Models & Pricing
Chat / Completions
Model
Rate
GPT-6 Astraopenai/gpt-6-astraOpenAI's most capable model for complex reasoning, coding and research — balanced thinking — click to see versions
Provider context 1.05M · Max output 128K tokens
See details $10.00 in / $50.00 out per 1M tokens
- Cached input:
- $1.00 per 1M tokens
- Cache write:
- $12.50 per 1M tokens
- Cached output:
- Not offered · standard output rate applies
GPT-6 Lunaopenai/gpt-6-lunaLow-cost GPT-6 model from OpenAI — click to see versions
Provider context 1.05M · Max output 128K tokens
See details $0.10 in / $0.50 out per 1M tokens
- Cached input:
- $0.01 per 1M tokens
- Cache write:
- No extra fee
- Cached output:
- Not offered · standard output rate applies
Claude Fable 5.1anthropic/claude-fable-5-1Claude Fable 5.1 with medium thinking (default) — click to see versions
Provider context 1M · Max output 128K tokens
See details $10.00 in / $50.00 out per 1M tokens
- Cached input:
- $0.25 per 1M tokens
- Cache write:
- $12.50 per 1M tokens
- Cached output:
- Not offered · standard output rate applies
Claude Opus 5.5anthropic/claude-opus-5-5Claude Opus 5.5 with medium thinking (default) — click to see versions
Provider context 1M · Max output 128K tokens
See details $4.00 in / $20.00 out per 1M tokens
- Cached input:
- $0.20 per 1M tokens
- Cache write:
- $5.00 per 1M tokens
- Cached output:
- Not offered · standard output rate applies
Claude Opus 5anthropic/claude-opus-5Claude Opus 5 with medium thinking (default) — click to see versions
Provider context 1M · Max output 128K tokens
See details $5.00 in / $25.00 out per 1M tokens
- Cached input:
- $0.50 per 1M tokens
- Cache write:
- $6.25 per 1M tokens
- Cached output:
- Not offered · standard output rate applies
GPT-5.6 Solopenai/gpt-5.6-solFlagship GPT-5.6 reasoning & agentic — click to see versions
Provider context 1.05M · Max output 128K tokens
See details $4.00 in / $20.00 out per 1M tokens
- Cached input:
- $0.40 per 1M tokens
- Cache write:
- No extra fee
- Cached output:
- Not offered · standard output rate applies
GPT-5.6 Terraopenai/gpt-5.6-terraBalanced everyday GPT-5.6 — click to see versions
Provider context 1.05M · Max output 128K tokens
See details $2.00 in / $12.00 out per 1M tokens
- Cached input:
- $0.20 per 1M tokens
- Cache write:
- No extra fee
- Cached output:
- Not offered · standard output rate applies
Claude Sonnet 5anthropic/claude-sonnet-5Claude Sonnet 5 with medium thinking (default) — click to see versions
Provider context 1M · Max output 128K tokens
See details $2.00 in / $10.00 out per 1M tokens
- Cached input:
- $0.20 per 1M tokens
- Cache write:
- $2.50 per 1M tokens
- Cached output:
- Not offered · standard output rate applies
GPT-5.6 Lunaopenai/gpt-5.6-lunaFast, low-cost GPT-5.6 — click to see versions
Provider context 1.05M · Max output 128K tokens
See details $0.20 in / $1.20 out per 1M tokens
- Cached input:
- $0.02 per 1M tokens
- Cache write:
- No extra fee
- Cached output:
- Not offered · standard output rate applies
Claude Haiku 4.5anthropic/claude-haiku-4-5Claude Haiku 4.5 with medium thinking (default) — click to see versions
Provider context 200K · Max output 64K tokens
See details $1.00 in / $5.00 out per 1M tokens
- Cached input:
- $0.10 per 1M tokens
- Cache write:
- $1.25 per 1M tokens
- Cached output:
- Not offered · standard output rate applies
Gemini 3.8 Flashgoogle/gemini-3.8-flashLatest-generation Gemini Flash model for fast coding, reasoning, and agentic workflows. — click to see versions
Provider context 1.05M · Max output 65.54K tokens
See details $0.75 in / $3.75 out per 1M tokens
- Cached input:
- $0.075 per 1M tokens
- Cache write:
- No extra fee
- Cached output:
- Not offered · standard output rate applies
Gemini 3.1 Progoogle/gemini-3.1-pro-previewNext-gen Gemini Pro reasoning
Provider context 1.05M · Max output 65.54K tokens
See details $2.00 in / $12.00 out per 1M tokens
- Cached input:
- $0.20 per 1M tokens
- Cache write:
- No extra fee
- Cached output:
- Not offered · standard output rate applies
Gemini 3.7 Flashgoogle/gemini-3.7-flashLatest Gemini Flash (default) — click to see versions
Provider context 1.05M · Max output 65.54K tokens
See details $0.75 in / $3.75 out per 1M tokens
- Cached input:
- $0.075 per 1M tokens
- Cache write:
