qwen-flash | ContextIn/Out per 1M tok ≤ 256K ↓ 0.05 $↑ 0.4 $ > 256K ↓ 0.25 $↑ 2 $ | ||
qwen-imageImage Generation | 0.035 $ | 0.035 $ | |
qwen-image-2.0Image Generation | 0.035 $ | 0.035 $ | |
qwen-image-2.0-proImage Generation | 0.075 $ | 0.075 $ | |
qwen-image-editImage Generation | 0.045 $ | 0.045 $ | |
qwen-max | ContextIn/Out per 1M tok ≤ 32K ↓ 1.2 $↑ 6 $ 32K - 128K ↓ 2.4 $↑ 12 $ 128K - 252K ↓ 3 $↑ 15 $ Cache: Hit 20% / Explicit 10% / Creation 125% | ||
qwen-plus | ContextIn/Out per 1M tok ≤ 256K ↓ 0.4 $↑ 1.2 $ 256K - 1.0M ↓ 1.2 $↑ 3.6 $ Cache: Hit 20% / Explicit 10% / Creation 125% | ||
qwen3-235b-a22b-instruct-2507 | 0.7 $ | 2.8 $ | |
qwen3-235b-a22b-thinking-2507 | 0.7 $ | 8.4 $ | |
qwen3-coder-30b-a3b-instruct | ContextIn/Out per 1M tok ≤ 32K ↓ 0.45 $↑ 2.25 $ 32K - 128K ↓ 0.75 $↑ 3.75 $ 128K - 200K ↓ 1.2 $↑ 6 $ Cache: Hit 20% / Explicit 10% / Creation 125% | ||
qwen3-coder-480b-a35b-instruct | ContextIn/Out per 1M tok ≤ 32K ↓ 1.5 $↑ 7.5 $ 32K - 128K ↓ 2.7 $↑ 13.5 $ 128K - 200K ↓ 4.5 $↑ 22.5 $ Cache: Hit 20% / Explicit 10% / Creation 125% | ||
qwen3-coder-flash | ContextIn/Out per 1M tok ≤ 32K ↓ 0.2 $↑ 0.8 $ 32K - 128K ↓ 0.36 $↑ 1.44 $ 128K - 256K ↓ 0.6 $↑ 2.4 $ 256K - 1.0M ↓ 1.2 $↑ 9.6 $ Cache: Hit 20% / Explicit 10% / Creation 125% | ||
qwen3-coder-plus | ContextIn/Out per 1M tok ≤ 32K ↓ 1 $↑ 5 $ 32K - 128K ↓ 1.8 $↑ 9 $ 128K - 256K ↓ 3 $↑ 15 $ 256K - 1.0M ↓ 6 $↑ 60 $ Cache: Hit 20% / Explicit 10% / Creation 125% | ||
qwen3-vl-235b-a22b-instructVision Capable | 0.7 $ | 2.8 $ | |
qwen3-vl-235b-a22b-thinkingVision Capable | 0.7 $ | 8.4 $ | |
qwen3.5-397b-a17bVision Capable | 0.6 $ | 3.6 $ | |
qwen3.5-plus-2026-02-15Vision Capable | ContextIn/Out per 1M tok ≤ 256K ↓ 0.4 $↑ 2.4 $ 256K - 1.0M ↓ 1.2 $↑ 7.2 $ Cache: Hit 20% / Explicit 10% / Creation 125% | ||
wan2.5-t2v-previewVideo Generation | 0.15 $ | 0.15 $ | |
wan2.6-i2vVision Capable, Video Generation | 0.1 $ | 0.15 $ | |
wan2.6-i2v-flashVision Capable, Video Generation | 0.025 $ | 0.075 $ | |
wan2.6-imageVision Capable, Image Generation | 0.03 $ | 0.03 $ | |
wan2.6-r2vVision Capable, Video Generation | 0.1 $ | 0.15 $ | |
wan2.6-r2v-flashVision Capable, Video Generation | 0.025 $ | 0.075 $ | |
wan2.6-t2iImage Generation | 0.03 $ | 0.03 $ | |
wan2.6-t2vVideo Generation | 0.1 $ | 0.15 $ | |
claude-3-haiku-20240307Vision Capable | 0.25 $ | 1.25 $ |
claude-haiku-4-5-20251001Vision Capable | 1 $ | 5 $ |
claude-opus-4-1-20250805Vision Capable | 15 $ | 75 $ |
claude-opus-4-20250514Vision Capable | 15 $ | 75 $ |
claude-opus-4-5-20251101Vision Capable | 5 $ | 25 $ |
