Skip to content
AI IntegratorDocumentation
Open app
Documentation/Configuration
Configuration

Models

Choose a Claude, GPT, Gemini, or other model in Chat, and find out why a model is locked.

3 min read

Choose a model

In Chat, click the model name beside the composer. The list shows the models available to your account, grouped by family. You can filter by provider and search by name or full identifier. The info view shows the provider, a release label, context and output sizes, published prices when available, and capability icons.

Capabilities apply to a specific route in the catalog. The same model from a different provider can have different capabilities. Code doesn’t use this list. A Code task uses the models that the installed runtime reports. See Runtimes.

Read the catalog

Each table lists one model per row, grouped by provider. Find a model searches by name, identifier, and provider. All providers filters by provider. The count updates as you type, and Clear filters shows the full list again.

  • ZDR means zero data retention. An asterisk means that only some routes to that model offer it.
  • Access cost is the provider’s published rate in US dollars, not the AI Integrator subscription price. Token rates are per million tokens. Audio and character rates use their own units.
  • More rates shows cache and tier pricing. A blank rate shows Not published.
  • Default marks the app’s default for that type of model. You can choose a different model in Settings.

Rates are updated from the AI Gateway model catalog about once an hour.

Tool useReasoningImage inputFile / PDF inputPrompt cachingLive audioZero data retentionNo training

Privacy icons: solid = all routes; * = some routes; slashed = not offered; ? = not published. Other icons appear when the catalog advertises that capability. Focus or hover over an icon for its label.

Language models

These models write replies in Chat. They include Claude, GPT, Gemini, and the other families in the table. Your plan, the model picker, and your privacy filters determine which ones you can use.