- No extra fee
- Cached output:
- Not offered · standard output rate applies
Gemini 3.6 Flashgoogle/gemini-3.6-flashHigh-efficiency Gemini 3.6 — click to see versions
Provider context 1.05M · Max output 65.54K tokens
See details $0.75 in / $3.75 out per 1M tokens
- Cached input:
- $0.075 per 1M tokens
- Cache write:
- No extra fee
- Cached output:
- Not offered · standard output rate applies
Gemini 3.5 Flashgoogle/gemini-3.5-flashHigh-efficiency Gemini 3.5 — click to see versions
Provider context 1.05M · Max output 65.54K tokens
See details $1.50 in / $9.00 out per 1M tokens
- Cached input:
- $0.15 per 1M tokens
- Cache write:
- No extra fee
- Cached output:
- Not offered · standard output rate applies
GPT-5.5 Proopenai/gpt-5.5-proExtended-reasoning GPT-5.5 Pro — click to see versions
Provider context 1.05M · Max output 128K tokens
See details $30.00 in / $180.00 out per 1M tokens
- Cached input:
- $3.00 per 1M tokens
- Cache write:
- No extra fee
- Cached output:
- Not offered · standard output rate applies
GPT-5openai/gpt-5Powerful multimodal all-rounder — click to see versions
Provider context 400K · Max output 128K tokens
See details $1.25 in / $10.00 out per 1M tokens
- Cached input:
- $0.125 per 1M tokens
- Cache write:
- No extra fee
- Cached output:
- Not offered · standard output rate applies
GPT-5.4 Proopenai/gpt-5.4-proPremium GPT-5.4 deep reasoning — click to see versions
Provider context 1.05M · Max output 128K tokens
See details $30.00 in / $180.00 out per 1M tokens
- Cached input:
- $3.00 per 1M tokens
- Cache write:
- No extra fee
- Cached output:
- Not offered · standard output rate applies
GPT-5.4openai/gpt-5.4Affordable frontier model — click to see versions
Provider context 1.05M · Max output 128K tokens
See details $2.50 in / $15.00 out per 1M tokens
- Cached input:
- $0.25 per 1M tokens
- Cache write:
- No extra fee
- Cached output:
- Not offered · standard output rate applies
GPT-5.5openai/gpt-5.5Frontier coding & analysis — click to see versions
Provider context 1.05M · Max output 128K tokens
See details $5.00 in / $30.00 out per 1M tokens
- Cached input:
- $0.50 per 1M tokens
- Cache write:
- No extra fee
- Cached output:
- Not offered · standard output rate applies
GPT-5.4 Miniopenai/gpt-5.4-miniStrong mini for high volume — click to see versions
Provider context 400K · Max output 128K tokens
See details $0.75 in / $4.50 out per 1M tokens
- Cached input:
- $0.075 per 1M tokens
- Cache write:
- No extra fee
- Cached output:
- Not offered · standard output rate applies
GPT-5.4 Nanoopenai/gpt-5.4-nanoCheapest GPT-5.4 for simple tasks — click to see versions
Provider context 400K · Max output 128K tokens
See details $0.20 in / $1.25 out per 1M tokens
- Cached input:
- $0.02 per 1M tokens
- Cache write:
- No extra fee
- Cached output:
- Not offered · standard output rate applies
GPT-5.2openai/gpt-5.2Complex reasoning & problem solving — click to see versions
Provider context 400K · Max output 128K tokens
See details $1.75 in / $14.00 out per 1M tokens
- Cached input:
- $0.175 per 1M tokens
- Cache write:
- No extra fee
- Cached output:
- Not offered · standard output rate applies
GPT-5 Miniopenai/gpt-5-miniFast, affordable GPT-5 — click to see versions
Provider context 400K · Max output 128K tokens
See details $0.25 in / $2.00 out per 1M tokens
- Cached input:
- $0.025 per 1M tokens
- Cache write:
- No extra fee
- Cached output:
- Not offered · standard output rate applies
GPT-5 Nanoopenai/gpt-5-nanoUltra-cheap GPT-5 for simple tasks — click to see versions
Provider context 400K · Max output 128K tokens
See details $0.05 in / $0.40 out per 1M tokens
- Cached input:
- $0.005 per 1M tokens
- Cache write:
- No extra fee
- Cached output:
- Not offered · standard output rate applies
Gemini 2.5 Flashgoogle/gemini-2.5-flashBalanced Gemini 2.5
Provider context 1.05M · Max output 65.54K tokens
See details $0.30 in / $2.50 out per 1M tokens
- Cached input:
- $0.03 per 1M tokens
- Cache write:
- No extra fee
- Cached output:
- Not offered · standard output rate applies
Gemini 2.5 Flash Litegoogle/gemini-2.5-flash-liteCheapest Gemini 2.5
Provider context 1.05M · Max output 65.54K tokens
See details $0.10 in / $0.40 out per 1M tokens
- Cached input:
- $0.01 per 1M tokens
- Cache write:
