 /1M

Output short $36.0 /1M

chatgpt-image-latest text image frontier

ChatGPT Image Latest - current image generation model for ChatGPT integration.

Input

$6.00 /1M

Output

$12.0 /1M

expand_more

All rates

1M_cached_input_tokens short $1.50 /1M

Input short $6.00 /1M

Output short $12.0 /1M

gpt-4.1 text image frontier

OpenAI GPT-4.1 - improved model with enhanced reasoning and coding capabilities.

Input

$2.40 /1M

Output

$9.60 /1M

expand_more

Context: 256,000 tokens

All rates

1M_cached_input_tokens short $0.600 /1M

Input short $2.40 /1M

Output short $9.60 /1M

gpt-4.5-preview text image frontier

Deprecated - a research preview of GPT-4.5. We recommend using gpt-4.1 or o3 models instead for most use cases

Input

$90.0 /1M

Output

$180 /1M

expand_more

Context: 128,000 tokens

All rates

1M_cached_input_tokens short $45.0 /1M

Input short $90.0 /1M

Output short $180 /1M

gpt-5 text image frontier

OpenAI GPT-5 base model - next generation for professional work.

Input

$1.50 /1M

Output

$12.0 /1M

expand_more

Context: 256,000 tokens

All rates

1M_cached_input_tokens short $0.160 /1M

Input short $1.50 /1M

Output short $12.0 /1M

gpt-5-pro text image frontier

GPT-5 pro uses more compute to think harder and provide consistently better answers.

Input

$18.0 /1M

Output

$144 /1M

expand_more

Context: 400,000 tokens

All rates

Input short $18.0 /1M

Output short $144 /1M

gpt-5.1 text image frontier

GPT-5.1 is our flagship model for coding and agentic tasks with configurable reasoning and non-reasoning effort. Learn more in our latest model guide. Reasoning.effort supports: none (default), low, medium, and high.

Input

$1.50 /1M

Output

$12.0 /1M

expand_more

Context: 400,000 tokens

All rates

1M_cached_input_tokens short $0.160 /1M

Input short $1.50 /1M

Output short $12.0 /1M

gpt-5.2 text image frontier

OpenAI GPT-5.2 - optimized variant with improved efficiency.

Input

$2.10 /1M

Output

$16.8 /1M

expand_more

Context: 256,000 tokens

All rates

1M_cached_input_tokens short $0.220 /1M

Input short $2.10 /1M

Output short $16.8 /1M

gpt-5.2-chat-latest text image frontier

GPT-5.2 Chat points to the GPT-5.2 snapshot used in ChatGPT. This model has been deprecated. We recommend GPT-5.5 for most API usage.

Input

$2.10 /1M

Output

$16.8 /1M

expand_more

Context: 128,000 tokens

All rates

1M_cached_input_tokens short $0.220 /1M

Input short $2.10 /1M

Output short $16.8 /1M

gpt-5.2-pro text image frontier

OpenAI GPT-5.2 Pro - enhanced professional variant with extended capabilities.

Input

$25.2 /1M

Output

$202 /1M

expand_more

Context: 256,000 tokens

All rates

Input short $25.2 /1M

Output short $202 /1M

gpt-5.3-chat-latest text image frontier

GPT-5.3 Chat points to the GPT-5.3 Instant snapshot currently used in ChatGPT.

Input

$2.10 /1M

Output

$16.8 /1M

expand_more

Context: 128,000 tokens

All rates

1M_cached_input_tokens short $0.220 /1M

Input short $2.10 /1M

Output short $16.8 /1M

gpt-5.3-codex text image frontier

GPT-5.3-Codex is optimized for agentic coding tasks in Codex or similar environments. GPT-5.3-Codex supports low, medium, high, and xhigh reasoning effort settings. If you want to learn more about prompting GPT-5.3-Codex, refer to our dedicated guide.