96 of 96 models
ModelCapabilitiesAccess cost USD
Alibaba / Qwen
Qwen 3.6 Plusalibaba/qwen3.6-plus
Input$0.50 / 1M tokens
Output$3.00 / 1M tokens
Tiered
More rates
Cached input
$0.05 / 1M tokens
Cache write
$0.625 / 1M tokens
Input, 0–256,000 context tokens
$0.50 / 1M tokens
Input, 256,000+ context tokens
$2.00 / 1M tokens
Output, 0–256,000 context tokens
$3.00 / 1M tokens
Output, 256,000+ context tokens
$6.00 / 1M tokens
Cached input, 0–256,000 context tokens
$0.05 / 1M tokens
Cached input, 256,000+ context tokens
$0.20 / 1M tokens
Cache write, 0–256,000 context tokens
$0.625 / 1M tokens
Cache write, 256,000+ context tokens
$2.50 / 1M tokens
Qwen 3.7 Flashalibaba/qwen3.7-flash
Input$0.03 / 1M tokens
Output$0.13 / 1M tokens
Tiered
More rates
Cached input
$0.006 / 1M tokens
Cache write
$0.038 / 1M tokens
Input, 0–32,000 context tokens
$0.03 / 1M tokens
Input, 32,000–256,000 context tokens
$0.10 / 1M tokens
Input, 256,000+ context tokens
$0.20 / 1M tokens
Output, 0–32,000 context tokens
$0.13 / 1M tokens
Output, 32,000–256,000 context tokens
$0.40 / 1M tokens
Output, 256,000+ context tokens
$0.80 / 1M tokens
Cached input, 0–32,000 context tokens
$0.006 / 1M tokens
Cached input, 32,000–256,000 context tokens
$0.02 / 1M tokens
Cached input, 256,000+ context tokens
$0.04 / 1M tokens
Cache write, 0–32,000 context tokens
$0.038 / 1M tokens
Cache write, 32,000–256,000 context tokens
$0.125 / 1M tokens
Cache write, 256,000+ context tokens
$0.25 / 1M tokens
Qwen 3.7 Maxalibaba/qwen3.7-max
Input$2.50 / 1M tokens
Output$7.50 / 1M tokens
More rates
Cached input
$0.50 / 1M tokens
Cache write
$3.125 / 1M tokens
Qwen 3.7 Plusalibaba/qwen3.7-plus
Input$0.40 / 1M tokens
Output$1.60 / 1M tokens
Tiered
More rates
Cached input
$0.08 / 1M tokens
Cache write
$0.50 / 1M tokens
Input, 0–256,000 context tokens
$0.40 / 1M tokens
Input, 256,000+ context tokens
$1.20 / 1M tokens
Output, 0–256,000 context tokens
$1.60 / 1M tokens
Output, 256,000+ context tokens
$4.80 / 1M tokens
Cached input, 0–256,000 context tokens
$0.08 / 1M tokens
Cached input, 256,000+ context tokens
$0.24 / 1M tokens
Cache write, 0–256,000 context tokens
$0.50 / 1M tokens
Cache write, 256,000+ context tokens
$1.50 / 1M tokens
Qwen 3.8 Flashalibaba/qwen3.8-flash
Input$0.15 / 1M tokens
Output$0.47 / 1M tokens
More rates
Cached input
$0.016 / 1M tokens
Cache write
$0.20 / 1M tokens
Qwen 3.8 Maxalibaba/qwen3.8-max
Input$2.00 / 1M tokens
Output$6.00 / 1M tokens
More rates
Cached input
$0.25 / 1M tokens
Qwen 3.8 Omni Flashalibaba/qwen3.8-omni-flash
Input$0.15 / 1M tokens
Output$0.47 / 1M tokens
More rates
Cached input
$0.016 / 1M tokens
Qwen3.8 27Balibaba/qwen3.8-27b
Input$0.50 / 1M tokens
Output$3.00 / 1M tokens
Varies by provider
More rates
Cached input
$0.10 / 1M tokens
Cache write
$0.625 / 1M tokens
Qwen3.8 Max 0902alibaba/qwen3.8-max-0902
Input$2.00 / 1M tokens
Output$6.00 / 1M tokens
More rates
Cached input
$0.25 / 1M tokens
Cache write
$2.50 / 1M tokens
Anthropic
Claude Fable 5.1anthropic/claude-fable-5.1
Input$10.00 / 1M tokens
Output$50.00 / 1M tokens
More rates
Cached input
$0.25 / 1M tokens
Cache write
$12.50 / 1M tokens
Web search
$0.01 / request
Claude Haiku 4.5anthropic/claude-haiku-4.5
Input$1.00 / 1M tokens
Output$5.00 / 1M tokens
More rates
Cached input
$0.10 / 1M tokens
Cache write
$1.25 / 1M tokens
Web search
$0.01 / request
Claude Opus 4.5anthropic/claude-opus-4.5
Input$5.00 / 1M tokens
Output$25.00 / 1M tokens
More rates
Cached input
$0.50 / 1M tokens
Cache write
$6.25 / 1M tokens
Web search
$0.01 / request
Claude Opus 4.6anthropic/claude-opus-4.6
Input$5.00 / 1M tokens
Output$25.00 / 1M tokens
More rates
Cached input
$0.50 / 1M tokens
Cache write
$6.25 / 1M tokens
Web search
$0.01 / request
Claude Opus 4.7anthropic/claude-opus-4.7
Input$5.00 / 1M tokens
Output$25.00 / 1M tokens
More rates
Cached input
$0.50 / 1M tokens
Cache write
$6.25 / 1M tokens
Web search
$0.01 / request
Claude Opus 4.8anthropic/claude-opus-4.8
Input$5.00 / 1M tokens
Output$25.00 / 1M tokens
More rates
Cached input
$0.50 / 1M tokens
Cache write
$6.25 / 1M tokens
Web search
$0.01 / request
Fast input
$10.00 / 1M tokens
Fast output
$50.00 / 1M tokens
Fast cached input
