Models and AI services

Catalog

Compare capabilities, availability, and pricing for your next build.

Integration guide

Estimate your cost

Explore the cost of your next build.

Estimate text chat and coding. Other model types are not included yet.

Start with an example or enter your own

Tokens measure text. Input includes your prompt, instructions and history. Output includes generated text and billable reasoning. Use an example if unsure.

YOUR ESTIMATEUSD
GPT-6 Astra
Estimated monthly cost
$54.00/ month

100 requests/day × 30 days = 3,000 requests/month

Per request
$0.018
Input / month
$13.50
Output / month
$40.50

Pay as you go · Published discounts included

Prompt cachingOff

Shares of total input, averaged across requests. The rest uses regular input pricing. Include cold starts, cache expiry and writes in your assumptions. Published rates do not guarantee cache hits; eligibility and setup vary by model. Uses the published write rate only; one-hour cache writes are excluded.

Compare models

Same token volumes and cache shares for each model. Missing required cache rates make an estimate unavailable. Actual output lengths and quality can differ.

Have a budget?

Approximately 555 requests at this request size.About 5.6 days at 100 requests/day.

Text only · Caching off · Media and tool fees excluded.
Agent tasks can make multiple requests. Final costs appear in Usage.

Explore the catalog82 models · 21 services · 15 providers

Chat & Reasoning53 models

Converse, write, analyze and reason with AI models.

From $0.0675 per 1M input tokens

Explain rate limiting in one sentence.

GPT-6 Astra

Rate limiting caps how many requests a client can send in a time window, so one busy caller can’t slow the service down for everyone else.

GPT-6 AstraClaude Fable 5.2Grok 4.7DeepSeek V4 Pro+48

Explore Chat & Reasoning
62 of 62 listings
Open gpt-6-astra details

gpt-6-astra

Frontier reasoning model for complex, long-context, and agentic workloads.

922K context
Pricing10% off
Base Input $9Base Output $45per 1M tokens
CacheReasoningTool calling+5
Route Auto
Open gpt-6.1-sol details

gpt-6.1-sol

Reasoning model for coding, professional work, and agentic workflows.

1.05M context
Pricing10% off
Base Input $1.8Base Output $9per 1M tokens
CacheReasoningTool calling+3
Route Auto10s41 tok/s
Open gpt-6.1-terra details

gpt-6.1-terra

Efficient reasoning for writing and focused analysis.

1.05M context
Pricing10% off
Base Input $0.9Base Output $4.5per 1M tokens
CacheReasoningStreaming
Route Auto
Open gpt-6-sol details

gpt-6-sol

Balanced reasoning model for coding and agentic workflows.

1.05M context
Pricing10% off
Base Input $1.8Base Output $9per 1M tokens
CacheReasoningTool calling+3
Route Auto
Open gpt-6-luna details

gpt-6-luna

Efficient reasoning model for focused, high-volume tasks.

1.05M context
Pricing10% off
Base Input $0.09Base Output $0.45per 1M tokens
CacheReasoningTool calling+3
Route Auto
Open gpt-5.6-sol details

gpt-5.6-sol

Flagship general-purpose model for complex reasoning, coding, and long-context work.

922K context
Pricing10% off
Base Input $3.6Base Output $18per 1M tokens
CacheReasoningTool calling+3
Route Auto
Open gpt-5.6-terra details

gpt-5.6-terra

Balanced general-purpose model for reasoning, coding, and production workloads.

922K context
Pricing10% off
Base Input $1.8Base Output $10.8per 1M tokens
CacheReasoningTool calling+3
Route Auto
Open gpt-5.6-luna details

gpt-5.6-luna

Efficient general-purpose model for fast, high-volume reasoning and chat.

922K context
Pricing10% off
Base Input $0.18Base Output $1.08per 1M tokens
CacheReasoningTool calling+3
Route Auto
Open gpt-5.5 details

gpt-5.5

High-capability general-purpose model for reasoning, chat, and developer workflows.

1.05M context
Pricing10% off
Base Input $4.5Base Output $27per 1M tokens
CacheReasoningTool calling+3
Route Auto
Open gpt-5-mini details

gpt-5-mini

Earlier small reasoning model for existing integrations and focused tasks.

400K context
Pricing10% off
Input $0.405Output $3.24per 1M tokens
CacheReasoningTool calling+3
Route Auto
Open gpt-5.3-codex details

gpt-5.3-codex

Code-focused reasoning model for agentic software-development workflows.