- No extra fee
- Cached output:
- Not offered · standard output rate applies
Gemini 2.5 Progoogle/gemini-2.5-proStrong multimodal reasoning
Provider context 1.05M · Max output 65.54K tokens
See details $1.25 in / $10.00 out per 1M tokens
- Cached input:
- $0.125 per 1M tokens
- Cache write:
- No extra fee
- Cached output:
- Not offered · standard output rate applies
Gemini 3 Flashgoogle/gemini-3-flash-previewFast Gemini preview
Provider context 1.05M · Max output 65.54K tokens
See details $0.50 in / $3.00 out per 1M tokens
- Cached input:
- $0.05 per 1M tokens
- Cache write:
- No extra fee
- Cached output:
- Not offered · standard output rate applies
Gemini 3.1 Flash Litegoogle/gemini-3.1-flash-liteCost-efficient high volume — click to see versions
Provider context 1.05M · Max output 65.54K tokens
See details $0.25 in / $1.50 out per 1M tokens
- Cached input:
- $0.025 per 1M tokens
- Cache write:
- No extra fee
- Cached output:
- Not offered · standard output rate applies
ChatGPT Latestopenai/chat-latestLatest Instant model used in ChatGPT — natural conversation
See details $5.00 in / $30.00 out per 1M tokens
- Cached input:
- $0.50 per 1M tokens
- Cache write:
- No extra fee
- Cached output:
- Not offered · standard output rate applies
Gemini 4 Argongoogle/gemini-4-argonFrontier Gemini model for long-horizon coding, reasoning and enterprise knowledge work — 1M context, text/image/audio/video input — click to see versions
Provider context 1.05M · Max output 65.54K tokens
See details $2.00 in / $10.00 out per 1M tokens
- Cached input:
- $0.10 per 1M tokens
- Cache write:
- No extra fee
- Cached output:
- Not offered · standard output rate applies
GPT-6 Solopenai/gpt-6-solOpenAI's mid-tier GPT-6 model — strong reasoning at a lower price, balanced thinking — click to see versions
See details $2.00 in / $10.00 out per 1M tokens
- Cached input:
- $0.20 per 1M tokens
- Cache write:
- No extra fee
- Cached output:
- Not offered · standard output rate applies
GPT-6.1 Solopenai/gpt-6.1-solNear-Astra performance for complex coding and professional work — balanced thinking — click to see versions
Provider context 1.05M · Max output 128K tokens
See details $2.00 in / $10.00 out per 1M tokens
- Cached input:
- $0.10 per 1M tokens
- Cache write:
- $2.50 per 1M tokens
- Cached output:
- Not offered · standard output rate applies
Image generation
Model
Rate
Gemini 3 Pro Imagegoogle/gemini-3-pro-imageHighest-quality Gemini image — 1K output — click to see versions
See details $0.134 per image
- Cached input:
- Not applicable
- Cache write:
- Not applicable
- Cached output:
- Not offered · standard output rate applies
GPT Image 2openai/gpt-image-2Highest-quality OpenAI image gen — Low/Medium/High quality, billed by tokens
See details $5.00 text in / $30.00 image out per 1M tokens
- Cached input:
- Not applicable
- Cache write:
- Not applicable
- Cached output:
- Not offered · standard output rate applies
$0.039 per image
- Cached input:
- Not applicable
- Cache write:
- Not applicable
- Cached output:
- Not offered · standard output rate applies
Gemini 3.1 Flash Imagegoogle/gemini-3.1-flash-imageNano Banana 2 — fast HQ image, 1K output — click to see versions
See details $0.067 per image
- Cached input:
- Not applicable
- Cache write:
- Not applicable
- Cached output:
- Not offered · standard output rate applies
Gemini 3.1 Flash Lite Imagegoogle/gemini-3.1-flash-lite-imageNano Banana 2 Lite — cheapest, 1K only
See details $0.0336 per image
- Cached input:
- Not applicable
- Cache write:
- Not applicable
- Cached output:
- Not offered · standard output rate applies
GPT Image 1 Miniopenai/gpt-image-1-miniCost-efficient OpenAI image gen — billed by tokens (being retired upstream)
See details $2.00 text in / $8.00 image out per 1M tokens
- Cached input:
- Not applicable
- Cache write:
- Not applicable
- Cached output:
- Not offered · standard output rate applies
GPT Image 2.5 Sunburstopenai/gpt-image-2.5-sunburstQuality-first OpenAI image generation and editing — Low to Max quality, billed by tokens
See details $5.00 text in / $30.00 image out per 1M tokens
- Cached input:
- Not applicable
- Cache write:
- Not applicable
- Cached output:
- Not offered · standard output rate applies
