Choose from leading model providers, compare answers, or let Auto choose a Twelva configuration for your request. Research, reason, write and create in one place.
Four named configurations: Auto picks Weaver, Swift or Owl for each message. The underlying provider model is always identified and can differ by region.
Picks Swift, Weaver or Owl for each message
Websites & creative work · runs on Claude Sonnet 5.5 in the US; may differ by region
Fast answers · runs on DeepSeek V4.1 Flash in the US; may differ by region
Deep thinking · runs on GPT‑6.1 in the US; may differ by region
One prompt, two models
The same prompt, sent to two models. Read their original responses and decide which direction fits the work.
Write three homepage headlines for a fictional independent ceramics studio called STILL. Each headline must be 5–9 words. Tone: quiet, direct, contemporary. Do not invent product claims. Return only the three headlines.
Anthropic
anthropic/claude-sonnet-5Original response · English
Here are three headlines for STILL:
Made slowly, by hand, in one place.
Ceramics for the way you actually live.
Simple forms. Quiet studio. Made by STILL.The first headline adds slow production, handmaking and a single location—facts the brief never supplied. Its concrete direction needs a factual check before use.
OpenAI
openai/gpt-6-solOriginal response · English
Objects for the spaces we live in
A quieter way to make a mark
Clay, form, and room to pauseSpaces, a quieter mark and room to pause suggest a more open, emotional direction. Consider whether that atmosphere is specific enough for the studio’s audience.
Generated via fal.ai / OpenRouter, outside the Twelva workspace. Responses are shown in full, without edits.
openrouter/router/enterpriseStart with a curated category, then compare the specifications that matter to your task. These are starting points, not performance rankings.
Task choices filter the curated list. Image input uses the catalog’s capability field; it does not mean image generation.
Choose two or three from the directory. Your selection stays here when you change filters.
Provider USD rates, not workspace credits. A larger context window is not a quality score. Availability and actual costs are confirmed in your workspace.
0 / 3 selectedInput and output prices below are gateway-listed provider rates in USD per 1 million tokens. These are reference rates, not Twelva credit prices. Your chat shows an estimated credit cost before sending.
How credits work| Model | Context | Image input | Input / 1M | Output / 1M |
|---|---|---|---|---|
Qwen3-14B alibaba/qwen-3-14b | 41K | — | $0.12 | $0.24 |
Qwen3 235B A22B alibaba/qwen-3-235b | 262.1K | — | $0.22 | $0.88 |
Qwen3-30B-A3B alibaba/qwen-3-30b | 41K | — | $0.12 | $0.50 |
Qwen 3 32B alibaba/qwen-3-32b | 128K | — | $0.15 | $0.60 |
Qwen3 Coder 480B A35B Instruct alibaba/qwen3-coder | 262.1K | — | $0.22 | $1.80 |
Qwen 3 Coder 30B A3B Instruct alibaba/qwen3-coder-30b-a3b | 262.1K | — | $0.15 | $0.60 |
Qwen3 Coder Next alibaba/qwen3-coder-next | 256K | — | $0.50 | $1.20 |
Qwen 3 Max Thinking alibaba/qwen3-max-thinking | 256K | — | $1.20 | $6.00 |
Qwen3 Next 80B A3B Instruct alibaba/qwen3-next-80b-a3b-instruct | 262.1K | — | $0.15 | $1.20 |
Qwen3 Next 80B A3B Thinking alibaba/qwen3-next-80b-a3b-thinking | 262.1K | — | $0.15 | $1.20 |
Qwen3 VL 235B A22B Instruct alibaba/qwen3-vl-instruct | 262.1K | Supported | $0.20 | $0.88 |
Qwen 3.5 Flash alibaba/qwen3.5-flash | 1M | Supported | $0.10 | $0.40 |
Qwen 3.5 Plus alibaba/qwen3.5-plus | 1M | Supported | $0.40 | $2.40 |
Qwen 3.6 27B alibaba/qwen3.6-27b | 256K | Supported | $0.60 | $3.60 |