claude-opus-4-6Vision Capable | 5 $ | 25 $ |
claude-sonnet-4-20250514Vision Capable | 3 $ | 15 $ |
claude-sonnet-4-5-20250929Vision Capable | 3 $ | 15 $ |
claude-sonnet-4-6Vision Capable | 3 $ | 15 $ |
kimi-k2.5Vision Capable | 0.6 $ | 3 $ |
seed-1-6-250915Vision Capable | ContextIn/Out per 1M tok ≤ 128K ↓ 0.25 $↑ 2 $ > 128K ↓ 0.5 $↑ 4 $ Cache: 0.05 $ per million | ||
seed-1-8-251228Vision Capable | ContextIn/Out per 1M tok ≤ 128K ↓ 0.25 $↑ 2 $ > 128K ↓ 0.5 $↑ 4 $ Cache: 0.05 $ per million | ||
seedance-1-0-pro-250528Video Generation | 2.5 $ | 2.5 $ | |
seedance-1-0-pro-fast-251015Video Generation | 1 $ | 1 $ | |
seedance-1-5-pro-251215Video Generation | 2.4 $ | 2.4 $ | |
seedream-4-0-250828Image Generation | 0.03 $ | 0.03 $ | |
seedream-4-5-251128Image Generation | 0.04 $ | 0.04 $ | |
deepseek-ai/DeepSeek-R1-0528 | 0.5 $ | 2.15 $ |
google/gemma-4-26B-A4B-itVision Capable | 0.08 $ | 0.35 $ |
google/gemma-4-31B-itVision Capable | 0.13 $ | 0.38 $ |
moonshotai/Kimi-K2.5Vision Capable | 0.45 $ | 2.25 $ |
deepseek-chat | 0.28 $ | 0.42 $ |
deepseek-reasoner | 0.28 $ | 0.42 $ |
gemini-2.0-flashVision Capable, Audio Generation Deprecated May 31, 2026 | 0.1 $ | 0.4 $ | |
gemini-2.0-flash-liteVision Capable, Audio Generation Deprecated May 31, 2026 | 0.075 $ | 0.3 $ | |
gemini-2.5-flashVision Capable, Audio Generation | 0.3 $ | 2.5 $ | |
gemini-2.5-flash-imageImage Generation | 0.3 $ | 2.5 $ | |
gemini-2.5-flash-liteVision Capable, Audio Generation | 0.1 $ | 0.4 $ | |
gemini-2.5-proVision Capable, Audio Generation | ContextIn/Out per 1M tok ≤ 200K ↓ 1.25 $↑ 10 $ > 200K ↓ 2.5 $↑ 15 $ Cache (≤ 200K):Read 0.125 $ Cache (> 200K):Read 0.25 $ | ||
gemini-3-flash-previewVision Capable, Audio Generation | 0.5 $ | 3 $ | |
gemini-3-pro-image-previewImage Generation | 2 $ | 12 $ | |
gemini-3-pro-previewVision Capable, Audio Generation | ContextIn/Out per 1M tok ≤ 200K ↓ 2 $↑ 12 $ > 200K ↓ 4 $↑ 18 $ Cache (≤ 200K):Read 0.2 $ Cache (> 200K):Read 0.4 $ | ||
gemini-3.1-flash-image-previewImage Generation | 0.5 $ | 3 $ | |
gemini-3.1-flash-lite-previewVision Capable | ContextIn/Out per 1M tok ≤ 200K ↓ 0.25 $↑ 1.5 $ > 200K ↓ 0.25 $↑ 1.5 $ Cache (≤ 200K):Read 0.03 $ Cache (> 200K):Read 0.03 $ | ||
gemini-3.1-pro-previewVision Capable | ContextIn/Out per 1M tok ≤ 200K ↓ 2 $↑ 12 $ > 200K ↓ 4 $↑ 18 $ Cache (≤ 200K):Read 0.2 $ Cache (> 200K):Read 0.4 $ | ||
imagen-4.0-fast-generate-001Image Generation | 0.02 $ | 0.02 $ | |
imagen-4.0-generate-001Image Generation | 0.04 $ | 0.04 $ | |
