Openai models
23 models, from $0.05 per 1M input tokens.
Codex Auto Review
Codexopenai/codex-auto-review
Specialised for reviewing diffs and flagging defects rather than open-ended generation.
$0.5 / 1M in
GPT-4.1
gpt-4-1openai/gpt-4.1
OpenAI GPT-4.1 via RouterBase. OpenAI-compatible chat completions.
$2 / 1M in
GPT-4.1 nano
gpt-4-1-nanoopenai/gpt-4.1-nano
OpenAI GPT-4.1 nano via RouterBase. Cheapest 4.1 tier.
$0.1 / 1M in
GPT-4o
gpt-4oopenai/gpt-4o
OpenAI GPT-4o via RouterBase. Multimodal chat completions.
$2.5 / 1M in
GPT-4o mini
gpt-4o-miniopenai/gpt-4o-mini
OpenAI GPT-4o mini via RouterBase. Low-cost multimodal chat.
$0.15 / 1M in
GPT-5
gpt-5openai/gpt-5
OpenAI GPT-5 via RouterBase. OpenAI-compatible chat completions with prompt caching and tool calling.
$1.25 / 1M in
GPT-5.3 Codex Spark
Codexopenai/gpt-5.3-codex-spark
Code-oriented model for editing, refactoring and review loops. Same chat completions interface as the rest.
$0.5 / 1M in
GPT-5.4
gpt-5-4openai/gpt-5.4
OpenAI GPT-5.4 via RouterBase. OpenAI-compatible chat completions with prompt caching and tool calling.
$0.5 / 1M in
GPT-5.4 mini
gpt-5-4-miniopenai/gpt-5.4-mini
OpenAI GPT-5.4 mini via RouterBase. Cost-efficient GPT-5.4 tier; OpenAI-compatible chat completions with prompt caching and tool calling.
$0.05 / 1M in
GPT-5.5
gpt-5-5openai/gpt-5.5
OpenAI GPT-5.5 via RouterBase. Highest-capability GPT-5 chat model; prompt caching and tool calling.
$0.5 / 1M in
GPT-5.6 Luna
GPT-5.6openai/gpt-5.6-luna
GPT-5.6 variant tuned for conversational latency rather than peak reasoning depth.
$1.25 / 1M in
GPT-5.6 Sol
GPT-5.6openai/gpt-5.6-sol
Flagship tier of the GPT-5.6 line, tuned for hard multi-step problems where the extra cost is worth it.
$1.25 / 1M in
GPT-5.6 Terra
GPT-5.6openai/gpt-5.6-terra
GPT-5.6 variant balanced for long documents and sustained sessions.
$1.25 / 1M in
GPT-5 nano
gpt-5-nanoopenai/gpt-5-nano
OpenAI GPT-5 nano via RouterBase. Lowest-cost GPT-5 tier for high-volume, latency-sensitive tasks.
$0.05 / 1M in
OpenAI o3
o3openai/o3
OpenAI o3 reasoning model via RouterBase. Built for multi-step logic, math and analysis.
$2 / 1M in
OpenAI o4-mini
o4-miniopenai/o4-mini
OpenAI o4-mini reasoning model via RouterBase. Cost-efficient reasoning.
$1.1 / 1M in
Text Embedding 3 Large
text-embedding-3-largeopenai/text-embedding-3-large
OpenAI text-embedding-3-large via RouterBase. High-dimensional text embeddings (up to 3072 dims, truncatable via `dimensions`), 8191-token input.
$0.13 / 1M in
OpenAI GPT Image 2(Image Editing)
gpt-image-2openai/gpt-image-2-edit
OpenAI Gpt Image 2 Edit (image generate).
$0.0527 / generation
OpenAI GPT Image 2(Text to Image )
gpt-image-2openai/gpt-image-2-t2i
OpenAI Gpt Image 2 (image generate).
$0.0527 / generation
OpenAI Sora 2 (Image-to-Video)
sora-2openai/sora-2-i2v
OpenAI Sora 2 Image-to-Video. Preserves identity and lighting from a reference image.
$0.4 / generation
OpenAI Sora 2 Pro (Image-to-Video)
sora-2-proopenai/sora-2-pro-i2v
OpenAI Sora 2 Pro Image-to-Video. Pro tier supports 1080p output.
$1.2 / generation
OpenAI Sora 2 Pro(Text to Video)
sora-2-proopenai/sora-2-pro-t2v
OpenAI Sora 2 Pro Text-to-Video. Pro tier supports 1024x1792 / 1792x1024 sizes.
$1.2 / generation
OpenAI Sora 2(Text to Video)
sora-2openai/sora-2-t2v
OpenAI Sora 2 Text-to-Video. Synchronized audio, sharper realism, broader styles.
$0.4 / generation