Input

$2.10 /1M

Output

$16.8 /1M

expand_more

Context: 400,000 tokens

All rates

1M_cached_input_tokens priority $0.420 /1M

Input priority $4.20 /1M

Output priority $33.6 /1M

1M_cached_input_tokens $0.220 /1M

1M_cached_input_tokens short $0.220 /1M

Input $2.10 /1M

Input short $2.10 /1M

Output $16.8 /1M

Output short $16.8 /1M

gpt-5.4 text image frontier

OpenAI frontier model for complex professional work across agentic, coding, and professional workflows.

Input

$6.00 /1M

Output

$27.0 /1M

expand_more

Context: 1,050,000 tokens

All rates

1M_cached_input_tokens batch long $0.300 /1M

1M_cached_input_tokens batch short $0.160 /1M

Input batch long $3.00 /1M

Input batch short $1.50 /1M

Output batch long $13.5 /1M

Output batch short $9.00 /1M

1M_cached_input_tokens flex long $0.300 /1M

1M_cached_input_tokens flex short $0.160 /1M

Input flex long $3.00 /1M

Input flex short $1.50 /1M

Output flex long $13.5 /1M

Output flex short $9.00 /1M

1M_cached_input_tokens priority short $0.600 /1M

Input priority short $6.00 /1M

Output priority short $36.0 /1M

1M_cached_input_tokens long $0.600 /1M

1M_cached_input_tokens short $0.300 /1M

Input long $6.00 /1M

Input short $3.00 /1M

Output long $27.0 /1M

Output short $18.0 /1M

gpt-5.4-mini text image frontier

GPT-5.4 mini brings the strengths of GPT-5.4 to a faster, more efficient model designed for high-volume workloads. Learn more in our latest model guide.

Input

$0.900 /1M

Output

$5.40 /1M

expand_more

Context: 400,000 tokens

All rates

1M_cached_input_tokens batch short $0.050 /1M

Input batch short $0.460 /1M

Output batch short $2.70 /1M

1M_cached_input_tokens flex short $0.050 /1M

Input flex short $0.460 /1M

Output flex short $2.70 /1M

1M_cached_input_tokens priority short $0.180 /1M

Input priority short $1.80 /1M

Output priority short $10.8 /1M

1M_cached_input_tokens short $0.100 /1M

Input short $0.900 /1M

Output short $5.40 /1M

gpt-5.4-pro text image frontier

GPT-5.4 pro uses more compute to think harder and provide consistently better answers.

Input

$72.0 /1M

Output

$324 /1M

expand_more

Context: 1,050,000 tokens

All rates

Input batch long $36.0 /1M

Input batch short $18.0 /1M

Output batch long $162 /1M

Output batch short $108 /1M

Input flex long $36.0 /1M

Input flex short $18.0 /1M

Output flex long $162 /1M

Output flex short $108 /1M

Input long $72.0 /1M

Input short $36.0 /1M

Output long $324 /1M

Output short $216 /1M

gpt-5.5 text image frontier

GPT-5.5 is our newest frontier model for the most complex professional work. Learn more in our latest model guide. Reasoning.effort supports: none, low, medium (default), high and xhigh.

Input

$12.0 /1M

Output

$54.0 /1M

expand_more

Context: 1,050,000 tokens

All rates

1M_cached_input_tokens batch long $0.600 /1M

1M_cached_input_tokens batch short $0.300 /1M

Input batch long $6.00 /1M

Input batch short $3.00 /1M

Output batch long $27.0 /1M

Output batch short $18.0 /1M

1M_cached_input_tokens flex long $0.600 /1M

1M_cached_input_tokens flex short $0.300 /1M

Input flex long $6.00 /1M

Input flex short $3.00 /1M

Output flex long $27.0 /1M

Output flex short $18.0 /1M

1M_cached_input_tokens priority short $1.50 /1M

Input priority short $15.0 /1M

Output priority short $90.0 /1M

1M_cached_input_tokens long $1.20 /1M

1M_cached_input_tokens short $0.600 /1M

Input long $12.0 /1M

Input short $6.00 /1M

Output long $54.0 /1M

Output short $36.0 /1M

gpt-5.5-pro text image frontier

GPT-5.5 pro uses more compute to think harder and provide consistently better answers.

