Skip to main content
Source: OpenAI model docs · API pricing (GPT-5.6 Sol promo at least through Nov 21, 2026). Prices are Standard tier; Batch/Flex are 50%, Fast mode (service_tier: "fast") is 2x.

​
GPT-6 Series

gpt-6-astra

Reasoning · Speedopenai/gpt-6-astraOpenAI’s most capable model, built for the hardest end-to-end work: complex reasoning, agentic coding, computer use, research, and document creation. Successor to GPT-5.6 Sol. reasoning.effort accepts low, medium, high, xhigh, and max (API default low).
  • $10 / $50 per 1M tokens (input / output); cached input $1 / 1M; cache writes $12.50 / 1M
  • Prompts over 272K input tokens bill the full request at long-context rates: $20 / $75, cached $2, cache writes $25
  • Function tools require the Responses API (Timbal’s default). With TIMBAL_OPENAI_API=chat_completions, tool calls return 400 and reasoning_effort: "none" is rejected
  • 1.05M context
  • 128K max output
  • Text, Image input
  • Extended thinking
  • Web search
  • Knowledge cutoff Apr 30, 2026
GPT-6 Astra was released September 3, 2026 in a staged rollout. Verified reachable on a standard API key via both /v1/responses and /v1/chat/completions on September 5, 2026; if your org still gets model_not_found, the rollout hasn’t reached it yet.

​
How long-context and cache pricing is tracked

GPT-6 Astra, GPT-5.6 Sol/Terra/Luna, GPT-5.5, GPT-5.4 and GPT-5.4 Pro bill the entire request at long-context rates once the prompt exceeds 272K input tokens — including cache reads, cache writes, and output. (GPT-5.5 Pro’s model card publishes no long-context tier and no cached-input discount, so it is billed flat.) Timbal’s collectors decide the tier from the raw prompt size reported by OpenAI (cache hits included; exactly 272K is still short context) and emit distinct usage units so each tier can be priced separately: input_cache_write_tokens is split out only for models whose catalog entry has a cache_write_price (OpenAI bills prompt-cache writes at 1.25x the input rate); on any other model those tokens stay in input_text_tokens so they are still billed. Reasoning tokens are folded into output_text_tokens (they are billed as output). Astra responses served by Flex or Fast processing additionally use _flex or _fast (for example, output_text_tokens_long_context_fast) so the processing multiplier is preserved. Eval usage assertions treat all pricing tiers as the same underlying tokens. The per-model thresholds and tier rates live in python/timbal/models.yaml (cached_input_price, cache_write_price, long_context, service_tiers).

​
GPT-5 Series

gpt-5.5

Reasoning · Speedopenai/gpt-5.5OpenAI’s latest flagship for coding, knowledge work, and research—positioned above GPT-5.4 with a 1.05M-token API context (per OpenAI model table) and higher per-token pricing.
  • $5 / $30 per 1M tokens (input / output); cached input $0.50 / 1M
  • 1.05M context
  • 128K max output
  • Text, Image input
  • Extended thinking
  • Web search

gpt-5.5-pro

Reasoning · Speedopenai/gpt-5.5-proGPT-5.5 Pro tier for the hardest coding, agentic, and research workloads via the Responses API.
  • $30 / $180 per 1M tokens (input / output)
  • 1.05M context
  • Text, Image input
  • Extended thinking

gpt-5.5-2026-04-23

Reasoning · Speedopenai/gpt-5.5-2026-04-23Dated snapshot of GPT-5.5 for reproducible runs; same capabilities and pricing as the rolling gpt-5.5 slug.
  • $5 / $30 per 1M tokens (input / output); cached input $0.50 / 1M
  • 1.05M context
  • 128K max output
  • Text, Image input
  • Extended thinking

gpt-5.6-sol

Reasoning · Speedopenai/gpt-5.6-solGPT-5.6 flagship tier for the hardest coding, agentic, and long-horizon tasks. Supports programmatic tool calling and multi-agent flows in the Responses API.
  • $4 / $20 per 1M tokens (input / output; promo at least through Nov 21, 2026); cached input $0.40 / 1M
  • 1.05M context
  • 128K max output
  • Text, Image input
  • Extended thinking
  • Web search