272K context
Pricing10% off
Input $1.575Output $12.6per 1M tokens
CacheReasoningTool calling+4
Route Auto
Open gpt-5.4-mini details

gpt-5.4-mini

Smaller, faster general-purpose model for everyday production tasks.

272K context
Pricing10% off
Input $0.675Output $4.05per 1M tokens
CacheReasoningTool calling+3
Route Auto
Open gpt-5.4-nano details

gpt-5.4-nano

Lightweight model for high-volume tasks where speed and unit cost matter.

272K context
Pricing10% off
Input $0.18Output $1.125per 1M tokens
CacheReasoningTool calling+3
Route Auto
Open gpt-5.4 details

gpt-5.4

Unavailable

High-capability model for reasoning, chat, and professional workflows.

1.05M context
Pricing10% off
Base Input $2.25Base Output $13.5per 1M tokens
CacheReasoningTool calling+3
No active route
Open gpt-5 details

gpt-5

Original GPT-5 reasoning model for existing integrations.

400K context
Pricing10% off
Input $2.25Output $18per 1M tokens
CacheReasoningTool calling+3
Route Auto
Open gpt-4o details

gpt-4o

Familiar multimodal model for existing OpenAI integrations.

128K context
Pricing10% off
Input $2.25Output $9per 1M tokens
CacheTool callingStructured output+2
Route Auto
Open gpt-4.1 details

gpt-4.1

Instruction-following non-reasoning model for existing integrations.

300K context
Pricing10% off
Input $1.8Output $7.2per 1M tokens
CacheTool callingStructured output+2
Route Auto
Open gpt-oss-120b details

gpt-oss-120b

GPT-OSS 120B: economical open-weight text reasoning and coding.

131K context
Pricing10% off
Input $0.135Output $0.54per 1M tokens
ReasoningStreaming
Route Auto
Open claude-fable-5-2 details

claude-fable-5-2

Claude Fable 5.2: reasoning for demanding technical work.

1M context
Pricing
Input $8Output $40per 1M tokens
CacheReasoningTool calling+1
Route Auto
Open claude-opus-5-5 details

claude-opus-5-5

High-capability Claude model for demanding reasoning, analysis, and agentic work.

1M context
Pricing
Input $4Output $20per 1M tokens
CacheReasoningTool calling+2
Route Auto6.8s69 tok/s
Open claude-sonnet-5-5 details

claude-sonnet-5-5

Claude model for reasoning, coding, and long-running agents.

1M context
Pricing
Input $2Output $10per 1M tokens
CacheReasoningTool calling+2
Route Auto
Open claude-haiku-5-5 details

claude-haiku-5-5

Fast reasoning for focused tasks, extraction, and coding.

1M context
Pricing
Base Input $0.1Base Output $0.5per 1M tokens
CacheReasoningTool calling+2
Route Auto
Open claude-fable-5-2-fast details

claude-fable-5-2-fast

Claude Fable 5.2 Fast: reasoning for demanding technical work.

1M context
Pricing
Input $16Output $80per 1M tokens
CacheReasoningTool calling+1
Route Auto
Open claude-opus-5-5-fast details

claude-opus-5-5-fast

Claude Opus 5.5 Fast: reasoning for demanding technical work.

1M context
Pricing
Input $8Output $40per 1M tokens
CacheReasoningTool calling+1
Route Auto
Open claude-fable-5-1 details

claude-fable-5-1

Claude model for long-context reasoning and general assistant workloads.

1M context
Pricing
Input $10Output $50per 1M tokens
CacheReasoningTool calling+2
Route Auto
Open claude-fable-5 details

claude-fable-5

Claude model for long-context reasoning and general assistant workloads.

1M context
Pricing
Input $10Output $50per 1M tokens
CacheReasoningTool calling+2
Route Auto
Open claude-opus-5 details

claude-opus-5

High-capability Claude model for demanding reasoning, analysis, and agentic work.

1M context
Pricing
Input $5Output $25per 1M tokens
CacheReasoningTool calling+2
Route Auto
Open claude-sonnet-5 details

claude-sonnet-5

Balanced Claude model for reasoning, coding, and production assistants.

