browse by creator
OpenAI
OpenAI API and models: 48 models on Impossibl, including GPT-6.1 Terra, GPT-6 Luna Decisions, and GPT-6.1 Sol. Compare pricing per million tokens, context windows, and capabilities between different OpenAI models.
models
48
modalities · in → out
takes text, image and audio in, gives text, image, embedding and typed answers out
latest release
GPT-6.1 TerraOct 26, 2026
- GPT-6.1 Terra
openai/gpt-6.1-terra
GPT-6.1 Terra is OpenAI's fast, efficient mid-tier model in the GPT-6.1 family, sitting beneath GPT-6.1 Sol.
OpenAIText generationimage input
- context
- 1.05mtokens
- input price
- $1.00/1m tokens
- output price
- $5.00/1m tokens
- released
- GPT-6 Luna Decisions
openai/gpt-6-luna-decisions
GPT-6 Luna Decisions is GPT-6 Luna served through OpenAI's Decisions API: it reads text or images against typed yes/no, choice, and score questions and returns probabilities and confidence instead of generated text.
OpenAIEvaluationimage input
- context
- 1.05mtokens
- input price
- $0.10/1m tokens
- output price
- $0.00free/1m tokens
- released
- GPT-6.1 Sol
openai/gpt-6.1-sol
GPT-6.1 Sol is OpenAI's near-flagship model, released a week after GPT-6 Sol and aimed at agentic coding, computer use and other demanding professional work.
OpenAIText generationimage input
- context
- 1.05mtokens
- input price
- $2.00/1m tokens
- output price
- $10.00/1m tokens
- released
- GPT-6 Luna
openai/gpt-6-luna
GPT-6 Luna is the small, cost-efficient tier of OpenAI's GPT-6 family, sitting below GPT-6 Sol and GPT-6 Astra.
OpenAIText generationimage input
- context
- 1.05mtokens
- input price
- $0.10/1m tokens
- output price
- $0.50/1m tokens
- released
- GPT-6 Sol
openai/gpt-6-sol
GPT-6 Sol is the cost-efficient high-end tier of OpenAI's GPT-6 family, sitting below the flagship GPT-6 Astra and above the smaller GPT-6 Luna.
OpenAIText generationimage input
- context
- 1.05mtokens
- input price
- $2.00/1m tokens
- output price
- $10.00/1m tokens
- released
- GPT Image 2.5 Flare
openai/gpt-image-2.5-flare
GPT Image 2.5 Flare is OpenAI's fastest model for high-quality, everyday image generation and editing.
OpenAIImage generation
- context
- 32ktokens
- input price
- $5.00/1m tokens
- output price
- $30.00/1m tokens
- released
- GPT Image 2.5 Sunburst
openai/gpt-image-2.5-sunburst
GPT Image 2.5 Sunburst is OpenAI's most capable image generation and editing model, positioned for work where editing precision matters most.
OpenAIImage generation
- context
- 32ktokens
- input price
- $5.00/1m tokens
- output price
- $30.00/1m tokens
- released
- GPT-6 Astra
openai/gpt-6-astra
GPT-6 Astra is OpenAI's flagship model, built for the hardest end-to-end work across complex reasoning, coding, computer use, research, and document creation.
OpenAIText generationimage input
- context
- 1.05mtokens
- input price
- $10.00/1m tokens
- output price
- $50.00/1m tokens
- released
- GPT Transcribe
openai/gpt-transcribe
GPT Transcribe is OpenAI's speech-to-text model for transcribing completed audio files, streamed file transcripts, and committed turns in Realtime sessions.
OpenAISpeech to textaudio input
- context
- unknown
- input price
- $0.0045/minute
- output price
- unknown
- released
- GPT-5.6 Luna
openai/gpt-5.6-luna
GPT-5.6 Luna is the fast, cost-efficient tier of OpenAI's GPT-5.6 series, designed for high-volume chat, classification, and lightweight agentic tasks.
OpenAIText generationimage input
- context
- 1.05mtokens
- input price
- $0.20/1m tokens
- output price
- $1.20/1m tokens
- released
- GPT-5.6 Sol
openai/gpt-5.6-sol
GPT-5.6 Sol is the flagship tier of OpenAI's GPT-5.6 series, positioned for complex professional work such as multi-step reasoning, coding, and agentic workflows.
OpenAIText generationimage input
- context
- 1.05mtokens
- input price
- $4.00/1m tokens
- output price
- $20.00/1m tokens
- released
- GPT-5.6 Terra
openai/gpt-5.6-terra
GPT-5.6 Terra is the balanced tier of OpenAI's GPT-5.6 series, designed for workloads that weigh intelligence against cost in everyday coding, reasoning, and agentic tasks.