Qwen 3.6 Plus alibaba/qwen3.6-plus | 1M | Supported | $0.50 | $3.00 |
Qwen 3.7 Flash alibaba/qwen3.7-flash | 991K | Supported | $0.03 | $0.13 |
Qwen 3.7 Max alibaba/qwen3.7-max | 991K | — | $2.50 | $7.50 |
Qwen 3.7 Plus alibaba/qwen3.7-plus | 1M | Supported | $0.40 | $1.60 |
Qwen3.8 2.4T A95B alibaba/qwen3.8-2.4t-a95b | 262.1K | Supported | $2.00 | $6.00 |
Qwen 3.8 27B alibaba/qwen3.8-27bMore models | 1M | Supported | $0.50 | $3.00 |
Qwen 3.8 Flash alibaba/qwen3.8-flashFast & economical | 991K | Supported | $0.15 | $0.47 |
Qwen 3.8 Max alibaba/qwen3.8-maxMore models | 262.1K | Supported | $2.00 | $6.00 |
Qwen3.8 Max 0902 alibaba/qwen3.8-max-0902 | 991K | Supported | $2.00 | $6.00 |
Qwen 3.8 Max Prime alibaba/qwen3.8-max-primeRecommended | 1M | Supported | $4.00 | $12.00 |
Qwen 3.8 Omni Flash alibaba/qwen3.8-omni-flash | 1M | Supported | $0.15 | $0.47 |
| Model | Context | Image input | Input / 1M | Output / 1M |
|---|---|---|---|---|
Nova 2 Lite amazon/nova-2-liteFast & economical | 1M | Supported | $0.30 | $2.50 |
Nova Lite amazon/nova-lite | 300K | Supported | $0.06 | $0.24 |
Nova Micro amazon/nova-micro | 128K | — | $0.035 | $0.14 |
Nova Pro amazon/nova-proMore models | 300K | Supported | $0.80 | $3.20 |
| Model | Context | Image input | Input / 1M | Output / 1M |
|---|---|---|---|---|
Claude Fable 5 anthropic/claude-fable-5 | 1M | Supported | $10.00 | $50.00 |
Claude Fable 5 (Batch) anthropic/claude-fable-5-batch | 1M | Supported | $5.00 | $25.00 |
Claude Fable 5.1 anthropic/claude-fable-5.1 | 1M | Supported | $10.00 | $50.00 |
Claude Fable 5.1 (Batch) anthropic/claude-fable-5.1-batch | 1M | Supported | $5.00 | $25.00 |
Claude Haiku 4.5 anthropic/claude-haiku-4.5Fast & economical | 200K | Supported | $1.00 | $5.00 |
Claude Haiku 4.5 (Batch) anthropic/claude-haiku-4.5-batch | 200K | Supported | $0.50 | $2.50 |
Claude Haiku 5.5 anthropic/claude-haiku-5.5 | 1M | Supported | $0.10 | $0.50 |
Claude Haiku 5.5 (Batch) anthropic/claude-haiku-5.5-batch | 1M | Supported | $0.05 | $0.25 |
Claude Opus 4.5 anthropic/claude-opus-4.5 | 200K | Supported | $5.00 | $25.00 |
Claude Opus 4.5 (Batch) anthropic/claude-opus-4.5-batch | 200K | Supported | $2.50 | $12.50 |
Claude Opus 4.6 anthropic/claude-opus-4.6 | 1M | Supported | $5.00 | $25.00 |
Claude Opus 4.6 (Batch) anthropic/claude-opus-4.6-batch | 1M | Supported | $2.50 | $12.50 |
Claude Opus 4.7 anthropic/claude-opus-4.7 | 1M | Supported | $5.00 | $25.00 |
Claude Opus 4.7 (Batch) anthropic/claude-opus-4.7-batch | 1M | Supported | $2.50 | $12.50 |
Claude Opus 4.8 anthropic/claude-opus-4.8 | 1M | Supported | $5.00 | $25.00 |
Claude Opus 4.8 (Batch) anthropic/claude-opus-4.8-batch | 1M | Supported | $2.50 | $12.50 |
Claude Opus 4.8 (Fast) anthropic/claude-opus-4.8-fast | 1M | Supported | $10.00 | $50.00 |
Claude Opus 5 anthropic/claude-opus-5 | 1M | Supported | $5.00 | $25.00 |
Claude Opus 5 (Batch) anthropic/claude-opus-5-batch | 1M | Supported | $2.50 | $12.50 |
Claude Opus 5 (Fast) anthropic/claude-opus-5-fast | 1M | Supported | $10.00 | $50.00 |
Claude Opus 5.5 anthropic/claude-opus-5.5 | 1M | Supported | $4.00 | $20.00 |
Claude Opus 5.5 (Batch) anthropic/claude-opus-5.5-batch | 1M | Supported | $2.00 | $10.00 |
Claude Opus 5.5 (Fast) anthropic/claude-opus-5.5-fast | 1M | Supported | $8.00 | $40.00 |
Claude Sonnet 4.5 anthropic/claude-sonnet-4.5 | 1M | Supported | $3.00 | $15.00 |
Claude Sonnet 4.5 (Batch) anthropic/claude-sonnet-4.5-batch | 1M | Supported | $1.50 | $7.50 |
Claude Sonnet 4.6 anthropic/claude-sonnet-4.6 | 1M | Supported | $3.00 | $15.00 |
Claude Sonnet 4.6 (Batch) anthropic/claude-sonnet-4.6-batch | 1M | Supported | $1.50 | $7.50 |