$1.00 / 1M tokens
Fast cache write
$12.50 / 1M tokens
Claude Opus 5anthropic/claude-opus-5
Input$5.00 / 1M tokens
Output$25.00 / 1M tokens
More rates
Cached input
$0.50 / 1M tokens
Cache write
$6.25 / 1M tokens
Web search
$0.01 / request
Fast input
$10.00 / 1M tokens
Fast output
$50.00 / 1M tokens
Fast cached input
$1.00 / 1M tokens
Fast cache write
$12.50 / 1M tokens
Claude Opus 5.5anthropic/claude-opus-5.5
Input$4.00 / 1M tokens
Output$20.00 / 1M tokens
More rates
Cached input
$0.20 / 1M tokens
Cache write
$5.00 / 1M tokens
Web search
$0.01 / request
Fast input
$8.00 / 1M tokens
Fast output
$40.00 / 1M tokens
Fast cached input
$0.40 / 1M tokens
Fast cache write
$10.00 / 1M tokens
Claude Sonnet 4.5anthropic/claude-sonnet-4.5
Input$3.00 / 1M tokens
Output$15.00 / 1M tokens
Tiered
More rates
Cached input
$0.30 / 1M tokens
Cache write
$3.75 / 1M tokens
Web search
$0.01 / request
Input, 0–200,001 context tokens
$3.00 / 1M tokens
Input, 200,001+ context tokens
$6.00 / 1M tokens
Output, 0–200,001 context tokens
$15.00 / 1M tokens
Output, 200,001+ context tokens
$22.50 / 1M tokens
Cached input, 0–200,001 context tokens
$0.30 / 1M tokens
Cached input, 200,001+ context tokens
$0.60 / 1M tokens
Cache write, 0–200,001 context tokens
$3.75 / 1M tokens
Cache write, 200,001+ context tokens
$7.50 / 1M tokens
Claude Sonnet 4.6anthropic/claude-sonnet-4.6
Input$3.00 / 1M tokens
Output$15.00 / 1M tokens
More rates
Cached input
$0.30 / 1M tokens
Cache write
$3.75 / 1M tokens
Web search
$0.01 / request
Claude Sonnet 5Defaultanthropic/claude-sonnet-5
Input$2.00 / 1M tokens
Output$10.00 / 1M tokens
More rates
Cached input
$0.20 / 1M tokens
Cache write
$2.50 / 1M tokens
Web search
$0.01 / request
DeepSeek
DeepSeek V3.2deepseek/deepseek-v3.2
Input$0.62 / 1M tokens
Output$1.85 / 1M tokens
Varies by provider
DeepSeek V3.2 Thinkingdeepseek/deepseek-v3.2-thinking
Input$0.62 / 1M tokens
Output$1.85 / 1M tokens
Varies by provider
DeepSeek V4 Flashdeepseek/deepseek-v4-flash
Input$0.13 / 1M tokens
Output$0.26 / 1M tokens
Varies by provider
More rates
Cached input
$0.028 / 1M tokens
DeepSeek V4 Flash 0731deepseek/deepseek-v4-flash-0731
Input$0.076 / 1M tokens
Output$0.153 / 1M tokens
Varies by provider
More rates
Cached input
$0.014 / 1M tokens
DeepSeek V4 Flash Vision Expdeepseek/deepseek-v4-flash-vision-exp
Input$0.2156 / 1M tokens
Output$0.6468 / 1M tokens
Varies by provider
More rates
Cached input
$0.0068 / 1M tokens
DeepSeek V4 Prodeepseek/deepseek-v4-pro
Input$0.66 / 1M tokens
Output$1.98 / 1M tokens
Varies by provider
More rates
Cached input
$0.022 / 1M tokens
DeepSeek V4 Pro 0813deepseek/deepseek-v4-pro-0813
Input$0.66 / 1M tokens
Output$1.98 / 1M tokens
Varies by provider
More rates
Cached input
$0.066 / 1M tokens
DeepSeek V4.1 Flashdeepseek/deepseek-v4.1-flash
Input$0.30 / 1M tokens
Output$1.20 / 1M tokens
Varies by provider
More rates
Cached input
$0.007 / 1M tokens
Google
Gemini 2.5 Flashgoogle/gemini-2.5-flash
Input$0.30 / 1M tokens
Output$2.50 / 1M tokens
More rates
Cached input
$0.03 / 1M tokens
Web search
$0.035 / request
Gemini 2.5 Flash Litegoogle/gemini-2.5-flash-lite
Input$0.10 / 1M tokens
Output$0.40 / 1M tokens
More rates
Cached input
$0.01 / 1M tokens
Web search
$0.035 / request
Gemini 2.5 Progoogle/gemini-2.5-pro
Input$1.25 / 1M tokens
Output$10.00 / 1M tokens
Tiered
More rates
Cached input
$0.125 / 1M tokens
Web search
$0.035 / request
Input, 0–200,001 context tokens
$1.25 / 1M tokens
Input, 200,001+ context tokens
$2.50 / 1M tokens
Output, 0–200,001 context tokens
$10.00 / 1M tokens
Output, 200,001+ context tokens
$15.00 / 1M tokens
Cached input, 0–200,001 context tokens
$0.125 / 1M tokens
Cached input, 200,001+ context tokens
$0.25 / 1M tokens
Gemini 3.1 Flash Litegoogle/gemini-3.1-flash-lite
Input$0.25 / 1M tokens
Output$1.50 / 1M tokens
More rates
Cached input
$0.03 / 1M tokens
Web search
$0.014 / request
Gemini 3.1 Pro Previewgoogle/gemini-3.1-pro-preview
Input$2.00 / 1M tokens
Output$12.00 / 1M tokens
Tiered
More rates
Cached input
$0.20 / 1M tokens
Web search
$0.014 / request
Input, 0–200,001 context tokens
$2.00 / 1M tokens
Input, 200,001+ context tokens
$4.00 / 1M tokens
Output, 0–200,001 context tokens
