Models & Pricing.
81 models, pay-as-you-go in USD. Token prices are per 1M tokens. Check /status in the bot for live availability.
How to read this page
| Term | Meaning |
|---|---|
| Input / Output | Price per 1M prompt tokens and per 1M generated tokens |
| Cache read / write | Price per 1M tokens read from or written to the prompt cache |
| Tier | Long-context tiers apply when a request's input is above the size shown |
| Per image / second / request | Flat price per generated image, per second of video, or per speech request |
Prices last updated 2026-10-25 04:47 UTC.
Privacy across all models: Outrun keeps prompts and responses out of operational request logs. Saved history, media-job storage, and processor limits still apply. ZDR badges identify additional upstream routing controls. Read the privacy details
OpenAI GPT
Use with /v1/responses (Codex) or /v1/chat/completions. Requests with more than 272k input tokens are billed at the long-context tier.
| Model | Tier | Input / 1M | Output / 1M | Cache read / 1M | Cache write / 1M |
|---|---|---|---|---|---|
GPT-6 Astra gpt-6-astra | up to 272k tokens | $0.59 | $2.94 | $0.06 | $0.74 |
GPT-6 Astra gpt-6-astra | over 272k tokens | $1.18 | $4.41 | $0.12 | $1.47 |
GPT-5.6 Sol gpt-5.6-sol | up to 272k tokens | $0.30 | $1.77 | $0.03 | $0.37 |
GPT-5.6 Sol gpt-5.6-sol | over 272k tokens | $0.59 | $2.65 | $0.06 | $0.74 |
GPT-5.6 Terra gpt-5.6-terra | up to 272k tokens | $0.12 | $0.71 | $0.02 | $0.15 |
GPT-5.6 Terra gpt-5.6-terra | over 272k tokens | $0.24 | $1.06 | $0.03 | $0.30 |
GPT-6 Sol gpt-6-sol | up to 272k tokens | $0.12 | $0.59 | $0.02 | $0.15 |
GPT-6 Sol gpt-6-sol | over 272k tokens | $0.24 | $0.89 | $0.03 | $0.30 |
GPT-6.1 Sol gpt-6.1-sol | up to 272k tokens | $0.12 | $0.59 | $0.01 | $0.15 |
GPT-6.1 Sol gpt-6.1-sol | over 272k tokens | $0.24 | $0.89 | $0.02 | $0.30 |
Anthropic Claude
Use with /v1/messages (Claude Code, Anthropic SDKs) or /v1/chat/completions. Cache write is the 5-minute cache; cache write 1h is the 1-hour cache.
| Model | Input / 1M | Output / 1M | Cache read / 1M | Cache write / 1M | Cache write 1h / 1M |
|---|---|---|---|---|---|
Claude Opus 5.5 claude-opus-5-5 | $2.24 | $11.20 | $0.112 | $2.80 | $4.48 |
Claude Opus 5 claude-opus-5 | $3.15 | $15.75 | $0.32 | $3.94 | $6.30 |
Claude Sonnet 5 claude-sonnet-5 | $1.12 | $5.60 | $0.112 | $1.40 | $2.24 |
Claude Fable 5.1 claude-fable-5-1 | $6.30 | $31.50 | $0.16 | $7.88 | $12.60 |
Claude Fable 5 claude-fable-5 | $5.60 | $28.00 | $0.56 | $7.00 | $11.20 |
Claude Sonnet 5.5 claude-sonnet-5-5 | $0.49 | $2.45 | $0.049 | $0.6125 | $0.98 |
Google Gemini
Gemini 4 Argon uses /v1/chat/completions. Other Gemini text models also support Gemini native https://api.outrun.to/v1/gemini-cli/v1beta/models/{model}:generateContent. Long-context tiers apply where shown.