Claude Sonnet 5 anthropic/claude-sonnet-5More models | 1M | Supported | $2.00 | $10.00 |
Claude Sonnet 5 (Batch) anthropic/claude-sonnet-5-batch | 1M | Supported | $1.00 | $5.00 |
Claude Sonnet 5.5 anthropic/claude-sonnet-5.5Recommended | 1M | Supported | $2.00 | $10.00 |
Claude Sonnet 5.5 (Batch) anthropic/claude-sonnet-5.5-batch | 1M | Supported | $1.00 | $5.00 |
| Model | Context | Image input | Input / 1M | Output / 1M |
|---|---|---|---|---|
Trinity Large Thinking arcee-ai/trinity-large-thinking | 262.1K | — | $0.25 | $0.80 |
| Model | Context | Image input | Input / 1M | Output / 1M |
|---|---|---|---|---|
Seed 1.6 bytedance/seed-1.6 | 256K | Supported | $0.25 | $2.00 |
Bytedance Seed 1.8 bytedance/seed-1.8 | 256K | Supported | $0.25 | $2.00 |
Seed 2.1 Turbo bytedance/seed-2.1-turboMore models | 262.1K | Supported | $0.50 | $2.50 |
| Model | Context | Image input | Input / 1M | Output / 1M |
|---|---|---|---|---|
Apex callstack/apex | 262.1K | Supported | $0.50 | $3.00 |
| Model | Context | Image input | Input / 1M | Output / 1M |
|---|---|---|---|---|
Command A cohere/command-a | 256K | — | $2.50 | $10.00 |
| Model | Context | Image input | Input / 1M | Output / 1M |
|---|---|---|---|---|
DeepSeek-R1 deepseek/deepseek-r1 | 128K | — | $1.35 | $5.40 |
DeepSeek V3.1 deepseek/deepseek-v3.1 | 163.8K | — | $0.25 | $0.95 |
DeepSeek V3.2 deepseek/deepseek-v3.2 | 128K | — | $0.62 | $1.85 |
DeepSeek V3.2 Thinking deepseek/deepseek-v3.2-thinkingReasoning | 128K | — | $0.62 | $1.85 |
DeepSeek V4 Flash deepseek/deepseek-v4-flash | 1M | — | $0.13 | $0.26 |
DeepSeek V4 Flash 0731 deepseek/deepseek-v4-flash-0731 | 1M | — | $0.076 | $0.153 |
DeepSeek V4 Flash Vision Exp deepseek/deepseek-v4-flash-vision-exp | 1M | Supported | $0.216 | $0.647 |
DeepSeek V4 Pro deepseek/deepseek-v4-proRecommended | 1M | — | $0.66 | $1.98 |
DeepSeek V4 Pro 0813 deepseek/deepseek-v4-pro-0813 | 1M | — | $0.66 | $1.98 |
DeepSeek V4.1 Flash deepseek/deepseek-v4.1-flashFast & economical | 1M | Supported | $0.075 | $0.30 |
DeepSeek V4.1 Flash 1017 deepseek/deepseek-v4.1-flash-1017 | 1M | Supported | $0.075 | $0.30 |
DeepSeek V4.1 Flash 1017 Fast deepseek/deepseek-v4.1-flash-1017-fast | 1M | Supported | $0.60 | $2.40 |
DeepSeek V4.1 Flash Fast deepseek/deepseek-v4.1-flash-fast | 1M | Supported | $0.60 | $2.40 |
| Model | Context | Image input | Input / 1M | Output / 1M |
|---|---|---|---|---|
Ember-1 fireworks/ember-1 | 1M | Supported | $3.00 | $15.00 |
| Model | Context | Image input | Input / 1M | Output / 1M |
|---|---|---|---|---|
Gemini 2.5 Flash google/gemini-2.5-flash | 1M | Supported | $0.30 | $2.50 |
Gemini 2.5 Flash (Batch) google/gemini-2.5-flash-batch | 1M | Supported | $0.15 | $1.25 |
Gemini 2.5 Flash Lite google/gemini-2.5-flash-lite | 1M | Supported | $0.10 | $0.40 |
Gemini 2.5 Flash Lite (Batch) google/gemini-2.5-flash-lite-batch | 1M | Supported | $0.05 | $0.20 |
Gemini 2.5 Pro google/gemini-2.5-pro | 1M | Supported | $1.25 | $10.00 |
Gemini 2.5 Pro (Batch) google/gemini-2.5-pro-batch | 1M | Supported | $0.625 | $5.00 |
Gemini 3 Flash google/gemini-3-flash | 1M | Supported | $0.50 | $3.00 |
Gemini 3 Flash (Batch) google/gemini-3-flash-batch | 1M | Supported | $0.25 | $1.50 |
Gemini 3.1 Flash Lite google/gemini-3.1-flash-lite | 1M | Supported | $0.25 | $1.50 |
Gemini 3.1 Flash Lite (Batch) google/gemini-3.1-flash-lite-batch | 1M | Supported | $0.125 | $0.75 |
Gemini 3.1 Pro Preview google/gemini-3.1-pro-preview | 1M | Supported | $2.00 | $12.00 |
Gemini 3.1 Pro Preview (Batch) google/gemini-3.1-pro-preview-batch | 1M | Supported | $1.00 | $6.00 |