Input

$72.0 /1M

Output

$324 /1M

expand_more

Context: 1,050,000 tokens

All rates

Input batch short $18.0 /1M

Output batch short $108 /1M

Input flex short $18.0 /1M

Output flex short $108 /1M

Input long $72.0 /1M

Input short $36.0 /1M

Output long $324 /1M

Output short $216 /1M

gpt-image-1-mini text image frontier

OpenAI GPT Image 1 Mini - efficient image generation for lightweight applications.

Input

$2.40 /1M

Output

$9.60 /1M

expand_more

All rates

1M_cached_input_tokens short $0.240 /1M

Input short $2.40 /1M

Output short $9.60 /1M

1M_cached_input_tokens $0.300 /1M

Input $3.00 /1M

Output $9.60 /1M

1M_cached_input_tokens batch $0.160 /1M

Input batch $1.50 /1M

Output batch $4.80 /1M

gpt-image-1.5 text image frontier

OpenAI GPT Image 1.5 - enhanced image generation model.

Input

$6.00 /1M

Output

$12.0 /1M

expand_more

All rates

1M_cached_input_tokens short $1.50 /1M

Input short $6.00 /1M

Output short $12.0 /1M

1M_cached_input_tokens $2.40 /1M

Input $9.60 /1M

Output $38.4 /1M

1M_cached_input_tokens batch $1.20 /1M

Input batch $4.80 /1M

Output batch $19.2 /1M

gpt-image-2 text image frontier

GPT Image 2 is our state-of-the-art image generation model for fast, high-quality image generation and editing. It supports flexible image sizes and high-fidelity image inputs. Learn more in our image generation guide, or see the pricing page and image generation calculator for cost estimates.

Input

$9.60 /1M

Output

$36.0 /1M

expand_more

All rates

1M_cached_input_tokens batch $1.20 /1M

Input batch $4.80 /1M

Output batch $18.0 /1M

1M_cached_input_tokens $2.40 /1M

Input $9.60 /1M

Output $36.0 /1M

o3 text image frontier

o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following. Use it to think through multi-step problems that involve analysis across text, code, and images.

Input

$2.40 /1M

Output

$9.60 /1M

expand_more

Context: 200,000 tokens

All rates

1M_cached_input_tokens short $0.600 /1M

Input short $2.40 /1M

Output short $9.60 /1M

o3-pro text image frontier

The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently better answers.

Input

$24.0 /1M

Output

$96.0 /1M

expand_more

Context: 200,000 tokens

All rates

Input short $24.0 /1M

Output short $96.0 /1M

gpt-4 text frontier

GPT-4 is an older version of a high-intelligence GPT model, usable in Chat Completions.

Input

$36.0 /1M

Output

$72.0 /1M

expand_more

Context: 8,192 tokens

All rates

Input short $36.0 /1M

Output short $72.0 /1M

gpt-4o-mini text image audio

OpenAI GPT-4o Mini - highly efficient multimodal model.

Input

$0.180 /1M

Output

$0.720 /1M

expand_more

Context: 128,000 tokens

All rates

1M_cached_input_tokens short $0.100 /1M

Input short $0.180 /1M

Output short $0.720 /1M

gpt-4o-transcribe-diarize text audio

OpenAI GPT-4o Transcribe Diarize - transcription with speaker diarization.

Input

— /1M

Output

— /1M

expand_more

Context: 200,000 tokens

All rates

Audio input short $3.00 /1M

Audio output short $12.0 /1M

gpt-audio-mini text audio

OpenAI GPT Audio Mini - efficient audio processing model.

Input

$0.720 /1M

Output

$2.88 /1M

expand_more

Context: 65,000 tokens

All rates

Input short $0.720 /1M

Output short $2.88 /1M

gpt-4.1-mini text image

OpenAI GPT-4.1 Mini - cost-efficient variant with solid capabilities.

Input

$0.480 /1M

Output

$1.92 /1M

expand_more

Context: 128,000 tokens

All rates

1M_cached_input_tokens short $0.120 /1M

Input short $0.480 /1M

Output short $1.92 /1M

gpt-5-mini text image

OpenAI GPT-5 Mini - cost-efficient variant for general tasks.