| Model | Tier | Input / 1M | Output / 1M | Cache read / 1M |
|---|---|---|---|---|
Gemini 3.8 Flash gemini-3.8-flash | - | $0.32 | $1.58 | $0.04 |
Gemini 3.1 Pro Preview gemini-3.1-pro-preview | up to 200k tokens | $1.26 | $7.56 | $0.13 |
Gemini 3.1 Pro Preview gemini-3.1-pro-preview | over 200k tokens | $2.52 | $11.34 | $0.26 |
Gemini 3.7 Flash gemini-3.7-flash | - | $0.95 | $4.73 | $0.10 |
Gemini 4 Argon gemini-4-argon | - | $1.20 | $6.00 | $0.12 |
xAI Grok
OpenAI-compatible: /v1/chat/completions. Long-context tiers apply where shown.
| Model | Tier | Input / 1M | Output / 1M | Cache read / 1M |
|---|---|---|---|---|
Grok 4.7 grok-4.7 | up to 200k tokens | $0.09 | $0.26 | $0.03 |
Grok 4.7 grok-4.7 | over 200k tokens | $0.17 | $0.51 | $0.05 |
Image generation
Billed per generated image via /v1/images/generations. nano-banana-pro is still accepted as an alias of gemini-3-pro-image.
| Model | Per image |
|---|---|
Nano Banana Pro / Gemini 3 Pro Image gemini-3-pro-image | $0.04 |
Nano Banana / Gemini 3.1 Flash Image gemini-3.1-flash-image | $0.03 |
GPT Image 2 gpt-image-2 | $0.06 |
Grok Imagine Image grok-imagine-image | $0.06 |
Speech
TTS (gemini-3.1-tts) is billed per request via /v1/audio/speech. STT models are billed per token; send audio through chat completions or Gemini native requests.
| Model | Input / 1M | Output / 1M | Cache read / 1M | Per request |
|---|---|---|---|---|
Gemini 3 STT gemini-3-stt | $0.32 | $1.89 | $0.04 | - |
Gemini 3.1 TTS gemini-3.1-tts | - | - | - | $0.04 |
Video generation
Billed per second of generated video via /v1/videos. Use the model ID exactly as shown.
| Model | Tier | Per second |
|---|---|---|
Gemini Omni Flash gemini-omni-flash | - | $0.06 |
Veo 3.1 veo-3.1 | 720p/1080p | $0.08 |
Veo 3.1 veo-3.1 | 4K | $0.12 |
Veo 3.1 Fast veo-3.1-fast | 720p/1080p | $0.03 |
Veo 3.1 Fast veo-3.1-fast | 4K | $0.07 |
Seedance 2.5 720p Official seedance-2.5-720p-official | - | $0.36 |
Seedance 2.0 Mini 720p seedance-2.0-mini-720p | - | $0.10 |
Seedance 2.5 720p seedance-2.5-720p | - | $0.29 |
Seedance 2.5 1080p seedance-2.5-1080p | - | $0.48 |
Seedance 2.0 720p seedance-2.0-720p | - | $0.26 |
Seedance 2.0 1080p seedance-2.0-1080p | - | $0.42 |
Grok Imagine Video 1.5 1080p grok-imagine-video-1.5-1080p | - | $0.09 |
Wan 3.0 1080p wan3.0-video-1080p | - | $0.33 |
Grok Imagine Video grok-imagine-video | - | $0.03 |
MiniMax H3 MiniMax-H3 | 768P | $0.06 |
Moonshot Kimi
OpenAI-compatible: /v1/chat/completions.
| Model | Input / 1M | Output / 1M | Cache read / 1M |
|---|---|---|---|
Kimi K3 kimi-k3 | $1.80 | $9.00 | $0.18 |
MiniMax
OpenAI-compatible: /v1/chat/completions. MiniMax M3 has long-context tiers above 512k input tokens; M3.1 Flash uses the same listed rates throughout its context window.