imagen-4.0-ultra-generate-001Image Generation | 0.06 $ | 0.06 $ | |
veo-3.0-fast-generate-001Video Generation | 0.15 $ | 0.15 $ | |
veo-3.0-generate-001Video Generation | 0.4 $ | 0.4 $ | |
veo-3.1-fast-generate-previewVideo Generation | 0.15 $ | 0.15 $ | |
veo-3.1-generate-previewVideo Generation | 0.4 $ | 0.4 $ | |
veo-3.1-lite-generate-previewVideo Generation | 0.05 $ | 0.05 $ | |
I2V-01-DirectorVideo Generation | 0.43 $ | 0.43 $ |
image-01Image Generation | 0.0035 $ | 0.0035 $ |
MiniMax-Hailuo-02Video Generation | 0.56 $ | 0.56 $ |
MiniMax-Hailuo-2.3Video Generation | 0.56 $ | 0.56 $ |
MiniMax-Hailuo-2.3-FastVideo Generation | 0.32 $ | 0.32 $ |
minimax-m2 | 0.3 $ | 1.2 $ |
minimax-m2.1 | 0.3 $ | 1.2 $ |
minimax-m2.5 | 0.3 $ | 1.2 $ |
minimax-m2.5-highspeed | 0.3 $ | 3.6 $ |
minimax-m2.7 | 0.3 $ | 1.2 $ |
minimax-m2.7-highspeed | 0.3 $ | 2.4 $ |
MiniMax-Text-01Vision Capable | 0.2 $ | 1.1 $ |
S2V-01Video Generation | 0.65 $ | 0.65 $ |
T2V-01-DirectorVideo Generation | 0.43 $ | 0.43 $ |
codestral-latest | 0.3 $ | 0.9 $ |
mistral-large-latestVision Capable | 0.5 $ | 1.5 $ |
mistral-medium-latestVision Capable | 0.4 $ | 2 $ |
kimi-k2-0905-preview | 0.6 $ | 2.5 $ | |
kimi-k2-thinking | 0.6 $ | 2.5 $ | |
kimi-k2-thinking-turbo | 1.15 $ | 8 $ | |
kimi-k2-turbo-preview | 1.15 $ | 8 $ | |
kimi-k2.5Vision Capable | 0.6 $ | 3 $ | |
kimi-latestVision Capable | ContextIn/Out per 1M tok ≤ 8K ↓ 0.2 $↑ 2 $ 8K - 33K ↓ 1 $↑ 3 $ 33K - 131K ↓ 2 $↑ 5 $ | ||
dall-e-2Image Generation | 0.02 $ | 0.02 $ | |
dall-e-3Image Generation | 0.04 $ | 0.04 $ | |
gpt-3.5-turbo | 0.5 $ | 1.5 $ | |
gpt-4 | 30 $ | 60 $ | |
gpt-4-turboVision Capable | 10 $ | 30 $ | |
gpt-4.1Vision Capable | 2 $ | 8 $ | |
gpt-4.1-miniVision Capable | 0.4 $ | 1.6 $ | |
gpt-4.1-nanoVision Capable | 0.1 $ | 0.4 $ | |
gpt-4oVision Capable | 2.5 $ | 10 $ | |
gpt-4o-miniVision Capable | 0.15 $ | 0.6 $ | |
gpt-4o-mini-transcribe | 1.25 $ | 5 $ | |
gpt-4o-mini-tts | 0.6 $ | 12 $ | |
gpt-4o-transcribe | 2.5 $ | 10 $ | |
gpt-4o-transcribe-diarize | 2.5 $ | 10 $ | |
gpt-5Vision Capable | 1.25 $ | 10 $ | |
gpt-5-miniVision Capable | 0.25 $ | 2 $ | |
gpt-5-nanoVision Capable | 0.05 $ | 0.4 $ | |
gpt-5.2Vision Capable | 1.75 $ | 14 $ | |
gpt-5.2-proVision Capable | 21 $ | 168 $ | |
gpt-5.4Vision Capable | ContextIn/Out per 1M tok ≤ 272K ↓ 2.5 $↑ 15 $ > 272K ↓ 5 $↑ 22.5 $ Cache (≤ 272K):Read 0.25 $ Cache (> 272K):Read 0.5 $ | ||
gpt-5.4-proVision Capable | ContextIn/Out per 1M tok ≤ 272K ↓ 30 $↑ 180 $ > 272K ↓ 60 $↑ 270 $ | ||
gpt-image-1Image Generation | 5 $ | 0 $ | |
gpt-image-1-miniImage Generation | 2.5 $ | 0 $ | |