$12.00 / 1M tokens
Output, 200,001+ context tokens
$18.00 / 1M tokens
Cached input, 0–200,001 context tokens
$0.20 / 1M tokens
Cached input, 200,001+ context tokens
$0.40 / 1M tokens
Gemini 3.5 Flashgoogle/gemini-3.5-flash
Input$1.50 / 1M tokens
Output$9.00 / 1M tokens
More rates
Cached input
$0.15 / 1M tokens
Web search
$0.014 / request
Gemini 3.5 Flash Litegoogle/gemini-3.5-flash-lite
Input$0.30 / 1M tokens
Output$2.50 / 1M tokens
More rates
Cached input
$0.03 / 1M tokens
Web search
$0.014 / request
Gemini 3.6 Flashgoogle/gemini-3.6-flash
Input$0.75 / 1M tokens
Output$3.75 / 1M tokens
More rates
Cached input
$0.075 / 1M tokens
Web search
$0.014 / request
Gemini 3.7 Flashgoogle/gemini-3.7-flash
Input$0.75 / 1M tokens
Output$3.75 / 1M tokens
More rates
Cached input
$0.075 / 1M tokens
Web search
$0.014 / request
Gemini 3.8 Flashgoogle/gemini-3.8-flash
Input$0.75 / 1M tokens
Output$3.75 / 1M tokens
More rates
Cached input
$0.075 / 1M tokens
Web search
$0.014 / request
Meta
Muse Glimmer 30Bmeta/muse-glimmer-30b
Input$0.35 / 1M tokens
Output$1.50 / 1M tokens
More rates
Cached input
$0.04 / 1M tokens
Muse Spark 1.1meta/muse-spark-1.1
Input$1.25 / 1M tokens
Output$4.25 / 1M tokens
More rates
Cached input
$0.15 / 1M tokens
Muse Spark 1.2meta/muse-spark-1.2
Input$1.25 / 1M tokens
Output$4.25 / 1M tokens
More rates
Cached input
$0.15 / 1M tokens
Muse Spark 1.2 Contributormeta/muse-spark-1.2-contributor
Input$0.10 / 1M tokens
Output$0.20 / 1M tokens
More rates
Cached input
$0.002 / 1M tokens
Muse Spark 1.3meta/muse-spark-1.3
Input$1.25 / 1M tokens
Output$4.25 / 1M tokens
More rates
Cached input
$0.15 / 1M tokens
Muse Spark 1.3 Contributormeta/muse-spark-1.3-contributor
Input$0.10 / 1M tokens
Output$0.20 / 1M tokens
More rates
Cached input
$0.002 / 1M tokens
MiniMax
MiniMax M2.7minimax/minimax-m2.7
Input$0.30 / 1M tokens
Output$1.20 / 1M tokens
Varies by provider
More rates
Cached input
$0.06 / 1M tokens
Cache write
$0.375 / 1M tokens
Fast input
$0.60 / 1M tokens
Fast output
$2.40 / 1M tokens
Fast cached input
$0.06 / 1M tokens
Fast cache write
$0.375 / 1M tokens
MiniMax M3minimax/minimax-m3
Input$0.30 / 1M tokens
Output$1.20 / 1M tokens
Varies by provider
More rates
Cached input
$0.06 / 1M tokens
Mistral
devstral-2mistral/devstral-2Not currently listed by the gateway
Not published
devstral-small-2mistral/devstral-small-2Not currently listed by the gateway
Not published
Ministral 14Bmistral/ministral-14b
Input$0.20 / 1M tokens
Output$0.20 / 1M tokens
More rates
Cached input
$0.02 / 1M tokens
Mistral Large 3mistral/mistral-large-3
Input$0.50 / 1M tokens
Output$1.50 / 1M tokens
More rates
Cached input
$0.05 / 1M tokens
Mistral Medium Latestmistral/mistral-medium-3.5
Input$1.50 / 1M tokens
Output$7.50 / 1M tokens
More rates
Cached input
$0.15 / 1M tokens
Moonshot AI
Kimi K2.5moonshotai/kimi-k2.5
Input$0.60 / 1M tokens
Output$3.00 / 1M tokens
Kimi K2.6moonshotai/kimi-k2.6
Input$0.95 / 1M tokens
Output$4.00 / 1M tokens
Varies by provider
More rates
Cached input
$0.16 / 1M tokens
Kimi K2.7 Codemoonshotai/kimi-k2.7-code
Input$0.95 / 1M tokens
Output$4.00 / 1M tokens
More rates
Cached input
$0.19 / 1M tokens
Fast input
$1.90 / 1M tokens
Fast output
$8.00 / 1M tokens
Fast cached input
$0.38 / 1M tokens
Kimi K2.7 Code High Speedmoonshotai/kimi-k2.7-code-highspeed
Input$1.90 / 1M tokens
Output$8.00 / 1M tokens
More rates
Cached input
$0.38 / 1M tokens
Kimi K3moonshotai/kimi-k3
Input$3.00 / 1M tokens
Output$15.00 / 1M tokens
Varies by provider
More rates
Cached input
$0.30 / 1M tokens
Fast input
$4.50 / 1M tokens
Fast output
$22.50 / 1M tokens
Fast cached input
$0.45 / 1M tokens
NVIDIA
Nemotron 3 Ultranvidia/nemotron-3-ultra-550b-a55b
Input$0.60 / 1M tokens
Output$2.40 / 1M tokens
Varies by provider
More rates
Cached input
$0.12 / 1M tokens
Nemotron 3.5 Lightning 30Bnvidia/nemotron-3.5-lightning
Input$0.05 / 1M tokens
Output$0.20 / 1M tokens
Varies by provider
More rates
Cached input
$0.01 / 1M tokens
OpenAI
GPT 5.4openai/gpt-5.4
Input$2.50 / 1M tokens
Output$15.00 / 1M tokens
Tiered
More rates
Cached input
$0.25 / 1M tokens
Web search
$0.01 / request
Fast input
$5.00 / 1M tokens
Fast output
$30.00 / 1M tokens