| Model | Tier | Input / 1M | Output / 1M | Cache read / 1M |
|---|---|---|---|---|
MiniMax M3 MiniMax-M3 | - | $0.18 | $0.72 | $0.036 |
MiniMax M3.1 Flash minimax-m3.1-flash | - | $0.09 | $0.36 | $0.009 |
DeepSeek
OpenAI-compatible: /v1/chat/completions.
| Model | Input / 1M | Output / 1M | Cache read / 1M |
|---|---|---|---|
DeepSeek V4 Pro deepseek-v4-pro | $1.35 | $4.05 | $0.05 |
DeepSeek V4 Flash deepseek-v4-flash | $0.45 | $1.35 | $0.02 |
DeepSeek V4.1 Flash deepseek-v4.1-flash | $0.30 | $1.20 | $0.01 |
DeepSeek V4.1 Flash 1017 deepseek-v4.1-flash-1017 · ZDR | $0.08 | $0.16 | $0.016 |
DeepSeek V4.1 Flash 1017 (3) deepseek-v4.1-flash-1017-3 | $0.20 | $1.00 | $0.006 |
Zhipu GLM
OpenAI-compatible: /v1/chat/completions.
| Model | Input / 1M | Output / 1M | Cache read / 1M |
|---|---|---|---|
GLM-5.3 Flash glm-5.3-flash | $0.12 | $0.42 | $0.04 |
GLM-5.3 glm-5.3 | $0.6552 | $2.0592 | $0.1216 |
GLM-5.3 Flash Cybersecurity glm-5.3-flash-cybersecurity | $0.30 | $1.00 | $0.15 |
Uncensored
Uncensored text and media models, grouped by type below. Images use /v1/images/generations; video models use /v1/videos when listed. Uncensored GLM, DeepSeek and MiMo variants. OpenAI-compatible: /v1/chat/completions. Some GLM variants include a built-in system prompt that counts as input tokens (about 14k previously measured on glm-5.3-uncensored and glm-5.3-flash-uncensored); this is not a stated MiMo surcharge. MiMo variants have a published 1,048,576-token context and 65,536-token maximum output; request limits and available balance still apply. MiMo Uncensored Thinking uses its default thinking mode; omit reasoning_effort overrides. Outrun Red Team Flash and Pro are branded security-focused routes, mapped to deepseek-v4.1-flash-redteam and glm-5.3-redteam respectively.
Text models
| Model | Input / 1M | Output / 1M | Cache read / 1M | Cache write / 1M |
|---|---|---|---|---|
GLM-5.3 Flash Uncensored glm-5.3-flash-uncensored | $0.10 | $0.10 | $0.01 | $0.10 |
GLM-5.3 Flash Abliterated glm-5.3-flash-abliterated | $0.40 | $0.40 | $0.10 | $0.40 |
GLM-5.3 Uncensored glm-5.3-uncensored | $0.20 | $0.20 | $0.06 | $0.20 |
DeepSeek V4 Pro Uncensored deepseek-v4-pro-uncensored | $0.50 | $0.50 | $0.10 | $0.50 |
GLM-5.3 Abliterated glm-5.3-abliterated | $1.40 | $1.40 | $0.40 | $1.40 |
MiMo V2.6 Flash Uncensored Thinking mimo-v2.6-flash-uncensored-thinking | $1.00 | $3.00 | $0.399 | - |
MiMo V2.6 Flash Abliterated mimo-v2.6-flash-abliterated | $1.00 | $3.00 | $0.55 | - |
MiMo V2.6 Flash Uncensored mimo-v2.6-flash-uncensored | $1.00 | $3.00 | $0.399 | - |
DeepSeek V4.1 Flash Abliterated deepseek-v4.1-flash-abliterated | $2.10 | $2.10 | $0.36 | - |
GLM-5.3 Flash Code Uncensored glm-5.3-flash-code-uncensored | $12.00 | $12.00 | $12.00 | - |