GPT Image 2.5 Flareopenai/gpt-image-2.5-flareLatency-first OpenAI image generation and editing — Low to Max quality, billed by tokens
See details $5.00 text in / $30.00 image out per 1M tokens
- Cached input:
- Not applicable
- Cache write:
- Not applicable
- Cached output:
- Not offered · standard output rate applies
Video generation
Model
Rate
Gemini Omni 1.1 Flashgoogle/gemini-omni-1.1-flashFast low-cost video gen, edit & extend — 360p drafts to 4K
See details $0.10 per second
- Cached input:
- Not applicable
- Cache write:
- Not applicable
- Cached output:
- Not offered · standard output rate applies
$0.40 per second
- Cached input:
- Not applicable
- Cache write:
- Not applicable
- Cached output:
- Not offered · standard output rate applies
$0.05 per second
- Cached input:
- Not applicable
- Cache write:
- Not applicable
- Cached output:
- Not offered · standard output rate applies
Music generation
Model
Rate
Lyria 3 Clipgoogle/lyria-3-clip-preview30-second music clips, loops and previews — vocals or instrumentals, from text or an image
See details $0.04 per clip
- Cached input:
- Not applicable
- Cache write:
- Not applicable
- Cached output:
- Not offered · standard output rate applies
Lyria 3 Progoogle/lyria-3-pro-previewFull-length songs up to ~3 minutes with verses, choruses and timed lyrics
See details $0.08 per song
- Cached input:
- Not applicable
- Cache write:
- Not applicable
- Cached output:
- Not offered · standard output rate applies
Text-to-speech
Model
Rate
$0.034 per 1k chars
- Cached input:
- Not applicable
- Cache write:
- Not applicable
- Cached output:
- Not offered · standard output rate applies
$0.0171 per 1k chars
- Cached input:
- Not applicable
- Cache write:
- Not applicable
- Cached output:
- Not offered · standard output rate applies
$0.0171 per 1k chars
- Cached input:
- Not applicable
- Cache write:
- Not applicable
- Cached output:
- Not offered · standard output rate applies
$0.034 per 1k chars
- Cached input:
- Not applicable
- Cache write:
- Not applicable
- Cached output:
- Not offered · standard output rate applies
$0.0149 per 1k chars
- Cached input:
- Not applicable
- Cache write:
- Not applicable
- Cached output:
- Not offered · standard output rate applies
Speech-to-text
Model
Rate
Gemini 3.5 Transcribegoogle/gemini-3.5-transcribeAuto language detection across 85+ languages
See details $0.00494 per minute
- Cached input:
- Not applicable
- Cache write:
- Not applicable
- Cached output:
- Not offered · standard output rate applies
$0.006 per minute
- Cached input:
- Not applicable
- Cache write:
- Not applicable
- Cached output:
- Not offered · standard output rate applies
GPT Transcribeopenai/gpt-transcribeLatest OpenAI speech-to-text — context, keyword and language hints for names & specialist words
See details $0.0045 per audio minute
- Cached input:
- Not applicable
- Cache write:
- Not applicable
- Cached output:
- Not offered · standard output rate applies
$0.00294 per minute
- Cached input:
- Not applicable
- Cache write:
- Not applicable
- Cached output:
- Not offered · standard output rate applies
Embeddings
Model
Rate
$0.15 per 1M tokens
- Cached input:
- Not applicable
- Cache write:
- Not applicable
- Cached output:
- Not offered · standard output rate applies
$0.20 per 1M tokens
- Cached input:
- Not applicable
- Cache write:
- Not applicable
- Cached output:
- Not offered · standard output rate applies
$0.13 per 1M tokens
- Cached input:
- Not applicable
- Cache write:
- Not applicable
- Cached output:
- Not offered · standard output rate applies
$0.02 per 1M tokens
- Cached input:
- Not applicable
- Cache write:
- Not applicable
- Cached output:
- Not offered · standard output rate applies
Typed decisions
Model
Rate
Jev Latesttypesafe/jev-latestTyped decisions with probabilities — classification, scoring and routing
See details $0.042 per 1M tokens
- Cached input:
- Not applicable
- Cache write:
- Not applicable
- Cached output:
- Not offered · standard output rate applies
Live voice (real-time calls)
Model
Rate
GPT Live 1openai/gpt-live-1Real-time two-way voice conversation — phone-call style, billed per second
$0.05 per minute · billed per second
See details $0.00083 per second
- Cached input:
- Not applicable
- Cache write:
- Not applicable
- Cached output:
- Not offered · standard output rate applies