Gemini 3.5 Flash google/gemini-3.5-flash | 1M | Supported | $1.50 | $9.00 |
Gemini 3.5 Flash (Batch) google/gemini-3.5-flash-batch | 1M | Supported | $0.75 | $4.50 |
Gemini 3.5 Flash Lite google/gemini-3.5-flash-liteFast & economical | 1M | Supported | $0.30 | $2.50 |
Gemini 3.5 Flash Lite (Batch) google/gemini-3.5-flash-lite-batch | 1M | Supported | $0.15 | $1.25 |
Gemini 3.6 Flash google/gemini-3.6-flash | 1M | Supported | $0.75 | $3.75 |
Gemini 3.6 Flash (Batch) google/gemini-3.6-flash-batch | 1M | Supported | $0.375 | $1.875 |
Gemini 3.7 Flash google/gemini-3.7-flashMore models | 1M | Supported | $0.75 | $3.75 |
Gemini 3.7 Flash (Batch) google/gemini-3.7-flash-batch | 1M | Supported | $0.375 | $1.875 |
Gemini 3.8 Flash google/gemini-3.8-flashRecommended | 1M | Supported | $0.75 | $3.75 |
Gemini 4 Argon google/gemini-4-argon | 1M | Supported | $2.00 | $10.00 |
Google Gemma 4 26B A4B google/gemma-4-26b-a4b-it | 262.1K | Supported | $0.15 | $0.60 |
Gemma 4 31B google/gemma-4-31b-itMore models | 262.1K | Supported | $0.14 | $0.40 |
| Model | Context | Image input | Input / 1M | Output / 1M |
|---|---|---|---|---|
Mercury 2 inception/mercury-2 | 128K | — | $0.25 | $0.75 |
Mercury 2.5 inception/mercury-2.5 | 260K | — | $0.04 | $0.15 |
Mercury 3 inception/mercury-3 | 1M | — | $0.10 | $0.35 |
Mercury Coder inception/mercury-coder-smallCoding | 32K | — | $0.25 | $1.00 |
| Model | Context | Image input | Input / 1M | Output / 1M |
|---|---|---|---|---|
Ling 3.0 Flash inclusionai/ling-3.0-flash | 256K | — | $0.021 | $0.063 |
Ling 3.0 Flash Fin inclusionai/ling-3.0-flash-fin | 256K | — | $0.075 | $0.22 |
Ling 3.0 Flash Sante inclusionai/ling-3.0-flash-sante | 256K | — | $0.075 | $0.22 |
Ling 3.0 Flash VL inclusionai/ling-3.0-flash-vl | 256K | Supported | $0.075 | $0.22 |
Ling 3.1 Flash inclusionai/ling-3.1-flash | 262.1K | — | $0.30 | $0.90 |
| Model | Context | Image input | Input / 1M | Output / 1M |
|---|---|---|---|---|
Interfaze Beta interfaze/interfaze-beta | 1M | Supported | $1.50 | $3.50 |
| Model | Context | Image input | Input / 1M | Output / 1M |
|---|---|---|---|---|
LFM2.5-24B-A2B liquid/lfm2.5-24b-a2b | 128K | — | $0.05 | $0.70 |
| Model | Context | Image input | Input / 1M | Output / 1M |
|---|---|---|---|---|
LongCat 2.5 Preview meituan/longcat-2.5-preview | 1M | Supported | $0.30 | $1.20 |
| Model | Context | Image input | Input / 1M | Output / 1M |
|---|---|---|---|---|
Llama 3.1 70B Instruct meta/llama-3.1-70b | 128K | — | $0.72 | $0.72 |
Llama 3.1 8B Instruct meta/llama-3.1-8b | 128K | — | $0.22 | $0.22 |
Llama 3.3 70B Instruct meta/llama-3.3-70b | 128K | — | $0.72 | $0.72 |
Llama 4 Maverick meta/llama-4-maverickMore models | 128K | Supported | $0.24 | $0.97 |
Llama 4 Scout 17B Instruct meta/llama-4-scout | 128K | Supported | $0.17 | $0.66 |
Muse Glimmer 30B meta/muse-glimmer-30b | 131.1K | Supported | $0.35 | $1.50 |
Muse Spark 1.1 meta/muse-spark-1.1 | 1M | Supported | $1.25 | $4.25 |
Muse Spark 1.2 meta/muse-spark-1.2 | 1M | Supported | $1.25 | $4.25 |
Muse Spark 1.2 Contributor meta/muse-spark-1.2-contributor | 1M | Supported | $0.10 | $0.20 |
Muse Spark 1.3 meta/muse-spark-1.3 | 1M | Supported | $1.25 | $4.25 |
Muse Spark 1.3 Contributor meta/muse-spark-1.3-contributor | 1M | Supported | $0.10 | $0.20 |
Muse Spark Open meta/muse-spark-open | 1M | Supported | $1.25 | $4.25 |
Muse Wonder meta/muse-wonder-1.0 | 1M | Supported | $4.00 | $20.00 |
| Model | Context | Image input | Input / 1M | Output / 1M |
|---|---|---|---|---|
MiniMax M2 minimax/minimax-m2 | 205K | — | $0.30 | $1.20 |
MiniMax M2.1 minimax/minimax-m2.1 | 204.8K | — | $0.30 | $1.20 |