1M context
Pricing
Input $2Output $10per 1M tokens
CacheReasoningTool calling+2
Route Auto
Open claude-opus-4-8 details

claude-opus-4-8

High-capability Claude model for demanding reasoning, analysis, and agentic work.

1M context
Pricing
Input $5Output $25per 1M tokens
CacheReasoningTool calling+2
Route Auto
Open claude-sonnet-4-6 details

claude-sonnet-4-6

Balanced Claude model for reasoning, coding, and production assistants.

1M context
Pricing
Input $3Output $15per 1M tokens
CacheReasoningTool calling+2
Route Auto
Open claude-haiku-4-5 details

claude-haiku-4-5

Unavailable

Fast, economical Claude model for responsive and high-volume tasks.

200K context
Pricing
Input $1Output $5per 1M tokens
CacheReasoningTool calling+2
Route Auto
Open grok-4.7 details

grok-4.7

Multimodal reasoning, coding, and tool-oriented workloads.

500K context
Pricing10% off
Base Input $1.8Base Output $5.4per 1M tokens
CacheReasoningTool calling+3
Route Auto
Open grok-4.6 details

grok-4.6

Flagship reasoning model for analysis, chat, and tool-oriented workloads.

200K context
Pricing10% off
Input $1.8Output $5.4per 1M tokens
CacheReasoningStreaming
Route Auto
Open grok-4.3 details

grok-4.3

General-purpose reasoning model for analysis, chat, and tool-oriented workloads.

200K context
Pricing10% off
Input $1.125Output $2.25per 1M tokens
CacheReasoningStreaming
Route Auto
Open grok-4-1-fast-reasoning details

grok-4-1-fast-reasoning

Coming soon

Low-cost fast model with extended reasoning for latency-sensitive workloads.

200K context
Pricing10% off
Input $0.18Output $0.45per 1M tokens
ReasoningStreaming
Route Auto
Open grok-4-1-fast-non-reasoning details

grok-4-1-fast-non-reasoning

Coming soon

Low-cost fast model for quick chat and tool-oriented workloads.

200K context
Pricing10% off
Input $0.18Output $0.45per 1M tokens
ReasoningStreaming
Route Auto
Open DeepSeek-V4-Pro details

DeepSeek-V4-Pro

High-capability reasoning model for complex analysis and production assistants.

1M context
Pricing10% off
Input $1.566Output $3.132per 1M tokens
CacheReasoningStreaming
Route Auto
Open DeepSeek-V4.1-Flash details

DeepSeek-V4.1-Flash

DeepSeek V4.1 Flash: efficient text reasoning and coding.

1.05M context
Pricing10% off
Input $0.405Output $1.62per 1M tokens
CacheReasoningStreaming
Route Auto
Open DeepSeek-V4-Flash details

DeepSeek-V4-Flash

Faster, lower-cost reasoning model for latency-sensitive workloads.

1M context
Pricing10% off
Input $0.171Output $0.459per 1M tokens
CacheReasoningStreaming
Route Auto
Open DeepSeek-V3.2 details

DeepSeek-V3.2

Coming soon

Efficient V3-line reasoning model for general analysis and chat.

128K context
Pricing10% off
Input $0.522Output $1.512per 1M tokens
ReasoningStreaming
Route Auto
Open DeepSeek-V3.2-Speciale details

DeepSeek-V3.2-Speciale

Coming soon

Specialized V3.2 reasoning variant for demanding analysis.

128K context
Pricing10% off
Input $0.522Output $1.512per 1M tokens
ReasoningStreaming
Route Auto
Open GLM-5.3 details

GLM-5.3

GLM 5.3: text reasoning, coding and long-horizon tasks.

1M context
Pricing10% off
Input $1.575Output $4.95per 1M tokens
CacheReasoningTool calling+2
Route Auto
Open GLM-5.3-Flash details

GLM-5.3-Flash

GLM 5.3 Flash: economical text chat and reasoning.

1M context
Pricing10% off
Input $0.1692Output $0.5625per 1M tokens
CacheReasoningTool calling+2
Route Auto
Open GLM-5.2-Fast details

GLM-5.2-Fast

Unavailable

GLM 5.2 Fast: text chat, coding and agent workflows.

1M context
Pricing10% off
Input $2.079Output $6.534per 1M tokens
CacheReasoningTool calling+2
Route Auto
Open Llama-4-Maverick details

Llama-4-Maverick

General-purpose mixture-of-experts model for chat and long-context workloads.