Input

$0.300 /1M

Output

$2.40 /1M

expand_more

Context: 128,000 tokens

All rates

1M_cached_input_tokens short $0.040 /1M

Input short $0.300 /1M

Output short $2.40 /1M

gpt-5-nano text image

OpenAI GPT-5 Nano - ultra-efficient model for edge and embedded applications.

Input

$0.060 /1M

Output

$0.480 /1M

expand_more

Context: 8,000 tokens

All rates

1M_cached_input_tokens short $0.010 /1M

Input short $0.060 /1M

Output short $0.480 /1M

gpt-5.4-nano text image

GPT-5.4 nano is designed for tasks where speed and cost matter most like classification, data extraction, ranking, and sub-agents. Learn more in our latest model guide.

Input

$0.240 /1M

Output

$1.50 /1M

expand_more

Context: 400,000 tokens

All rates

1M_cached_input_tokens batch short $0.010 /1M

Input batch short $0.120 /1M

Output batch short $0.760 /1M

1M_cached_input_tokens flex short $0.010 /1M

Input flex short $0.120 /1M

Output flex short $0.760 /1M

1M_cached_input_tokens short $0.020 /1M

Input short $0.240 /1M

Output short $1.50 /1M

Vertex AI

19 models

gemini-2.0-flash-001 text image video audio frontier

Gemini 2.0 Flash 001 - previous generation flash model.

Input

$0.600 /1M

Output

$2.40 /1M

expand_more

Context: 200,000 tokens

All rates

Audio input batch $0.600 /1M

Image input batch $0.100 /1M

Input batch $0.100 /1M

1M_input_video_tokens batch $0.100 /1M

Output batch $0.360 /1M

1M_cached_input_audio_tokens $0.300 /1M

1M_cached_input_image_tokens $0.050 /1M

1M_cached_input_tokens $0.050 /1M

1M_cached_input_video_tokens $0.050 /1M

Audio input $3.60 /1M

Audio input $1.20 /1M

1M_input_audio_tokens_long $1.20 /1M

Image input $0.180 /1M

Image input $3.60 /1M

1M_input_image_tokens_long $0.180 /1M

Input $0.600 /1M

Input $0.180 /1M

1M_input_tokens_long $0.180 /1M

1M_input_video_tokens $3.60 /1M

1M_input_video_tokens $0.180 /1M

1M_input_video_tokens_long $0.180 /1M

Audio output $14.4 /1M

Image output $36.0 /1M

1M_output_image_tokens_long $36.0 /1M

Output $2.40 /1M

Output $0.720 /1M

1M_output_tokens_long $0.720 /1M

gemini-2.5-flash text image video audio frontier

Gemini 2.5 Flash - efficient model for high-throughput applications.