MiniMax M2.1 Lightning minimax/minimax-m2.1-lightning | 204.8K | — | $0.30 | $2.40 |
MiniMax M2.5 minimax/minimax-m2.5 | 204.8K | — | $0.30 | $1.20 |
MiniMax M2.5 High Speed minimax/minimax-m2.5-highspeed | 204.8K | — | $0.60 | $2.40 |
MiniMax M2.7 minimax/minimax-m2.7 | 204.8K | — | $0.30 | $1.20 |
MiniMax M2.7 High Speed minimax/minimax-m2.7-highspeed | 204.8K | — | $0.60 | $2.40 |
MiniMax M3 minimax/minimax-m3More models | 512K | Supported | $0.30 | $1.20 |
MiniMax-M3.1-Flash minimax/minimax-m3.1-flash | 1M | Supported | $0.00 | $0.00 |
| Model | Context | Image input | Input / 1M | Output / 1M |
|---|---|---|---|---|
Codestral mistral/codestralCoding | 128K | — | $0.30 | $0.90 |
Ministral 14B mistral/ministral-14b | 262.1K | Supported | $0.20 | $0.20 |
Ministral 3B mistral/ministral-3b | 131.1K | Supported | $0.10 | $0.10 |
Ministral 8B mistral/ministral-8b | 262.1K | Supported | $0.15 | $0.15 |
Mistral Large 3 mistral/mistral-large-3More models | 262.1K | Supported | $0.50 | $1.50 |
Mistral Large 4 mistral/mistral-large-4 | 524.3K | Supported | $1.36 | $4.18 |
Mistral Medium 3.5 mistral/mistral-medium-3.5More models | 262.1K | Supported | $1.50 | $7.50 |
Mistral Nemo 12B mistral/mistral-nemo | 131.1K | — | $0.029 | $0.03 |
Mistral Small mistral/mistral-smallFast & economical | 262.1K | Supported | $0.15 | $0.60 |
| Model | Context | Image input | Input / 1M | Output / 1M |
|---|---|---|---|---|
Toast 1 mixedbread/toast-1 | 131K | — | $0.30 | $0.72 |
| Model | Context | Image input | Input / 1M | Output / 1M |
|---|---|---|---|---|
Kimi K2 Instruct moonshotai/kimi-k2 | 131.1K | — | $0.57 | $2.30 |
Kimi K2.5 moonshotai/kimi-k2.5 | 256K | Supported | $0.60 | $3.00 |
Kimi K2.6 moonshotai/kimi-k2.6 | 262K | Supported | $0.95 | $4.00 |
Kimi K2.7 Code moonshotai/kimi-k2.7-codeCoding | 256K | Supported | $0.95 | $4.00 |
Kimi K2.7 Code Highspeed moonshotai/kimi-k2.7-code-highspeedCoding | 262.1K | Supported | $1.90 | $8.00 |
Kimi K3 moonshotai/kimi-k3Recommended | 1M | Supported | $3.00 | $15.00 |
Kimi K3 Fast moonshotai/kimi-k3-fastFast & economical | 1M | Supported | $4.50 | $22.50 |
| Model | Context | Image input | Input / 1M | Output / 1M |
|---|---|---|---|---|
Nemotron 3 Nano 30B A3B nvidia/nemotron-3-nano-30b-a3b | 262.1K | — | $0.05 | $0.20 |
Nemotron 3 Super nvidia/nemotron-3-super-120b-a12bMore models | 256K | — | $0.15 | $0.65 |
Nemotron 3 Ultra nvidia/nemotron-3-ultra-550b-a55bReasoning | 1M | — | $0.60 | $2.40 |
Nemotron 3.5 Lightning nvidia/nemotron-3.5-lightningFast & economical | 262.1K | — | $0.05 | $0.20 |
Nemotron 3.5 Lightning Free nvidia/nemotron-3.5-lightning-free | 1M | — | $0.00 | $0.00 |
NVIDIA Nemotron 3.5 Super VL nvidia/nemotron-3.5-super-vl | 1M | Supported | $0.20 | $0.50 |
Nvidia Nemotron Nano 12B V2 VL nvidia/nemotron-nano-12b-v2-vl | 131.1K | Supported | $0.20 | $0.60 |
Nvidia Nemotron Nano 9B V2 nvidia/nemotron-nano-9b-v2 | 131.1K | — | $0.06 | $0.23 |
| Model | Context | Image input | Input / 1M | Output / 1M |
|---|---|---|---|---|
GPT-3.5 Turbo openai/gpt-3.5-turbo | 16.4K | — | $0.50 | $1.50 |
GPT-4 Turbo openai/gpt-4-turbo | 128K | Supported | $10.00 | $30.00 |
GPT-4.1 openai/gpt-4.1 | 1M | Supported | $2.00 | $8.00 |
GPT-4.1 (Batch) openai/gpt-4.1-batch | 1M | Supported | $1.00 | $4.00 |
GPT-4.1 (Fast) openai/gpt-4.1-fast | 1M | Supported | $3.50 | $14.00 |
GPT-4.1 mini openai/gpt-4.1-mini | 1M | Supported | $0.40 | $1.60 |
GPT-4.1 mini (Batch) openai/gpt-4.1-mini-batch | 1M | Supported | $0.20 | $0.80 |
GPT-4.1 mini (Fast) openai/gpt-4.1-mini-fast | 1M | Supported | $0.70 | $2.80 |
GPT-4.1 nano openai/gpt-4.1-nano | 1M | Supported | $0.10 | $0.40 |