Fast cached input
$0.50 / 1M tokens
Input, 0–272,000 context tokens
$2.50 / 1M tokens
Input, 272,000+ context tokens
$5.00 / 1M tokens
Output, 0–272,000 context tokens
$15.00 / 1M tokens
Output, 272,000+ context tokens
$22.50 / 1M tokens
Cached input, 0–272,000 context tokens
$0.25 / 1M tokens
Cached input, 272,000+ context tokens
$0.50 / 1M tokens
GPT 5.4 Miniopenai/gpt-5.4-mini
Input$0.75 / 1M tokens
Output$4.50 / 1M tokens
More rates
Cached input
$0.075 / 1M tokens
Web search
$0.01 / request
Fast input
$1.50 / 1M tokens
Fast output
$9.00 / 1M tokens
Fast cached input
$0.15 / 1M tokens
GPT 5.4 Nanoopenai/gpt-5.4-nano
Input$0.20 / 1M tokens
Output$1.25 / 1M tokens
More rates
Cached input
$0.02 / 1M tokens
Web search
$0.01 / request
GPT 5.5openai/gpt-5.5
Input$5.00 / 1M tokens
Output$30.00 / 1M tokens
Tiered · Varies by provider
More rates
Cached input
$0.50 / 1M tokens
Web search
$0.01 / request
Fast input
$12.50 / 1M tokens
Fast output
$75.00 / 1M tokens
Fast cached input
$1.25 / 1M tokens
Input, 0–272,000 context tokens
$5.00 / 1M tokens
Input, 272,000+ context tokens
$10.00 / 1M tokens
Output, 0–272,000 context tokens
$30.00 / 1M tokens
Output, 272,000+ context tokens
$45.00 / 1M tokens
Cached input, 0–272,000 context tokens
$0.50 / 1M tokens
Cached input, 272,000+ context tokens
$1.00 / 1M tokens
GPT 5.6 Lunaopenai/gpt-5.6-luna
Input$0.20 / 1M tokens
Output$1.20 / 1M tokens
Tiered
More rates
Cached input
$0.02 / 1M tokens
Cache write
$0.25 / 1M tokens
Web search
$0.01 / request
Fast input
$0.40 / 1M tokens
Fast output
$2.40 / 1M tokens
Fast cached input
$0.04 / 1M tokens
Fast cache write
$0.50 / 1M tokens
Input, 0–272,000 context tokens
$0.20 / 1M tokens
Input, 272,000+ context tokens
$0.40 / 1M tokens
Output, 0–272,000 context tokens
$1.20 / 1M tokens
Output, 272,000+ context tokens
$1.80 / 1M tokens
Cached input, 0–272,000 context tokens
$0.02 / 1M tokens
Cached input, 272,000+ context tokens
$0.04 / 1M tokens
Cache write, 0–272,000 context tokens
$0.25 / 1M tokens
Cache write, 272,000+ context tokens
$0.50 / 1M tokens
GPT 5.6 Solopenai/gpt-5.6-sol
Input$4.00 / 1M tokens
Output$20.00 / 1M tokens
Tiered · Varies by provider
More rates
Cached input
$0.40 / 1M tokens
Cache write
$5.00 / 1M tokens
Web search
$0.01 / request
Fast input
$8.00 / 1M tokens
Fast output
$40.00 / 1M tokens
Fast cached input
$0.80 / 1M tokens
Fast cache write
$10.00 / 1M tokens
Input, 0–272,000 context tokens
$4.00 / 1M tokens
Input, 272,000+ context tokens
$8.00 / 1M tokens
Output, 0–272,000 context tokens
$20.00 / 1M tokens
Output, 272,000+ context tokens
$30.00 / 1M tokens
Cached input, 0–272,000 context tokens
$0.40 / 1M tokens
Cached input, 272,000+ context tokens
$0.80 / 1M tokens
Cache write, 0–272,000 context tokens
$5.00 / 1M tokens
Cache write, 272,000+ context tokens
$10.00 / 1M tokens
GPT 5.6 Terraopenai/gpt-5.6-terra
Input$2.00 / 1M tokens
Output$12.00 / 1M tokens
Tiered
More rates
Cached input
$0.20 / 1M tokens
Cache write
$2.50 / 1M tokens
Web search
$0.01 / request
Fast input
$4.00 / 1M tokens
Fast output
$24.00 / 1M tokens
Fast cached input
$0.40 / 1M tokens
Fast cache write
$5.00 / 1M tokens
Input, 0–272,000 context tokens
$2.00 / 1M tokens
Input, 272,000+ context tokens
$4.00 / 1M tokens
Output, 0–272,000 context tokens
$12.00 / 1M tokens
Output, 272,000+ context tokens
$18.00 / 1M tokens
Cached input, 0–272,000 context tokens
$0.20 / 1M tokens
Cached input, 272,000+ context tokens
$0.40 / 1M tokens
Cache write, 0–272,000 context tokens
$2.50 / 1M tokens
Cache write, 272,000+ context tokens
$5.00 / 1M tokens
GPT OSS 120Bopenai/gpt-oss-120b
Input$0.10 / 1M tokens
Output$0.50 / 1M tokens
Varies by provider
More rates
Cached input
$0.10 / 1M tokens
GPT-4.1openai/gpt-4.1
Input$2.00 / 1M tokens
Output$8.00 / 1M tokens
More rates
Cached input
$0.50 / 1M tokens
Web search
$0.01 / request
Fast input
$3.50 / 1M tokens
Fast output
$14.00 / 1M tokens
Fast cached input
$0.875 / 1M tokens
GPT-4.1 miniopenai/gpt-4.1-mini
Input$0.40 / 1M tokens
Output$1.60 / 1M tokens
More rates
Cached input
$0.10 / 1M tokens
Web search
$0.01 / request
Fast input
$0.70 / 1M tokens
Fast output
$2.80 / 1M tokens
Fast cached input