Input

$0.180 /1M

Output

$4.20 /1M

expand_more

Context: 1,050,000 tokens

All rates

Audio input batch $0.600 /1M

1M_input_audio_tokens_long batch $0.600 /1M

Image input batch $0.180 /1M

Image input batch $0.100 /1M

1M_input_image_tokens_long batch $0.180 /1M

Input batch $0.180 /1M

Input batch $0.100 /1M

1M_input_tokens_long batch $0.100 /1M

1M_input_tokens_long batch $0.180 /1M

1M_input_video_tokens batch $0.100 /1M

1M_input_video_tokens batch $0.180 /1M

1M_input_video_tokens_long batch $0.100 /1M

1M_input_video_tokens_long batch $0.180 /1M

Image output batch $18.0 /1M

1M_output_image_tokens_long batch $18.0 /1M

Output batch $1.50 /1M

Output batch $2.10 /1M

Output batch $1.50 /1M

Output batch $0.360 /1M

Output batch $1.50 /1M

1M_output_tokens_long batch $1.50 /1M

1M_output_tokens_long batch $2.10 /1M

1M_output_tokens_long batch $0.360 /1M

1M_cached_input_audio_tokens priority $0.220 /1M

1M_cached_input_audio_tokens_long priority $0.220 /1M

1M_cached_input_image_tokens priority $0.060 /1M

1M_cached_input_image_tokens_long priority $0.060 /1M

1M_cached_input_tokens priority $0.060 /1M

1M_cached_input_tokens_long priority $0.060 /1M

1M_cached_input_video_tokens priority $0.060 /1M

1M_cached_input_video_tokens_long priority $0.060 /1M

Audio input priority $2.16 /1M

1M_input_audio_tokens_long priority $2.16 /1M

Image input priority $0.650 /1M

1M_input_image_tokens_long priority $0.650 /1M

Input priority $0.650 /1M

1M_input_tokens_long priority $0.650 /1M

1M_input_video_tokens priority $0.650 /1M

1M_input_video_tokens_long priority $0.650 /1M

Output priority $5.40 /1M

1M_output_tokens_long priority $5.40 /1M

1M_cached_input_audio_tokens $0.300 /1M

1M_cached_input_audio_tokens $0.120 /1M

1M_cached_input_audio_tokens_long $0.300 /1M

1M_cached_input_audio_tokens_long $0.120 /1M

1M_cached_input_image_tokens $0.050 /1M

1M_cached_input_image_tokens $0.040 /1M

1M_cached_input_image_tokens_long $0.050 /1M

1M_cached_input_image_tokens_long $0.040 /1M

1M_cached_input_tokens $0.050 /1M

1M_cached_input_tokens $0.040 /1M

1M_cached_input_tokens_long $0.040 /1M

1M_cached_input_tokens_long $0.050 /1M

1M_cached_input_video_tokens $0.040 /1M

1M_cached_input_video_tokens $0.050 /1M

1M_cached_input_video_tokens_long $0.040 /1M

1M_cached_input_video_tokens_long $0.050 /1M

Audio input $3.60 /1M

Audio input $1.20 /1M

1M_input_audio_tokens_long $1.20 /1M

Image input $0.360 /1M

Image input $0.180 /1M

Image input $3.60 /1M

1M_input_image_tokens_long $0.360 /1M

1M_input_image_tokens_long $0.180 /1M

Input $0.180 /1M

Input $0.600 /1M

Input $0.360 /1M

1M_input_tokens_long $0.360 /1M

1M_input_tokens_long $0.180 /1M

1M_input_video_tokens $3.60 /1M

1M_input_video_tokens $0.360 /1M

1M_input_video_tokens $0.180 /1M

1M_input_video_tokens_long $0.180 /1M

1M_input_video_tokens_long $0.360 /1M

Audio output $14.4 /1M

Image output $36.0 /1M

1M_output_image_tokens_long $36.0 /1M

Output $4.20 /1M

Output $0.720 /1M

Output $3.00 /1M

Output $4.20 /1M

Output $3.00 /1M

Output $4.20 /1M

Output $2.40 /1M

Output $3.00 /1M

1M_output_tokens_long $3.00 /1M

1M_output_tokens_long $4.20 /1M

1M_output_tokens_long $3.00 /1M

1M_output_tokens_long $0.720 /1M

gemini-2.5-pro text image video audio frontier

Gemini 2.5 Pro - advanced multimodal model for enterprise applications.