GPT-4.1 nano (Batch) openai/gpt-4.1-nano-batch | 1M | Supported | $0.05 | $0.20 |
GPT-4.1 nano (Fast) openai/gpt-4.1-nano-fast | 1M | Supported | $0.20 | $0.80 |
GPT-4o openai/gpt-4o | 128K | Supported | $2.50 | $10.00 |
GPT-4o (Batch) openai/gpt-4o-batch | 128K | Supported | $1.25 | $5.00 |
GPT-4o (Fast) openai/gpt-4o-fast | 128K | Supported | $4.25 | $17.00 |
GPT-4o mini openai/gpt-4o-mini | 128K | Supported | $0.15 | $0.60 |
GPT-4o mini (Batch) openai/gpt-4o-mini-batch | 128K | Supported | $0.075 | $0.30 |
GPT-4o mini (Fast) openai/gpt-4o-mini-fast | 128K | Supported | $0.25 | $1.00 |
GPT-5 openai/gpt-5 | 400K | Supported | $1.25 | $10.00 |
GPT-5 (Batch) openai/gpt-5-batch | 400K | Supported | $0.625 | $5.00 |
GPT-5-Codex openai/gpt-5-codex | 400K | Supported | $1.25 | $10.00 |
GPT-5 (Fast) openai/gpt-5-fast | 400K | Supported | $2.50 | $20.00 |
GPT-5 mini openai/gpt-5-mini | 400K | Supported | $0.25 | $2.00 |
GPT-5 mini (Batch) openai/gpt-5-mini-batch | 400K | Supported | $0.125 | $1.00 |
GPT-5 mini (Fast) openai/gpt-5-mini-fast | 400K | Supported | $0.45 | $3.60 |
GPT-5 nano openai/gpt-5-nano | 400K | Supported | $0.05 | $0.40 |
GPT-5 nano (Batch) openai/gpt-5-nano-batch | 400K | Supported | $0.025 | $0.20 |
GPT-5 pro openai/gpt-5-pro | 400K | Supported | $15.00 | $120.00 |
GPT-5 pro (Batch) openai/gpt-5-pro-batch | 400K | Supported | $7.50 | $60.00 |
GPT-5.1-Codex openai/gpt-5.1-codex | 400K | Supported | $1.25 | $10.00 |
GPT 5.1 Codex Max openai/gpt-5.1-codex-max | 400K | Supported | $1.25 | $10.00 |
GPT 5.1 Codex Mini openai/gpt-5.1-codex-mini | 400K | Supported | $0.25 | $2.00 |
GPT 5.1 Thinking openai/gpt-5.1-thinking | 400K | Supported | $1.25 | $10.00 |
GPT 5.1 Thinking (Fast) openai/gpt-5.1-thinking-fast | 400K | Supported | $2.50 | $20.00 |
GPT 5.2 openai/gpt-5.2 | 400K | Supported | $1.75 | $14.00 |
GPT 5.2 (Batch) openai/gpt-5.2-batch | 400K | Supported | $0.875 | $7.00 |
GPT 5.2 Codex openai/gpt-5.2-codex | 400K | Supported | $1.75 | $14.00 |
GPT 5.2 (Fast) openai/gpt-5.2-fast | 400K | Supported | $3.50 | $28.00 |
GPT 5.2 openai/gpt-5.2-pro | 400K | Supported | $21.00 | $168.00 |
GPT 5.3 Codex openai/gpt-5.3-codex | 400K | Supported | $1.75 | $14.00 |
GPT 5.3 Codex (Fast) openai/gpt-5.3-codex-fast | 400K | Supported | $3.50 | $28.00 |
GPT 5.4 openai/gpt-5.4 | 1.1M | Supported | $2.50 | $15.00 |
GPT 5.4 (Batch) openai/gpt-5.4-batch | 1.1M | Supported | $1.25 | $7.50 |
GPT 5.4 (Fast) openai/gpt-5.4-fast | 1.1M | Supported | $5.00 | $30.00 |
GPT 5.4 Mini openai/gpt-5.4-mini | 400K | Supported | $0.75 | $4.50 |
GPT 5.4 Mini (Batch) openai/gpt-5.4-mini-batch | 400K | Supported | $0.375 | $2.25 |
GPT 5.4 Mini (Fast) openai/gpt-5.4-mini-fast | 400K | Supported | $1.50 | $9.00 |
GPT 5.4 Nano openai/gpt-5.4-nano | 400K | Supported | $0.20 | $1.25 |
GPT 5.4 Nano (Batch) openai/gpt-5.4-nano-batch | 400K | Supported | $0.10 | $0.625 |
GPT 5.4 Pro openai/gpt-5.4-pro | 1.1M | Supported | $30.00 | $180.00 |
GPT 5.5 openai/gpt-5.5 | 1M | Supported | $5.00 | $30.00 |
GPT 5.5 (Batch) openai/gpt-5.5-batch | 1M | Supported | $2.50 | $15.00 |
GPT 5.5 (Fast) openai/gpt-5.5-fast | 1M | Supported | $12.50 | $75.00 |
GPT 5.5 Pro openai/gpt-5.5-pro | 1M | Supported | $30.00 | $180.00 |
GPT 5.5 Pro (Batch) openai/gpt-5.5-pro-batch | 1M | Supported | $15.00 | $90.00 |
GPT 5.6 Luna openai/gpt-5.6-luna | 1.1M | Supported | $0.20 | $1.20 |
GPT 5.6 Luna (Batch) openai/gpt-5.6-luna-batch | 1.1M | Supported | $0.10 | $0.60 |
GPT 5.6 Luna (Fast) openai/gpt-5.6-luna-fast | 1.1M | Supported | $0.40 | $2.40 |
GPT 5.6 Sol openai/gpt-5.6-sol | 1.1M | Supported | $4.00 | $20.00 |