$0.175 / 1M tokens
GPT-4.1 nanoopenai/gpt-4.1-nano
Input$0.10 / 1M tokens
Output$0.40 / 1M tokens
Varies by provider
More rates
Cached input
$0.025 / 1M tokens
Web search
$0.01 / request
Fast input
$0.20 / 1M tokens
Fast output
$0.80 / 1M tokens
Fast cached input
$0.05 / 1M tokens
GPT-4oopenai/gpt-4o
Input$2.50 / 1M tokens
Output$10.00 / 1M tokens
More rates
Cached input
$1.25 / 1M tokens
Web search
$0.01 / request
Fast input
$4.25 / 1M tokens
Fast output
$17.00 / 1M tokens
Fast cached input
$2.125 / 1M tokens
GPT-4o miniopenai/gpt-4o-mini
Input$0.15 / 1M tokens
Output$0.60 / 1M tokens
More rates
Cached input
$0.075 / 1M tokens
Web search
$0.01 / request
Fast input
$0.25 / 1M tokens
Fast output
$1.00 / 1M tokens
Fast cached input
$0.125 / 1M tokens
GPT-6 Astraopenai/gpt-6-astra
Input$10.00 / 1M tokens
Output$50.00 / 1M tokens
Tiered
More rates
Cached input
$1.00 / 1M tokens
Cache write
$12.50 / 1M tokens
Web search
$0.01 / request
Fast input
$20.00 / 1M tokens
Fast output
$100.00 / 1M tokens
Fast cached input
$2.00 / 1M tokens
Fast cache write
$25.00 / 1M tokens
Input, 0–272,001 context tokens
$10.00 / 1M tokens
Input, 272,001+ context tokens
$20.00 / 1M tokens
Output, 0–272,001 context tokens
$50.00 / 1M tokens
Output, 272,001+ context tokens
$75.00 / 1M tokens
Cached input, 0–272,001 context tokens
$1.00 / 1M tokens
Cached input, 272,001+ context tokens
$2.00 / 1M tokens
Cache write, 0–272,001 context tokens
$12.50 / 1M tokens
Cache write, 272,001+ context tokens
$25.00 / 1M tokens
GPT-6 Lunaopenai/gpt-6-luna
Input$0.10 / 1M tokens
Output$0.50 / 1M tokens
Tiered
More rates
Cached input
$0.01 / 1M tokens
Cache write
$0.125 / 1M tokens
Web search
$0.01 / request
Fast input
$0.20 / 1M tokens
Fast output
$1.00 / 1M tokens
Fast cached input
$0.02 / 1M tokens
Fast cache write
$0.25 / 1M tokens
Input, 0–272,001 context tokens
$0.10 / 1M tokens
Input, 272,001+ context tokens
$0.20 / 1M tokens
Output, 0–272,001 context tokens
$0.50 / 1M tokens
Output, 272,001+ context tokens
$0.75 / 1M tokens
Cached input, 0–272,001 context tokens
$0.01 / 1M tokens
Cached input, 272,001+ context tokens
$0.02 / 1M tokens
Cache write, 0–272,001 context tokens
$0.125 / 1M tokens
Cache write, 272,001+ context tokens
$0.25 / 1M tokens
GPT-6 Solopenai/gpt-6-sol
Input$2.00 / 1M tokens
Output$10.00 / 1M tokens
Tiered
More rates
Cached input
$0.20 / 1M tokens
Cache write
$2.50 / 1M tokens
Web search
$0.01 / request
Fast input
$4.00 / 1M tokens
Fast output
$20.00 / 1M tokens
Fast cached input
$0.40 / 1M tokens
Fast cache write
$5.00 / 1M tokens
Input, 0–272,001 context tokens
$2.00 / 1M tokens
Input, 272,001+ context tokens
$4.00 / 1M tokens
Output, 0–272,001 context tokens
$10.00 / 1M tokens
Output, 272,001+ context tokens
$15.00 / 1M tokens
Cached input, 0–272,001 context tokens
$0.20 / 1M tokens
Cached input, 272,001+ context tokens
$0.40 / 1M tokens
Cache write, 0–272,001 context tokens
$2.50 / 1M tokens
Cache write, 272,001+ context tokens
$5.00 / 1M tokens
o3openai/o3
Input$2.00 / 1M tokens
Output$8.00 / 1M tokens
More rates
Cached input
$0.50 / 1M tokens
Web search
$0.01 / request
Fast input
$3.50 / 1M tokens
Fast output
$14.00 / 1M tokens
Fast cached input
$0.875 / 1M tokens
o4-miniopenai/o4-mini
Input$1.10 / 1M tokens
Output$4.40 / 1M tokens
More rates
Cached input
$0.275 / 1M tokens
Web search
$0.01 / request
Fast input
$2.00 / 1M tokens
Fast output
$8.00 / 1M tokens
Fast cached input
$0.50 / 1M tokens
Thinking Machines
Inklingthinkingmachines/inkling
Input$1.00 / 1M tokens
Output$4.05 / 1M tokens
Varies by provider
More rates
Cached input
$0.17 / 1M tokens
Inkling Smallthinkingmachines/inkling-small
Input$0.45 / 1M tokens
Output$1.20 / 1M tokens
Varies by provider
More rates
Cached input
$0.10 / 1M tokens
xAI
Grok 4.1 Fast Non-Reasoningspacexai/grok-4.1-fast-non-reasoning
Input$0.20 / 1M tokens
Output$0.50 / 1M tokens
More rates
Cached input
$0.05 / 1M tokens
Grok 4.1 Fast Reasoningspacexai/grok-4.1-fast-reasoning
Input$0.20 / 1M tokens
Output$0.50 / 1M tokens
More rates
Cached input
$0.05 / 1M tokens
Grok 4.3spacexai/grok-4.3
Input$1.25 / 1M tokens
Output$2.50 / 1M tokens
Tiered
More rates
Cached input
$0.20 / 1M tokens