Input

$1.50 /1M

Output

$12.0 /1M

expand_more

Context: 1,050,000 tokens

All rates

Audio input batch $0.760 /1M

1M_input_audio_tokens_long batch $1.50 /1M

Image input batch $0.760 /1M

1M_input_image_tokens_long batch $1.50 /1M

Input batch $0.760 /1M

1M_input_tokens_long batch $1.50 /1M

1M_input_video_tokens batch $0.760 /1M

1M_input_video_tokens_long batch $1.50 /1M

Output batch $6.00 /1M

1M_output_tokens_long batch $9.00 /1M

1M_cached_input_audio_tokens priority $0.280 /1M

1M_cached_input_audio_tokens_long priority $0.540 /1M

1M_cached_input_image_tokens priority $0.280 /1M

1M_cached_input_image_tokens_long priority $0.540 /1M

1M_cached_input_tokens priority $0.280 /1M

1M_cached_input_tokens_long priority $0.540 /1M

1M_cached_input_video_tokens priority $0.280 /1M

1M_cached_input_video_tokens_long priority $0.540 /1M

Audio input priority $2.70 /1M

1M_input_audio_tokens_long priority $5.40 /1M

Image input priority $2.70 /1M

1M_input_image_tokens_long priority $5.40 /1M

Input priority $2.70 /1M

1M_input_tokens_long priority $5.40 /1M

1M_input_video_tokens priority $2.70 /1M

1M_input_video_tokens_long priority $5.40 /1M

Output priority $21.6 /1M

1M_output_tokens_long priority $32.4 /1M

1M_cached_input_audio_tokens $0.160 /1M

1M_cached_input_audio_tokens_long $0.300 /1M

1M_cached_input_image_tokens $0.160 /1M

1M_cached_input_image_tokens_long $0.300 /1M

1M_cached_input_tokens $0.160 /1M

1M_cached_input_tokens_long $0.300 /1M

1M_cached_input_video_tokens $0.160 /1M

1M_cached_input_video_tokens_long $0.300 /1M

Audio input $1.50 /1M

1M_input_audio_tokens_long $3.00 /1M

Image input $1.50 /1M

1M_input_image_tokens_long $3.00 /1M

Input $1.50 /1M

1M_input_tokens_long $3.00 /1M

1M_input_video_tokens $1.50 /1M

1M_input_video_tokens_long $3.00 /1M

Output $12.0 /1M

1M_output_tokens_long $18.0 /1M

gemini-3-flash-preview text image video audio frontier

Google gemini-3-flash-preview

Input

$0.600 /1M

Output

$3.60 /1M

expand_more

All rates

1M_cached_input_audio_tokens batch $0.060 /1M

1M_cached_input_image_tokens batch $0.040 /1M

1M_cached_input_tokens batch $0.040 /1M

1M_cached_input_video_tokens batch $0.040 /1M

Audio input batch $0.600 /1M

Image input batch $0.300 /1M

Input batch $0.300 /1M

1M_input_video_tokens batch $0.300 /1M

Output batch $1.80 /1M

1M_cached_input_audio_tokens flex $0.060 /1M

1M_cached_input_image_tokens flex $0.040 /1M

1M_cached_input_tokens flex $0.040 /1M

1M_cached_input_video_tokens flex $0.040 /1M

Audio input flex $0.600 /1M

Image input flex $0.300 /1M

Input flex $0.300 /1M

1M_input_video_tokens flex $0.300 /1M

Output flex $1.80 /1M

1M_cached_input_audio_tokens priority $0.220 /1M

1M_cached_input_image_tokens priority $0.110 /1M

1M_cached_input_tokens priority $0.110 /1M

1M_cached_input_video_tokens priority $0.110 /1M

Audio input priority $2.16 /1M

Image input priority $1.08 /1M

Input priority $1.08 /1M

1M_input_video_tokens priority $1.08 /1M

Output priority $6.48 /1M

1M_cached_input_audio_tokens $0.120 /1M

1M_cached_input_image_tokens $0.060 /1M

1M_cached_input_tokens $0.060 /1M

1M_cached_input_video_tokens $0.060 /1M

Audio input $1.20 /1M

Image input $0.600 /1M

Input $0.600 /1M

1M_input_video_tokens $0.600 /1M

Output $3.60 /1M

gemini-3.1-flash-lite text image video audio frontier

Google gemini-3.1-flash-lite

Input

$0.300 /1M

Output

$3.60 /1M