GPT 5.6 Sol (Batch) openai/gpt-5.6-sol-batch | 1.1M | Supported | $2.00 | $10.00 |
GPT 5.6 Sol (Fast) openai/gpt-5.6-sol-fast | 1.1M | Supported | $8.00 | $40.00 |
GPT 5.6 Terra openai/gpt-5.6-terra | 1.1M | Supported | $2.00 | $12.00 |
GPT 5.6 Terra (Batch) openai/gpt-5.6-terra-batch | 1.1M | Supported | $1.00 | $6.00 |
GPT 5.6 Terra (Fast) openai/gpt-5.6-terra-fast | 1.1M | Supported | $4.00 | $24.00 |
GPT-6 Astra openai/gpt-6-astra | 1.1M | Supported | $10.00 | $50.00 |
GPT-6 Astra (Batch) openai/gpt-6-astra-batch | 1.1M | Supported | $5.00 | $25.00 |
GPT-6 Astra (Fast) openai/gpt-6-astra-fast | 1.1M | Supported | $20.00 | $100.00 |
GPT‑6 Luna openai/gpt-6-lunaFast & economical | 1.1M | Supported | $0.10 | $0.50 |
GPT-6 Luna (Batch) openai/gpt-6-luna-batch | 1.1M | Supported | $0.05 | $0.25 |
GPT-6 Luna (Fast) openai/gpt-6-luna-fast | 1.1M | Supported | $0.20 | $1.00 |
GPT‑6 openai/gpt-6-solMore models | 1.1M | Supported | $2.00 | $10.00 |
GPT-6 Sol (Batch) openai/gpt-6-sol-batch | 1.1M | Supported | $1.00 | $5.00 |
GPT-6 Sol (Fast) openai/gpt-6-sol-fast | 1.1M | Supported | $4.00 | $20.00 |
GPT‑6.1 openai/gpt-6.1-solRecommended | 1.1M | Supported | $2.00 | $10.00 |
GPT-6.1 Sol (Batch) openai/gpt-6.1-sol-batch | 1.1M | Supported | $1.00 | $5.00 |
GPT‑6.1 Fast openai/gpt-6.1-sol-fastCoding | 1.1M | Supported | $4.00 | $20.00 |
GPT OSS 120B openai/gpt-oss-120b | 131.1K | — | $0.10 | $0.50 |
GPT OSS 20B openai/gpt-oss-20b | 131.1K | — | $0.03 | $0.14 |
GPT OSS Safeguard 120B openai/gpt-oss-safeguard-120b | 128K | — | $0.15 | $0.60 |
GPT OSS Safeguard 20B openai/gpt-oss-safeguard-20b | 128K | — | $0.07 | $0.20 |
o1 openai/o1 | 200K | Supported | $15.00 | $60.00 |
o3 openai/o3 | 200K | Supported | $2.00 | $8.00 |
o3 (Fast) openai/o3-fast | 200K | Supported | $3.50 | $14.00 |
o3-mini openai/o3-mini | 200K | — | $1.10 | $4.40 |
o3 Pro openai/o3-pro | 200K | Supported | $20.00 | $80.00 |
o4-mini openai/o4-mini | 200K | Supported | $1.10 | $4.40 |
o4-mini (Fast) openai/o4-mini-fast | 200K | Supported | $2.00 | $8.00 |
| Model | Context | Image input | Input / 1M | Output / 1M |
|---|---|---|---|---|
Laguna S 2.1 poolside/laguna-s-2.1Coding | 1M | — | $0.09 | $0.18 |
Laguna S 2.1 Free poolside/laguna-s-2.1-free | 256K | — | $0.00 | $0.00 |
| Model | Context | Image input | Input / 1M | Output / 1M |
|---|---|---|---|---|
Arrow 2 quiverai/arrow-2 | 131.1K | Supported | $4.00 | $20.00 |
Arrow 2 Telos quiverai/arrow-2-telos | 131.1K | Supported | $6.00 | $30.00 |
| Model | Context | Image input | Input / 1M | Output / 1M |
|---|---|---|---|---|
Beam 1.0 reflection/beam | 1M | — | $0.00 | $0.00 |
Beam 1.0 (Free) reflection/beam-free | 1M | — | $0.00 | $0.00 |
| Model | Context | Image input | Input / 1M | Output / 1M |
|---|---|---|---|---|
Fugu Max sakana/fugu-maxReasoning | 1M | Supported | $2.00 | $6.00 |
Fugu Ultra sakana/fugu-ultra | 1M | Supported | $5.00 | $30.00 |
Fugu Ultra v2 sakana/fugu-ultra-v2 | 1M | Supported | $5.00 | $30.00 |
Sakana Namazu sakana/namazu | 256K | Supported | $0.95 | $4.00 |
| Model | Context | Image input | Input / 1M | Output / 1M |
|---|---|---|---|---|
Glyph Cluster stealth/glyph-cluster | 256K | — | $0.00 | $0.00 |
| Model | Context | Image input | Input / 1M | Output / 1M |
|---|---|---|---|---|
Step 3.7 Flash stepfun/step-3.7-flash | 256K | Supported | $0.20 | $1.15 |
Step 5 Preview stepfun/step-5-preview | 1M | Supported | $1.00 | $2.70 |
| Model | Context | Image input | Input / 1M | Output / 1M |
|---|---|---|---|---|
Hy3 tencent/hy3 | 262.1K | — | $0.14 | $0.58 |
Hunyuan 4 tencent/hy4-previewMore models | 1M | — | $0.834 | $2.501 |
| Model | Context | Image input | Input / 1M | Output / 1M |