gpt-5.6-terra

Reasoning · Speedopenai/gpt-5.6-terraGPT-5.6 balanced tier for everyday production work—competitive with GPT-5.5 at roughly half the cost of Sol.
  • $2 / $12 per 1M tokens (input / output); cached input $0.20 / 1M
  • 1.05M context
  • 128K max output
  • Text, Image input
  • Extended thinking
  • Web search

gpt-5.6-luna

Reasoning · Speedopenai/gpt-5.6-lunaGPT-5.6 fast, cost-efficient tier for high-volume, latency-sensitive, and budget-conscious workloads.
  • $0.20 / $1.20 per 1M tokens (input / output); cached input $0.02 / 1M
  • 1.05M context
  • 128K max output
  • Text, Image input
  • Extended thinking
  • Web search

gpt-5.4

Reasoning · Speedopenai/gpt-5.4OpenAI’s most capable and efficient frontier model for professional work, combining industry-leading coding, reasoning, and agentic workflows with native computer-use capabilities.
  • $2.50 / $15
  • 1.05M context
  • 128K max output
  • Text, Image input
  • Extended thinking
  • Web search
  • Knowledge cutoff Aug 2025

gpt-5.4-pro

Reasoning · Speedopenai/gpt-5.4-proGPT-5.4 Pro tier for maximum capability coding and agent workloads via the Responses API.
  • $30 / $180 per 1M tokens (input / output)
  • 1.05M context
  • Text, Image input
  • Extended thinking

gpt-5.4-mini

Reasoning · Speedopenai/gpt-5.4-miniOpenAI’s most capable small model, significantly improving over GPT-5 mini across coding, reasoning, multimodal understanding, and tool use while running more than 2x faster.
  • $0.75 / $4.50
  • 400K context
  • 128K max output
  • Text, Image input
  • Thinking
  • Web search
  • Knowledge cutoff Aug 2025

gpt-5.4-nano

Reasoning · Speedopenai/gpt-5.4-nanoThe smallest, cheapest version of GPT-5.4 for tasks where speed and cost matter most. Ideal for classification, data extraction, ranking, and coding subagents.
  • $0.20 / $1.25
  • 400K context
  • 128K max output
  • Text, Image input
  • Knowledge cutoff Aug 2025

gpt-5.2

Reasoning · Speedopenai/gpt-5.2The most capable model series for professional knowledge work, with significant improvements in general intelligence, long-context understanding, agentic tool-calling, and vision.
  • $1.75 / $14
  • 400K context
  • 128K max output
  • Text, Image input
  • Thinking
  • Web search
  • Knowledge cutoff Aug 2025

gpt-5.2-pro

Reasoning · Speedopenai/gpt-5.2-proA version of GPT-5.2 that uses more compute to think harder and provide consistently better answers for complex tasks.
  • $21 / $168
  • 400K context
  • 128K max output
  • Text, Image input
  • Thinking
  • Web search
  • Knowledge cutoff Aug 2025

gpt-5.1

Reasoning · Speedopenai/gpt-5.1Improves meaningfully on both intelligence and communication style; the first model to use adaptive reasoning to decide when to think before responding.
  • $1.25 / $10
  • 400K context
  • 128K max output
  • Text, Image input
  • Thinking
  • Web search
  • Knowledge cutoff Sep 2024

gpt-5.1-codex

Reasoning · Speedopenai/gpt-5.1-codexA faster, more intelligent agentic coding model designed for long-running, project-scale work with enhanced reasoning and token efficiency.
  • $1.25 / $10
  • 400K context
  • 128K max output
  • Text, Image input
  • Thinking
  • Web search
  • Knowledge cutoff Sep 2024

gpt-5

Reasoning · Speedopenai/gpt-5OpenAI’s unified AI system representing a significant leap in intelligence, with a smart efficient model for most questions and a deeper reasoning model for harder problems.
  • $1.25 / $10
  • 400K context
  • 128K max output
  • Text, Image, Audio, Video input
  • Thinking
  • Web search
  • Knowledge cutoff Sep 2024

gpt-5-mini

Reasoning · Speedopenai/gpt-5-miniA smaller, faster variant of GPT-5’s thinking model optimized for developer use, balancing strong reasoning with lower cost and latency.
  • $0.25 / $2
  • 400K context
  • 128K max output
  • Text, Image input
  • Web search
  • Knowledge cutoff May 2024

gpt-5-nano

Reasoning · Speedopenai/gpt-5-nanoThe smallest and fastest variant in the GPT-5 family, made for developers needing maximum speed at minimal cost.
  • $0.05 / $0.40
  • 400K context
  • 128K max output
  • Text, Image input
  • Knowledge cutoff May 2024