expand_more

All rates

1M_cached_input_audio_tokens batch $0.040 /1M

1M_cached_input_image_tokens batch $0.010 /1M

1M_cached_input_tokens batch $0.010 /1M

1M_cached_input_video_tokens batch $0.010 /1M

Audio input batch $0.300 /1M

Image input batch $0.160 /1M

Input batch $0.300 /1M

Input batch $0.160 /1M

1M_input_video_tokens batch $0.160 /1M

Output batch $0.900 /1M

Output batch $1.80 /1M

Output batch $0.900 /1M

1M_cached_input_audio_tokens flex $0.040 /1M

1M_cached_input_image_tokens flex $0.010 /1M

1M_cached_input_tokens flex $0.010 /1M

1M_cached_input_video_tokens flex $0.010 /1M

Audio input flex $0.300 /1M

Image input flex $0.160 /1M

Input flex $0.160 /1M

Input flex $0.300 /1M

1M_input_video_tokens flex $0.160 /1M

Output flex $0.900 /1M

Output flex $1.80 /1M

Output flex $0.900 /1M

1M_cached_input_audio_tokens priority $0.110 /1M

1M_cached_input_image_tokens priority $0.060 /1M

1M_cached_input_tokens priority $0.060 /1M

1M_cached_input_video_tokens priority $0.060 /1M

Audio input priority $1.08 /1M

Image input priority $0.540 /1M

Input priority $0.540 /1M

Input priority $1.08 /1M

1M_input_video_tokens priority $0.540 /1M

Output priority $6.48 /1M

Output priority $3.24 /1M

1M_cached_input_audio_tokens $0.060 /1M

1M_cached_input_image_tokens $0.040 /1M

1M_cached_input_tokens $0.040 /1M

1M_cached_input_video_tokens $0.040 /1M

Audio input $0.600 /1M

Image input $0.300 /1M

Input $0.300 /1M

Input $0.600 /1M

1M_input_video_tokens $0.300 /1M

Output $3.60 /1M

Output $1.80 /1M

gemini-3.5-flash text image video audio frontier

Google gemini-3.5-flash

Input

$1.80 /1M

Output

$10.8 /1M

expand_more

All rates

1M_cached_input_audio_tokens batch $0.100 /1M

1M_cached_input_image_tokens batch $0.100 /1M

1M_cached_input_tokens batch $0.100 /1M

1M_cached_input_video_tokens batch $0.100 /1M

Audio input batch $0.900 /1M

Image input batch $0.900 /1M

Input batch $0.900 /1M

1M_input_video_tokens batch $0.900 /1M

Output batch $5.40 /1M

1M_cached_input_audio_tokens flex $0.100 /1M

1M_cached_input_image_tokens flex $0.100 /1M

1M_cached_input_tokens flex $0.100 /1M

1M_cached_input_video_tokens flex $0.100 /1M

Audio input flex $0.900 /1M

Image input flex $0.900 /1M

Input flex $0.900 /1M

1M_input_video_tokens flex $0.900 /1M

Output flex $5.40 /1M

1M_cached_input_audio_tokens priority $0.320 /1M

1M_cached_input_image_tokens priority $0.320 /1M

1M_cached_input_tokens priority $0.320 /1M

1M_cached_input_video_tokens priority $0.320 /1M

Audio input priority $3.24 /1M

Image input priority $3.24 /1M

Input priority $3.24 /1M

1M_input_video_tokens priority $3.24 /1M

Output priority $19.4 /1M

1M_cached_input_audio_tokens $0.180 /1M

1M_cached_input_image_tokens $0.180 /1M

1M_cached_input_tokens $0.180 /1M

1M_cached_input_video_tokens $0.180 /1M

Audio input $1.80 /1M

Image input $1.80 /1M

Input $1.80 /1M

1M_input_video_tokens $1.80 /1M

Output $10.8 /1M

gemini-3.1-flash-image-preview text image frontier

Google gemini-3.1-flash-image-preview

Input

— /1M

Output

— /1M

expand_more

All rates

Image input batch $0.300 /1M

Image output batch $36.0 /1M

Image input flex $0.300 /1M

Image output flex $36.0 /1M

Image input priority $1.08 /1M

Image output priority $130 /1M

Image input $0.600 /1M

Image output $72.0 /1M

deepseek-r1-0528-maas text frontier

deepseek-ai deepseek-r1-0528-maas

Input

$1.62 /1M