|---|---|---|---|---|
Inkling thinkingmachines/inkling | 256K | Supported | $1.00 | $4.05 |
Inkling Small thinkingmachines/inkling-small | 1M | Supported | $0.45 | $1.20 |
| Model | Context | Image input | Input / 1M | Output / 1M |
|---|---|---|---|---|
Grok 4.1 Fast Non-Reasoning spacexai/grok-4.1-fast-non-reasoning | 1M | Supported | $0.20 | $0.50 |
Grok 4.1 Fast Reasoning spacexai/grok-4.1-fast-reasoning | 1M | Supported | $0.20 | $0.50 |
Grok 4.20 Multi-Agent spacexai/grok-4.20-multi-agent | 2M | Supported | $1.25 | $2.50 |
Grok 4.20 Multi-Agent (Batch) spacexai/grok-4.20-multi-agent-batch | 2M | Supported | $1.00 | $2.00 |
Grok 4.20 Multi Agent Beta spacexai/grok-4.20-multi-agent-beta | 2M | Supported | $1.25 | $2.50 |
Grok 4.20 Non-Reasoning spacexai/grok-4.20-non-reasoning | 2M | Supported | $1.25 | $2.50 |
Grok 4.20 Non-Reasoning (Batch) spacexai/grok-4.20-non-reasoning-batch | 2M | Supported | $1.00 | $2.00 |
Grok 4.20 Beta Non-Reasoning spacexai/grok-4.20-non-reasoning-beta | 2M | Supported | $1.25 | $2.50 |
Grok 4.20 Reasoning spacexai/grok-4.20-reasoning | 2M | Supported | $1.25 | $2.50 |
Grok 4.20 Reasoning (Batch) spacexai/grok-4.20-reasoning-batch | 2M | Supported | $1.00 | $2.00 |
Grok 4.20 Reasoning spacexai/grok-4.20-reasoning-betaReasoning | 2M | Supported | $1.25 | $2.50 |
Grok 4.3 spacexai/grok-4.3 | 1M | Supported | $1.25 | $2.50 |
Grok 4.3 (Batch) spacexai/grok-4.3-batch | 1M | Supported | $1.00 | $2.00 |
Grok 4.5 spacexai/grok-4.5 | 500K | Supported | $2.00 | $6.00 |
Grok 4.6 spacexai/grok-4.6 | 500K | Supported | $2.00 | $6.00 |
Grok 4.7 spacexai/grok-4.7Recommended | 500K | Supported | $2.00 | $6.00 |
Grok Build spacexai/grok-build-0.1Coding | 256K | Supported | $1.00 | $2.00 |
| Model | Context | Image input | Input / 1M | Output / 1M |
|---|---|---|---|---|
MiMo M2.5 xiaomi/mimo-v2.5 | 1.1M | Supported | $0.14 | $0.28 |
MiMo V2.5 Pro xiaomi/mimo-v2.5-pro | 1.1M | — | $0.305 | $0.609 |
MiMo V2.6 Flash xiaomi/mimo-v2.6-flash | 1M | Supported | $0.14 | $0.28 |
MiMo V2.6 Pro xiaomi/mimo-v2.6-pro | 1M | Supported | $0.435 | $0.87 |
MiMo V2.6 Pro UltraSpeed xiaomi/mimo-v2.6-pro-ultraspeed | 1M | Supported | $4.35 | $8.70 |
| Model | Context | Image input | Input / 1M | Output / 1M |
|---|---|---|---|---|
GLM 4.5 zai/glm-4.5 | 128K | — | $0.60 | $2.20 |
GLM 4.5 Air zai/glm-4.5-air | 128K | — | $0.20 | $1.10 |
GLM 4.5V zai/glm-4.5v | 66K | Supported | $0.60 | $1.80 |
GLM 4.6 zai/glm-4.6 | 200K | — | $0.60 | $2.20 |
GLM 4.7 zai/glm-4.7 | 200K | — | $0.60 | $2.20 |
GLM 4.7 Flash zai/glm-4.7-flash | 200K | — | $0.07 | $0.40 |
GLM 4.7 FlashX zai/glm-4.7-flashx | 200K | — | $0.06 | $0.40 |
GLM 5 zai/glm-5 | 202.8K | — | $1.00 | $3.20 |
GLM 5 Turbo zai/glm-5-turbo | 202.8K | — | $1.20 | $4.00 |
GLM 5.1 zai/glm-5.1 | 202.8K | — | $1.40 | $4.40 |
GLM 5.2 zai/glm-5.2 | 1M | — | $0.80 | $2.55 |
GLM 5.2 Fast zai/glm-5.2-fast | 1M | — | $2.80 | $8.80 |
GLM 5.3 zai/glm-5.3 | 1M | — | $1.40 | $4.40 |
GLM 5.3 Fast zai/glm-5.3-fast | 1M | — | $2.10 | $6.60 |
GLM 5.3 Flash zai/glm-5.3-flash | 1M | Supported | $0.15 | $0.50 |
GLM 5.3 FlashX zai/glm-5.3-flashx | 1M | Supported | $0.37 | $1.25 |
GLM 5V Turbo zai/glm-5v-turbo | 200K | Supported | $1.20 | $4.00 |
Categories organize the curated shortlist; More includes other catalog models. Weaver, Swift and Owl are TwelveBirds configurations of provider models. Image input means a model accepts images in chat; generation uses separate creation tools.
Catalog specifications and rates can change. Model availability is checked by the studio; a directory listing does not guarantee access to every provider.