o1Vision Capable | 15 $ | 60 $ | |
o1-proVision Capable | 150 $ | 600 $ | |
o3Vision Capable | 2 $ | 8 $ | |
o3-mini | 1.1 $ | 4.4 $ | |
o4-miniVision Capable | 1.1 $ | 4.4 $ | |
sora-2Video Generation Deprecated Sep 24, 2026 | 0.1 $ | 0.1 $ | |
sora-2-proVideo Generation Deprecated Sep 24, 2026 | 0.5 $ | 0.5 $ | |
whisper-1 | 0.006 $ | 0 $ | |
grok-4-0709Vision Capable | 3 $ | 15 $ | |
grok-4-1-fast-non-reasoningVision Capable | ContextIn/Out per 1M tok ≤ 128K ↓ 0.2 $↑ 0.5 $ > 128K ↓ 0.4 $↑ 1 $ Cache: 0.05 $ per million Tool Calls: x_search: $0.005, web_search: $0.005, code_execution: $0.005, attachment_search: $0.01, collections_search: $0.0025 | ||
grok-4-1-fast-reasoningVision Capable | ContextIn/Out per 1M tok ≤ 128K ↓ 0.2 $↑ 0.5 $ > 128K ↓ 0.4 $↑ 1 $ Cache: 0.05 $ per million Tool Calls: x_search: $0.005, web_search: $0.005, code_execution: $0.005, attachment_search: $0.01, collections_search: $0.0025 | ||
grok-4-fastVision Capable | ContextIn/Out per 1M tok ≤ 128K ↓ 0.2 $↑ 0.5 $ > 128K ↓ 0.4 $↑ 1 $ Cache: 0.05 $ per million Tool Calls: x_search: $0.005, web_search: $0.005, code_execution: $0.005, attachment_search: $0.01, collections_search: $0.0025 | ||
grok-4-fast-non-reasoningVision Capable | ContextIn/Out per 1M tok ≤ 128K ↓ 0.2 $↑ 0.5 $ > 128K ↓ 0.4 $↑ 1 $ Cache: 0.05 $ per million Tool Calls: x_search: $0.005, web_search: $0.005, code_execution: $0.005, attachment_search: $0.01, collections_search: $0.0025 | ||
grok-4-fast-reasoningVision Capable | ContextIn/Out per 1M tok ≤ 128K ↓ 0.2 $↑ 0.5 $ > 128K ↓ 0.4 $↑ 1 $ Cache: 0.05 $ per million Tool Calls: x_search: $0.005, web_search: $0.005, code_execution: $0.005, attachment_search: $0.01, collections_search: $0.0025 | ||
grok-code-fast-1 | 0.2 $ | 1.5 $ | |
grok-imagine-imageImage Generation | 0.002 $ | 0.02 $ | |
grok-imagine-videoVideo Generation | 0 $ | 0.05 $ | |
grok-tts | 4.2 $ | 0 $ | |
cogvideox-3Video Generation | 0.2 $ | 0.2 $ |
cogview-4-250304Image Generation | 0.01 $ | 0.01 $ |
glm-4.5-air | 0.2 $ | 1.1 $ |
glm-4.6 | 0.6 $ | 2.2 $ |
glm-4.6vVision Capable | 0.3 $ | 0.9 $ |
glm-4.7 | 0.6 $ | 2.2 $ |
glm-5 | 1 $ | 3.2 $ |
glm-5-code | 1.2 $ | 5 $ |
glm-asr-2512 | 0.03 $ | 0 $ |
glm-imageImage Generation | 0.015 $ | 0.015 $ |
vidu2-imageVideo Generation | 0.2 $ | 0.2 $ |
vidu2-referenceVideo Generation | 0.4 $ | 0.4 $ |
vidu2-start-endVideo Generation | 0.2 $ | 0.2 $ |
viduq1-imageVideo Generation | 0.4 $ | 0.4 $ |
viduq1-start-endVideo Generation | 0.4 $ | 0.4 $ |
viduq1-textVideo Generation | 0.4 $ | 0.4 $ |