OpenAIText generationimage input
- context
- 1.05mtokens
- input price
- $2.00/1m tokens
- output price
- $12.00/1m tokens
- released
- GPT Chat Latest
openai/chat-latest
GPT Chat Latest is OpenAI's rolling alias that points to the latest Instant model currently used in ChatGPT, with text and image input and tool support.
OpenAIText generationimage input
- context
- 400ktokens
- input price
- $5.00/1m tokens
- output price
- $30.00/1m tokens
- released
- GPT-5.5
openai/gpt-5.5
GPT-5.5 is an OpenAI flagship model for the most complex professional work, positioned as a new class of intelligence for coding and knowledge work.
OpenAIText generationimage input
- context
- 1.05mtokens
- input price
- $5.00/1m tokens
- output price
- $30.00/1m tokens
- released
- GPT-5.5 Pro
openai/gpt-5.5-pro
GPT-5.5 Pro is the high-compute version of OpenAI's GPT-5.5, aimed at deep reasoning and accuracy on complex, high-stakes workloads.
OpenAIText generationimage input
- context
- 1.05mtokens
- input price
- $30.00/1m tokens
- output price
- $180.00/1m tokens
- released
- GPT Image 2
openai/gpt-image-2
GPT Image 2 is OpenAI's image generation model for fast, high-quality image creation and editing from text and image prompts.
OpenAIImage generation
- context
- 32ktokens
- input price
- $5.00/1m tokens
- output price
- $30.00/1m tokens
- released
- GPT-5.4 mini
openai/gpt-5.4-mini
GPT-5.4 mini is the faster, more efficient tier of OpenAI's GPT-5.4 family, designed for high-volume workloads.
OpenAIText generationimage input
- context
- 400ktokens
- input price
- $0.75/1m tokens
- output price
- $4.50/1m tokens
- released
- GPT-5.4 nano
openai/gpt-5.4-nano
GPT-5.4 nano is the lightest, most cost-efficient tier of OpenAI's GPT-5.4 family, optimised for speed-critical and high-volume tasks.
OpenAIText generationimage input
- context
- 400ktokens
- input price
- $0.20/1m tokens
- output price
- $1.25/1m tokens
- released
- GPT-5.4
openai/gpt-5.4
GPT-5.4 is an OpenAI flagship model for complex professional work, positioned as a more affordable option for coding and knowledge work.
OpenAIText generationimage input
- context
- 1.05mtokens
- input price
- $2.50/1m tokens
- output price
- $15.00/1m tokens
- released
- GPT-5.4 Pro
openai/gpt-5.4-pro
GPT-5.4 Pro is the high-compute version of OpenAI's GPT-5.4, built to tackle tough problems on complex, high-stakes tasks.
OpenAIText generationimage input
- context
- 1.05mtokens
- input price
- $30.00/1m tokens
- output price
- $180.00/1m tokens
- released
- GPT-5.3 Codex
openai/gpt-5.3-codex
GPT-5.3 Codex is OpenAI's agentic coding model, optimised for autonomous software engineering in Codex and similar environments.
OpenAIText generationimage input
- context
- 400ktokens
- input price
- $1.75/1m tokens
- output price
- $14.00/1m tokens
- released
- GPT-5.2 Codex
openai/gpt-5.2-codex
GPT-5.2 Codex is the software engineering version of OpenAI's GPT-5.2, an upgrade over GPT-5.1 Codex for coding workflows.
OpenAIText generationimage input
- context
- 400ktokens
- input price
- $1.75/1m tokens
- output price
- $14.00/1m tokens
- released
- GPT-5.2
openai/gpt-5.2
GPT-5.2 is a previous OpenAI flagship for complex professional work, following GPT-5.1 in the GPT-5 series.
OpenAIText generationimage input
- context
- 400ktokens
- input price
- $1.75/1m tokens
- output price
- $14.00/1m tokens
- released
- GPT-5.1 Codex
openai/gpt-5.1-codex
GPT-5.1 Codex is a specialised version of OpenAI's GPT-5.1 optimised for software engineering and coding workflows.
OpenAIText generationimage input
- context
- 400ktokens
- input price
- $1.25/1m tokens
- output price
- $10.00/1m tokens
- released
- GPT-5.1 Codex mini
openai/gpt-5.1-codex-mini
GPT-5.1 Codex mini is the smaller, faster version of OpenAI's GPT-5.1 Codex, aimed at the same agentic software engineering workflows.
OpenAIText generationimage input
- context
- 400ktokens
- input price
- $0.25/1m tokens
- output price
- $2.00/1m tokens
- released
- GPT-5.1
openai/gpt-5.1
GPT-5.1 is OpenAI's GPT-5 series flagship for coding and agentic tasks, with stronger reasoning, better instruction adherence, and a more natural style than GPT-5.