Web search
$0.005 / request
Input, 0–200,001 context tokens
$1.25 / 1M tokens
Input, 200,001+ context tokens
$2.50 / 1M tokens
Output, 0–200,001 context tokens
$2.50 / 1M tokens
Output, 200,001+ context tokens
$5.00 / 1M tokens
Cached input, 0–200,001 context tokens
$0.20 / 1M tokens
Cached input, 200,001+ context tokens
$0.40 / 1M tokens
Grok 4.5spacexai/grok-4.5
Input$2.00 / 1M tokens
Output$6.00 / 1M tokens
Tiered
More rates
Cached input
$0.30 / 1M tokens
Web search
$0.005 / request
Input, 0–200,001 context tokens
$2.00 / 1M tokens
Input, 200,001+ context tokens
$4.00 / 1M tokens
Output, 0–200,001 context tokens
$6.00 / 1M tokens
Output, 200,001+ context tokens
$12.00 / 1M tokens
Cached input, 0–200,001 context tokens
$0.30 / 1M tokens
Cached input, 200,001+ context tokens
$0.60 / 1M tokens
Grok 4.6spacexai/grok-4.6
Input$2.00 / 1M tokens
Output$6.00 / 1M tokens
Tiered
More rates
Cached input
$0.50 / 1M tokens
Web search
$0.005 / request
Input, 0–200,001 context tokens
$2.00 / 1M tokens
Input, 200,001+ context tokens
$4.00 / 1M tokens
Output, 0–200,001 context tokens
$6.00 / 1M tokens
Output, 200,001+ context tokens
$12.00 / 1M tokens
Cached input, 0–200,001 context tokens
$0.50 / 1M tokens
Cached input, 200,001+ context tokens
$1.00 / 1M tokens
Grok 4.7spacexai/grok-4.7
Input$2.00 / 1M tokens
Output$6.00 / 1M tokens
Tiered
More rates
Cached input
$0.50 / 1M tokens
Web search
$0.005 / request
Input, 0–200,001 context tokens
$2.00 / 1M tokens
Input, 200,001+ context tokens
$4.00 / 1M tokens
Output, 0–200,001 context tokens
$6.00 / 1M tokens
Output, 200,001+ context tokens
$12.00 / 1M tokens
Cached input, 0–200,001 context tokens
$0.50 / 1M tokens
Cached input, 200,001+ context tokens
$1.00 / 1M tokens
Grok 4.20 Non-Reasoningspacexai/grok-4.20-non-reasoning
Input$1.25 / 1M tokens
Output$2.50 / 1M tokens
Tiered · Varies by provider
More rates
Cached input
$0.20 / 1M tokens
Web search
$0.005 / request
Input, 0–200,001 context tokens
$1.25 / 1M tokens
Input, 200,001+ context tokens
$2.50 / 1M tokens
Output, 0–200,001 context tokens
$2.50 / 1M tokens
Output, 200,001+ context tokens
$5.00 / 1M tokens
Cached input, 0–200,001 context tokens
$0.20 / 1M tokens
Cached input, 200,001+ context tokens
$0.40 / 1M tokens
Grok 4.20 Reasoningspacexai/grok-4.20-reasoning
Input$1.25 / 1M tokens
Output$2.50 / 1M tokens
Tiered · Varies by provider
More rates
Cached input
$0.20 / 1M tokens
Web search
$0.005 / request
Input, 0–200,001 context tokens
$1.25 / 1M tokens
Input, 200,001+ context tokens
$2.50 / 1M tokens
Output, 0–200,001 context tokens
$2.50 / 1M tokens
Output, 200,001+ context tokens
$5.00 / 1M tokens
Cached input, 0–200,001 context tokens
$0.20 / 1M tokens
Cached input, 200,001+ context tokens
$0.40 / 1M tokens
xiaomi
MiMo V2.6 Flashxiaomi/mimo-v2.6-flash
Input$0.14 / 1M tokens
Output$0.28 / 1M tokens
Varies by provider
More rates
Cached input
$0.0028 / 1M tokens
MiMo V2.6 Proxiaomi/mimo-v2.6-pro
Input$0.435 / 1M tokens
Output$0.87 / 1M tokens
Varies by provider
More rates
Cached input
$0.0036 / 1M tokens
MiMo V2.6 Pro UltraSpeedxiaomi/mimo-v2.6-pro-ultraspeed
Input$4.35 / 1M tokens
Output$8.70 / 1M tokens
More rates
Cached input
$0.036 / 1M tokens
Z.ai
GLM 4.7 Flashzai/glm-4.7-flash
Input$0.07 / 1M tokens
Output$0.40 / 1M tokens
GLM 5zai/glm-5
Input$1.00 / 1M tokens
Output$3.20 / 1M tokens
GLM 5.1zai/glm-5.1
Input$1.40 / 1M tokens
Output$4.40 / 1M tokens
Varies by provider
More rates
Cached input
$0.26 / 1M tokens
GLM 5.2zai/glm-5.2
Input$0.80 / 1M tokens
Output$2.55 / 1M tokens
Varies by provider
More rates
Cached input
$0.16 / 1M tokens
Fast input
$2.80 / 1M tokens
Fast output
$8.80 / 1M tokens
Fast cached input
$0.56 / 1M tokens
GLM 5.3zai/glm-5.3
Input$1.40 / 1M tokens
Output$4.40 / 1M tokens
Varies by provider
More rates
Cached input
$0.14 / 1M tokens
Fast input
$2.10 / 1M tokens
Fast output
$6.60 / 1M tokens
Fast cached input
$0.21 / 1M tokens
GLM 5.3 Flashzai/glm-5.3-flash
Input$0.15 / 1M tokens
Output$0.50 / 1M tokens
Varies by provider
More rates
Cached input
$0.03 / 1M tokens
GLM 5.3 FlashXzai/glm-5.3-flashx
Input$0.37 / 1M tokens
Output$1.25 / 1M tokens
More rates
Cached input
$0.075 / 1M tokens