Apex Flash 1 Abliterated glm-5.3-flash-apex-abliterated | $0.30 | $1.00 | $0.15 | - |
GPT OSS 120B Uncensored gpt-oss-120b-uncensored | $0.219 | $1.456 | $0.219 | - |
Kimi K2.6 Uncensored kimi-k2.6-uncensored | $2.34 | $14.68 | $0.585 | - |
MiniMax M3 Uncensored minimax-m3-uncensored | $1.50 | $8.00 | $0.375 | - |
Outrun Red Team Flash outrun-redteam-flash | $1.35 | $4.50 | $0.23145 | - |
Outrun Red Team Pro outrun-redteam-pro | $2.25 | $9.00 | $0.6375 | - |
Hermes 4 405B hermes-4-405b-uncensored | $1.80 | $7.20 | $1.80 | - |
Nemotron 3 Ultra 550B Uncensored nemotron-3-ultra-550b-a55b-uncensored | $1.6875 | $9.90 | $0.423 | - |
DeepSeek V4.1 Flash Abliterated Fast deepseek-v4.1-flash-abliterated-fast | $1.40 | $1.40 | $0.32 | $1.40 |
Image generation and editing
| Model | Tier | Per image |
|---|---|---|
Anime Image Uncensored anime-image-uncensored | - | $0.036 |
Chroma Uncensored chroma-uncensored | - | $0.006 |
Lustify SDXL Uncensored lustify-sdxl-uncensored | - | $0.018 |
Seedream 5.0 Lite Edit Uncensored seedream-5.0-lite-edit-uncensored | - | $0.0626 |
Vision Image Uncensored vision-image-uncensored | - | $0.006 |
Vision Pro Image Uncensored vision-pro-image-uncensored | - | $0.09 |
Qwen Image 2.1 Uncensored qwen-image-2.1-uncensored | 1K | $0.075 |
Qwen Image 2.1 Uncensored qwen-image-2.1-uncensored | 2K | $0.40 |
Video generation
| Model | Tier | Per second |
|---|---|---|
Wan 3.0 Video Uncensored wan-3.0-video-uncensored | 480p | $0.40 |
Wan 3.0 Video Uncensored wan-3.0-video-uncensored | 720p | $0.80 |
Wan 3.0 Video Uncensored wan-3.0-video-uncensored | 1080p | $1.60 |
Uncensored · 2
Alternative source; select its distinct model ID.
| Model | Input / 1M | Output / 1M | Cache read / 1M | Cache write / 1M |
|---|---|---|---|---|
GLM-5.3 Uncensored (2) glm-5.3-uncensored-2 | $0.3492 | $0.3492 | $0.099 | - |
GLM-5.3 Flash Uncensored (2) glm-5.3-flash-uncensored-2 | $0.168 | $0.168 | $0.0168 | - |
GLM-5.3 Abliterated (2) glm-5.3-abliterated-2 | $4.50 | $4.50 | $1.32 | - |
GLM-5.3 Flash Abliterated (2) glm-5.3-flash-abliterated-2 | $1.32 | $1.32 | $0.36 | - |
DeepSeek V4.1 Flash Abliterated (2) deepseek-v4.1-flash-abliterated-2 | $0.70 | $0.70 | $0.12 | $0.70 |
Uncensored · 3
Alternative source; select its distinct model ID.
| Model | Input / 1M | Output / 1M | Cache read / 1M | Cache write / 1M |
|---|---|---|---|---|
GLM-5.3 Uncensored (3) glm-5.3-uncensored-3 | $2.50 | $4.50 | $0.60 | - |
GLM-5.3 Flash Uncensored (3) glm-5.3-flash-uncensored-3 | $0.40 | $1.60 | $0.14 | - |
Inception
OpenAI-compatible: /v1/chat/completions.
| Model | Input / 1M | Output / 1M | Cache read / 1M |
|---|---|---|---|
Mercury 3 mercury-3 | $0.20 | $0.70 | $0.02 |