OpenAIText generationimage input
- context
- 400ktokens
- input price
- $1.25/1m tokens
- output price
- $10.00/1m tokens
- released
- GPT-5 Codex
openai/gpt-5-codex
GPT-5 Codex is a version of OpenAI's GPT-5 optimised for agentic coding in Codex or similar environments.
OpenAIText generationimage input
- context
- 400ktokens
- input price
- $1.25/1m tokens
- output price
- $10.00/1m tokens
- released
- GPT-5
openai/gpt-5
GPT-5 is OpenAI's frontier model of its generation, with major improvements in reasoning, code quality, and user experience over GPT-4.1.
OpenAIText generationimage input
- context
- 400ktokens
- input price
- $1.25/1m tokens
- output price
- $10.00/1m tokens
- released
- GPT-5 mini
openai/gpt-5-mini
GPT-5 mini is the compact tier of OpenAI's GPT-5 family, designed for lighter-weight reasoning tasks at lower latency and cost.
OpenAIText generationimage input
- context
- 400ktokens
- input price
- $0.25/1m tokens
- output price
- $2.00/1m tokens
- released
- GPT-5 nano
openai/gpt-5-nano
GPT-5 nano is the smallest and fastest tier of OpenAI's GPT-5 family, optimised for developer tools, rapid interactions, and ultra-low-latency environments.
OpenAIText generationimage input
- context
- 400ktokens
- input price
- $0.05/1m tokens
- output price
- $0.40/1m tokens
- released
- GPT-5 Pro
openai/gpt-5-pro
GPT-5 Pro is the high-compute version of OpenAI's GPT-5, aimed at the hardest problems in reasoning, coding, and analysis.
OpenAIText generationimage input
- context
- 400ktokens
- input price
- $15.00/1m tokens
- output price
- $120.00/1m tokens
- released
- GPT OSS 120B
openai/gpt-oss-120b
GPT OSS 120B is OpenAI's open-weight mixture-of-experts language model, released under Apache 2.0 for high-reasoning, agentic, and general-purpose production use.
OpenAIText generation
- context
- 128ktokens
- input price
- $0.35/1m tokens
- output price
- $0.75/1m tokens
- released
- GPT OSS 20B
openai/gpt-oss-20b
GPT OSS 20B is the smaller of OpenAI's open-weight gpt-oss models, released under Apache 2.0 for local, on-device, and low-latency use.
OpenAIText generation
- context
- 128ktokens
- input price
- $0.075/1m tokens
- output price
- $0.30/1m tokens
- released
- OpenAI o3
openai/o3
OpenAI o3 is a reasoning model in OpenAI's o-series, well-rounded across math, science, coding, and visual reasoning, and strong at technical writing and instruction following.
OpenAIText generationimage input
- context
- 200ktokens
- input price
- $2.00/1m tokens
- output price
- $8.00/1m tokens
- released
- OpenAI o4-mini
openai/o4-mini
OpenAI o4-mini is a compact reasoning model in OpenAI's o-series, optimised for fast, cost-efficient performance.
OpenAIText generationimage input
- context
- 200ktokens
- input price
- $1.10/1m tokens
- output price
- $4.40/1m tokens
- released
- GPT-4.1
openai/gpt-4.1
GPT-4.1 is OpenAI's flagship of the GPT-4.1 series, optimised for advanced instruction following, real-world software engineering, and long-context reasoning.
OpenAIText generationimage input
- context
- 1mtokens
- input price
- $2.00/1m tokens
- output price
- $8.00/1m tokens
- released
- GPT-4.1 mini
openai/gpt-4.1-mini
GPT-4.1 mini is the mid-sized tier of OpenAI's GPT-4.1 series, delivering performance competitive with GPT-4o at substantially lower latency and cost.
OpenAIText generationimage input
- context
- 1mtokens
- input price
- $0.40/1m tokens
- output price
- $1.60/1m tokens
- released
- GPT-4.1 nano
openai/gpt-4.1-nano
GPT-4.1 nano is the fastest and cheapest tier of OpenAI's GPT-4.1 series, built for tasks that demand low latency.
OpenAIText generationimage input
- context
- 1mtokens
- input price
- $0.10/1m tokens
- output price
- $0.40/1m tokens
- released
- OpenAI o3-mini
openai/o3-mini
OpenAI o3-mini is the small, cost-efficient reasoning model in OpenAI's o-series, optimised for STEM tasks in science, mathematics, and coding.
OpenAIText generation
- context
- 200ktokens
- input price
- $1.10/1m tokens
- output price
- $4.40/1m tokens
- released
- OpenAI o1
openai/o1
OpenAI o1 is the first full model in OpenAI's o-series, trained with large-scale reinforcement learning to spend more time thinking before it responds.
OpenAIText generationimage input
- context
- 200ktokens
- input price
- $15.00/1m tokens
- output price
- $60.00/1m tokens
- released
- GPT-4o mini
openai/gpt-4o-mini
GPT-4o mini is OpenAI's small model of the GPT-4o generation, supporting text and image input for cost-efficient chat and everyday tasks.