Speech to text

Transcription models turn a recording into text. Choose one in Settings → Speech & Voice. A Live audio icon means the model offers streaming. The microphone in the composer does the recording. See Voice.

8 of 8 models
ModelCapabilitiesAccess cost USD
Fish Audio
Transcribe-1fish-audio/transcribe-1
Audio$0.006 / minute
Google
Gemini 3.5 Transcribegoogle/gemini-3.5-transcribe
Input$2.00 / 1M tokens
Audio input$2.00 / 1M tokens
Output$12.00 / 1M tokens
Gemini 3.5 Transcribe Livegoogle/gemini-3.5-transcribe-live
Audio$0.009 / minute
OpenAI
GPT-4o mini Transcribeopenai/gpt-4o-mini-transcribe
Input$1.25 / 1M tokens
Audio input$1.25 / 1M tokens
Output$5.00 / 1M tokens
GPT-4o Transcribeopenai/gpt-4o-transcribe
Input$2.50 / 1M tokens
Audio input$2.50 / 1M tokens
Output$10.00 / 1M tokens
gpt-realtime-whisperopenai/gpt-realtime-whisper
Audio$0.01704 / minute
Whisperopenai/whisper-1
Audio$0.006 / minute
xAI
Grok STTDefaultspacexai/grok-stt
Audio$0.00168 / minute

Text to speech

Read aloud uses these models. Choose a model, and a voice if the model offers named voices, in Settings → Speech & Voice. Character rates apply to the text that’s read aloud.

6 of 6 models
ModelCapabilitiesAccess cost USD
Fish Audio
S1fish-audio/s1
Text$15.00 / 1M characters
S2 Profish-audio/s2-pro
Text$15.00 / 1M characters
S2.1 Profish-audio/s2.1-pro
Text$15.00 / 1M characters
OpenAI
TTS-1Defaultopenai/tts-1
Text$15.00 / 1M characters
TTS-1 HDopenai/tts-1-hd
Text$30.00 / 1M characters
xAI
Grok TTSspacexai/grok-tts
Text$15.00 / 1M characters

Embeddings and rerankers

Embedding models power search across memory, earlier chats, and indexed documents. If you change the embedding model, existing entries may need to be indexed again. See Memory.

Rerankers reorder search results that were already retrieved. A model listed here isn’t used by every search.

9 of 9 models
ModelCapabilitiesAccess cost USD
Alibaba / Qwen
Qwen3 Embedding 4BDefaultalibaba/qwen3-embedding-4b
Input$0.02 / 1M tokens
Amazon
Titan Text Embeddings V2amazon/titan-embed-text-v2
Input$0.02 / 1M tokens
Google
Text Embedding 005google/text-embedding-005
Input$0.025 / 1M tokens
OpenAI
text-embedding-3-smallopenai/text-embedding-3-small
Input$0.02 / 1M tokens
Voyage AI
Voyage 3.5voyage/voyage-3.5
Input$0.06 / 1M tokens
Voyage 3.5 Litevoyage/voyage-3.5-lite
Input$0.02 / 1M tokens
Voyage 4voyage/voyage-4
Input$0.06 / 1M tokens
Voyage 4 Largevoyage/voyage-4-large
Input$0.12 / 1M tokens
Voyage 4 Litevoyage/voyage-4-lite
Input$0.02 / 1M tokens
1 of 1 models
ModelCapabilitiesAccess cost USD
Cohere
Cohere Rerank 3.5cohere/rerank-v3.5
Not published

If a model is locked

  • If a model has no reasoning levels, the reasoning control shows None.
  • Settings → Advanced can require zero data retention or no training. A model without a matching route stays locked, and its row shows the reason.
  • Some models require Pro or Max.
  • Fast is a separate route, offered only when the catalog lists one.

For plan prices and included usage, see Plans and usage. For privacy filters, see Privacy.

KEEP EXPLORING

Connected guides

Documentation