Output

$6.48 /1M

expand_more

All rates

Input batch $0.820 /1M

Output batch $3.24 /1M

Input $1.62 /1M

Output $6.48 /1M

gemini-2.0-flash-lite-001 text image video audio

Google gemini-2.0-flash-lite-001

Input

$0.100 /1M

Output

$0.360 /1M

expand_more

All rates

Audio input batch $0.050 /1M

Image input batch $0.050 /1M

Input batch $0.050 /1M

1M_input_video_tokens batch $0.050 /1M

Output batch $0.180 /1M

1M_cached_input_audio_tokens $0.020 /1M

1M_cached_input_image_tokens $0.020 /1M

1M_cached_input_tokens $0.020 /1M

1M_cached_input_video_tokens $0.020 /1M

Audio input $0.100 /1M

Image input $0.100 /1M

Input $0.100 /1M

1M_input_video_tokens $0.100 /1M

Output $0.360 /1M

gemini-2.5-flash-lite text image video audio

Gemini 2.5 Flash Lite - ultra-efficient model for mobile and edge devices.

Input

$0.120 /1M

Output

$0.480 /1M

expand_more

Context: 256,000 tokens

All rates

Audio input batch $0.180 /1M

Image input batch $0.060 /1M

Input batch $0.060 /1M

1M_input_video_tokens batch $0.060 /1M

Output batch $0.240 /1M

1M_cached_input_audio_tokens priority $0.060 /1M

1M_cached_input_image_tokens priority $0.020 /1M

1M_cached_input_tokens priority $0.020 /1M

1M_cached_input_video_tokens priority $0.020 /1M

Audio input priority $0.650 /1M

Image input priority $0.220 /1M

Input priority $0.220 /1M

1M_input_video_tokens priority $0.220 /1M

Output priority $0.860 /1M

1M_cached_input_audio_tokens $0.040 /1M

1M_cached_input_image_tokens $0.010 /1M

1M_cached_input_tokens $0.010 /1M

1M_cached_input_video_tokens $0.010 /1M

Audio input $0.360 /1M

Image input $0.120 /1M

Input $0.120 /1M

1M_input_video_tokens $0.120 /1M

Output $0.480 /1M

imagen-3.0-generate-002 text image

Google imagen-3.0-generate-002

Input

— /1M

Output

— /1M

expand_more

All rates

per_image $0.050 /1M

imagen-4.0-generate-001 text image

Imagen 4.0 Generate 001 - high-fidelity image generation model.

Input

— /1M

Output

— /1M

expand_more

All rates

per_image $0.050 /1M

veo-2.0-generate-001 text image video

Google veo-2.0-generate-001

Input

— /1M

Output

— /1M

expand_more

All rates

per_second_video $0.600 /1M

deepseek-ocr-maas text

deepseek-ai deepseek-ocr-maas

Input

$0.360 /1M

Output

$1.44 /1M

expand_more

All rates

Input $0.360 /1M

Output $1.44 /1M

deepseek-v3.1-maas text

deepseek-ai deepseek-v3.1-maas

Input

$0.720 /1M

Output

$2.04 /1M

expand_more

All rates

Input batch $0.360 /1M

Output batch $1.02 /1M

1M_cached_input_tokens $0.070 /1M

Input $0.720 /1M

Output $2.04 /1M

deepseek-v3.2-maas text

deepseek-ai deepseek-v3.2-maas

Input

$0.670 /1M

Output

$2.02 /1M

expand_more

All rates

1M_cached_input_tokens $0.070 /1M

Input $0.670 /1M

Output $2.02 /1M

gemma-4-26b-a4b-it-maas text

Google gemma-4-26b-a4b-it-maas

Input

$0.180 /1M

Output

$0.720 /1M

expand_more

All rates

1M_cached_input_tokens $0.020 /1M

Input $0.180 /1M

Output $0.720 /1M

gpt-oss-120b-maas text

openai gpt-oss-120b-maas

Input

$0.110 /1M

Output

$0.430 /1M

expand_more

All rates

Input batch $0.060 /1M

Output batch $0.220 /1M

Input $0.110 /1M

Output $0.430 /1M

llama-4-maverick-17b-128e-instruct-maas text

meta llama-4-maverick-17b-128e-instruct-maas

Input

$0.420 /1M

Output

$1.38 /1M

expand_more

All rates

Input batch $0.220 /1M

Output batch $0.700 /1M

Input $0.420 /1M

Output $1.38 /1M

Every model. One key.

Every model.
One key.