​
GPT-4 Series

gpt-4.1

Reasoning · Speedopenai/gpt-4.1Excels at instruction following and tool calling with broad knowledge, featuring a 1M token context window and low latency without a reasoning step.
  • $2 / $8
  • 1.05M context
  • 32K max output
  • Text, Image input
  • Web search
  • Knowledge cutoff Jun 2024

gpt-4.1-mini

Reasoning · Speedopenai/gpt-4.1-miniA significant leap in small model performance that matches or exceeds GPT-4o in intelligence evals while reducing latency by nearly half and cost by 83%.
  • $0.40 / $1.60
  • 1M context
  • 32K max output
  • Text, Image input
  • Web search
  • Knowledge cutoff Jun 2024

gpt-4.1-nano

Reasoning · Speedopenai/gpt-4.1-nanoOpenAI’s fastest and cheapest model with a 1M token context window, ideal for classification and autocompletion tasks.
  • $0.10 / $0.40
  • 1M context
  • 32K max output
  • Text, Image input
  • Web search
  • Knowledge cutoff Jun 2024

gpt-4o

Reasoning · Speedopenai/gpt-4oAn autoregressive omni model that accepts any combination of text, audio, image, and video inputs, trained end-to-end across modalities.
  • $2.50 / $10
  • 128K context
  • 16K max output
  • Text, Image, Audio input
  • Knowledge cutoff Jun 2024

gpt-4o-mini

Reasoning · Speedopenai/gpt-4o-miniA fast, affordable small model for focused tasks that accepts text and image inputs at a fraction of the cost of frontier models.
  • $0.15 / $0.60
  • 128K context
  • 16K max output
  • Text, Image input
  • Knowledge cutoff Oct 2023

​
o-Series (Reasoning)

o4-mini

Reasoning · Speedopenai/o4-miniA smaller reasoning model optimized for fast, cost-efficient reasoning with exceptional performance in math, coding, and visual tasks.
  • $1.10 / $4.40
  • 200K context
  • 100K max output
  • Text, Image input
  • Thinking
  • Web search
  • Knowledge cutoff Jun 2024

o4-mini-deep-research

Reasoning · Speedopenai/o4-mini-deep-researchDeep research variant of o4-mini designed for extended multi-step research tasks with mandatory search.
  • $2 / $8
  • 200K context
  • 100K max output
  • Text, Image input
  • Thinking
  • Web search (required)
  • Knowledge cutoff Jun 2024

o3

Reasoning · Speedopenai/o3OpenAI’s most powerful reasoning model that pushes the frontier across coding, math, science, and visual perception, ideal for complex queries requiring multi-faceted analysis.
  • $2 / $8
  • 200K context
  • 100K max output
  • Text, Image input
  • Thinking
  • Web search
  • Knowledge cutoff Jun 2024

o3-mini

Reasoning · Speedopenai/o3-miniThe most cost-efficient model in OpenAI’s reasoning series, delivering o1-level STEM performance with lower cost and faster speed.
  • $1.10 / $4.40
  • 200K context
  • 100K max output
  • Text input
  • Thinking
  • Knowledge cutoff Oct 2023

o3-pro

Reasoning · Speedopenai/o3-proA version of o3 designed to think longer and provide the most reliable, thoroughly reasoned responses for maximum performance on complex tasks.
  • $20 / $80
  • 200K context
  • 100K max output
  • Text, Image input
  • Thinking
  • Web search
  • Knowledge cutoff Jun 2024

o3-deep-research

Reasoning · Speedopenai/o3-deep-researchDeep research variant of o3 for extended multi-step research tasks with mandatory search and maximum reasoning depth.
  • $10 / $40
  • 200K context
  • 100K max output
  • Text, Image input
  • Thinking
  • Web search (required)
  • Knowledge cutoff Jun 2024

o1

Reasoning · Speedopenai/o1OpenAI’s first reasoning model, trained to think before answering by producing a long internal chain of thought, with strong performance in science, coding, and math.
  • $15 / $60
  • 200K context
  • 100K max output
  • Text, Image input
  • Thinking
  • Knowledge cutoff Oct 2023
Reasoning tokens are billed as output tokens on all o-series models.