OpenAIText generationimage input
- context
- 128ktokens
- input price
- $0.15/1m tokens
- output price
- $0.60/1m tokens
- released
- GPT-4o
openai/gpt-4o
GPT-4o is OpenAI's omni model of the GPT-4 generation, accepting text and image input with text output for general chat, analysis, and coding.
OpenAIText generationimage input
- context
- 128ktokens
- input price
- $2.50/1m tokens
- output price
- $10.00/1m tokens
- released
- GPT-4 Turbo
openai/gpt-4-turbo
GPT-4 Turbo is OpenAI's GPT-4 generation model with vision, an older flagship for chat, analysis, and coding over long inputs.
OpenAIText generationimage input
- context
- 128ktokens
- input price
- $10.00/1m tokens
- output price
- $30.00/1m tokens
- released
- Text Embedding 3 Large
openai/text-embedding-3-large
Text Embedding 3 Large is OpenAI's most capable embedding model, converting text into vectors for search, clustering, recommendations, anomaly detection, and classification.
OpenAIEmbeddings
- context
- 8.19ktokens
- input price
- $0.13/1m tokens
- output price
- $0.00free/1m tokens
- released
- Text Embedding 3 Small
openai/text-embedding-3-small
Text Embedding 3 Small is OpenAI's compact embedding model, the successor to the ada embedding model for search, clustering, recommendations, and classification.
OpenAIEmbeddings
- context
- 8.19ktokens
- input price
- $0.02/1m tokens
- output price
- $0.00free/1m tokens
- released
- GPT-3.5 Turbo
openai/gpt-3.5-turbo
GPT-3.5 Turbo is OpenAI's earlier fast chat model, able to understand and generate natural language and code.
OpenAIText generation
- context
- 16ktokens
- input price
- $0.50/1m tokens
- output price
- $1.50/1m tokens
- released
- Whisper Large V3
openai/whisper-large-v3
Whisper Large V3 is OpenAI's multilingual speech recognition model for turning audio recordings into text.
OpenAISpeech to textaudio input
- context
- unknown
- input price
- $0.00185/minute
- output price
- unknown
- released
- —
- Whisper Large V3 Turbo
openai/whisper-large-v3-turbo
Whisper Large V3 Turbo is an optimized version of OpenAI's Whisper model for fast multilingual transcription.
OpenAISpeech to textaudio input
- context
- unknown
- input price
- $0.00066667/minute
- output price
- unknown
- released
- —
compare OpenAI models
compare models with the same model type and billing unit. each comparison includes published api prices, context limits, and capabilities.
frequently asked questions
Which GPT models are available through Impossibl?
The directory lists 48 models from OpenAI available through the Impossibl API, including GPT-6.1 Terra, GPT-6 Luna Decisions, and GPT-6.1 Sol. Open each model page for its API identifier, capabilities, and current pricing.
How much do GPT models cost?
OpenAI model prices vary by model and usage. All rates below are published base API rates in USD. For token-priced models, published input rates start at $0.02 per million input tokens. Published output rates start at $0.00 per million output tokens. Input and output minima may refer to different models. For audio-duration models, published input rates start at $0.00066667 per minute of audio. Long-context tiers can change prices for the whole request; check each model's thresholds and rates. Individual model pages include published cache prices and billing units. Applicable fees and workspace-specific pricing can affect the amount paid.
What is the cheapest GPT model?
By published input rate, the cheapest GPT text generation model on Impossibl is GPT-5 nano (openai/gpt-5-nano) at $0.05 per million input tokens and $0.40 per million output tokens. Cheapest by input rate is not always cheapest for a workload; output-heavy or cached requests can favor another model.
Does Impossibl add a markup to OpenAI pricing?
No. Usage is charged at the provider's list price with 0% usage markup. Prepaid credit purchases include a 5% platform fee, and there is no subscription. The rates on this page are OpenAI's published base rates, and usage comes off your balance when the request finishes.
What context windows do GPT models support?
Among OpenAI models with a published limit on Impossibl, the largest context window is 1,050,000 tokens, listed for GPT-5.4, GPT-5.4 Pro, and GPT-5.5. Context limits vary by model and are separate from maximum output limits. Context windows are unpublished for 3 models.
What inputs and capabilities do GPT models support?
Available model types include embeddings, evaluation, image generation, speech to text, and text generation. Published input support includes audio, image, and text; support varies by model. Tool calling is published as unsupported for 1 model. Tool-calling support is unspecified for 47 models.
How do I use GPT models through an API?
Use the exact model identifier from the model page with the Impossibl API. For example, select openai/gpt-6.1-terra with /v1/chat/completions. Endpoint compatibility depends on the selected model. The API quickstart explains how to create an API key and send a request.