1M context
Pricing10% off
Input $0.225Output $0.9per 1M tokens
Streaming
Route Auto
Open Llama-4-Scout details

Llama-4-Scout

Efficient mixture-of-experts model for chat and long-context workloads.

1M context
Pricing
Input $0.16Output $0.64per 1M tokens
Streaming
Route Auto
Open Llama-3.3-70B-Instruct details

Llama-3.3-70B-Instruct

Dense multilingual instruct model for general chat and reasoning.

128K context
Pricing10% off
Input $0.639Output $0.639per 1M tokens
Streaming
Route Auto
Open model-router details

model-router

Selects a suitable available model for each request while preserving one Primex API surface.

Chat & Reasoning
Pricing
Billed at the selected model’s rate
StreamingRouting
Route Auto
Open Phi-4 details

Phi-4

Compact Phi text model for existing integrations.

16K context
Pricing10% off
Input $0.1125Output $0.45per 1M tokens
Streaming
Route Auto
Open Phi-4-mini-instruct details

Phi-4-mini-instruct

Economical Phi text model for focused tasks.

131K context
Pricing10% off
Input $0.0675Output $0.27per 1M tokens
Streaming
Route Auto
Open Mistral-Large-3 details

Mistral-Large-3

General-purpose Mistral model for reasoning, chat, and multilingual work.

256K context
Pricing10% off
Input $0.45Output $1.35per 1M tokens
Streaming
Route Auto
Open mistral-medium-3-5 details

mistral-medium-3-5

Capable mid-tier Mistral model for reasoning, chat, and multilingual work.

128K context
Pricing10% off
Input $1.35Output $6.75per 1M tokens
Streaming
Route Auto
Open Kimi-K3.1-Pro details

Kimi-K3.1-Pro

Long-context reasoning for coding, research and document workflows.

1M context
Pricing10% off
Input $2.07Output $10.35per 1M tokens
CacheReasoningStreaming
Route Auto
Open Kimi-K3 details

Kimi-K3

Kimi K3: long-context text reasoning and coding.

1.05M context
Pricing10% off
Input $2.97Output $14.85per 1M tokens
CacheReasoningStreaming
Route Auto
Open Kimi-K2.6 details

Kimi-K2.6

Long-context general-purpose model for reasoning and document-heavy conversations.

262K context
Pricing10% off
Input $0.855Output $3.6per 1M tokens
CacheStreaming
Route Auto
Open qwen3.5-122b-a10b details

qwen3.5-122b-a10b

Qwen3.5 122B A10B: open-weight text reasoning and coding.

256K context
Pricing10% off
Input $0.198Output $1.98per 1M tokens
ReasoningStreaming
Route Auto
Open qwen3-next-80b-a3b-instruct details

qwen3-next-80b-a3b-instruct

Qwen3-Next 80B A3B: economical instruction following and text generation.

33K context
Pricing10% off
Input $0.135Output $1.08per 1M tokens
Streaming
Route Auto
Open cohere-command-a details

cohere-command-a

Enterprise chat and reasoning model for retrieval-grounded workflows.

256K context
Pricing10% off
Input $2.25Output $9per 1M tokens
Streaming
Route Auto
Open Cohere-command-a-plus-05-2026 details

Cohere-command-a-plus-05-2026

Unavailable

Newer, efficient Cohere Command model for enterprise chat and reasoning.

256K context
Pricing10% off
Input $0.72Output $2.88per 1M tokens
Streaming
Route Auto
Open Nemotron-3-Ultra details

Nemotron-3-Ultra

Nemotron 3 Ultra: text reasoning and long-context agent workflows.

262K context
Pricing10% off
Input $0.594Output $2.376per 1M tokens
CacheReasoningTool calling+2
Route Auto
Open Nemotron-Lightning-3.5 details

Nemotron-Lightning-3.5

Coming soon

Nemotron Lightning 3.5: economical text chat and reasoning.

262K context
Pricing10% off
Input $0.054Output $0.198per 1M tokens
CacheReasoningTool calling+2
Route Auto
Open MiniMax-M3 details

MiniMax-M3

MiniMax M3: economical text chat and reasoning.

524K context
Pricing10% off
Input $0.297Output $1.188per 1M tokens
CacheReasoningTool calling+2
Route Auto

Prices per stated unit. Open an offering for its full pricing and requirements.