86 models in the catalog
Explore AI models
Compare prices, capabilities and context windows across the QuickSilver Pro catalog.
Featured models
Not sure where to start? Pick the job.
Curated starting points from catalog data, not a ranking. Every model below is one string away.
AnthropicClaude Opus 5.5Coding, knowledge work and computer use$1.00 / $5.00 · 1M−75%OpenAIGPT-6.2 SolText, images, tools and structured output$2.00 / $10.00 · 1M—Z.aiGLM 5.3Complex software engineering, long-horizon agents$0.60 / $2.20 · 1MAt listMoonshot AIKimi K3.1 ProLong-context coding and image-based workflows.$2.00 / $10.00 · 1MAt list
Model catalog and prices
All models86 models found. Sorted by Featured
Compare
Model / author
Official
Our price
Discount
Context
Latency
Status
gemini-4-neonat list
Input $3.00 Output $15.00per 1M tokenscache $0.15
at list
1M
—
Checking…
gpt-6.2-astraOpenAI list rates for prompts up to 200K tokens; longer prompts use QuickSilver's long-context rate
Input $8.00 Output $40.00per 1M tokenscache $0.40Above 200,000 prompt tokens: input $16.00, output $60.00, cache read $0.80 per 1M tokens.
OpenAI list rates for prompts up to 200K tokens; longer prompts use QuickSilver's long-context rate
1M
—
Checking…
GPT-6.2 SolNew
gpt-6.2-solOpenAI list rates for prompts up to 200K tokens; longer prompts use QuickSilver's long-context rate
Input $2.00 Output $10.00per 1M tokenscache $0.10Above 200,000 prompt tokens: input $4.00, output $15.00, cache read $0.20 per 1M tokens.
OpenAI list rates for prompts up to 200K tokens; longer prompts use QuickSilver's long-context rate
1M
—
Checking…
gemini-4-hydrogenat list
Input $1.50 Output $7.50per 1M tokenscache $0.075
at list
1M
—
Checking…
claude-fable-5-2Input $2.00 Output $10.00per 1M tokenscache $0.05
−75%
1M
—
Checking…
gemini-4-carbonat list
Input $2.00 Output $10.00per 1M tokenscache $0.10
at list
1M
—
Checking…
gpt-6.1-terraat list
Input $1.00 Output $5.00per 1M tokenscache $0.10Above 200,000 prompt tokens: input $2.00, output $7.50, cache read $0.20 per 1M tokens.
at list
1M
—
Checking…
gpt-6.1-terra-proat list
Input $1.00 Output $5.00per 1M tokenscache $0.10Above 200,000 prompt tokens: input $2.00, output $7.50, cache read $0.20 per 1M tokens.
at list
1M
—
Checking…
kimi-k3.1-proat list
Input $2.00 Output $10.00per 1M tokenscache $0.20
at list
1M
—
Checking…
kimi-k3.1-pro-highspeedat list
Input $4.00 Output $20.00per 1M tokenscache $0.20
at list
1M
—
Checking…
deepseek-v4.1-flash-1017at list
Input $0.098 Output $0.294per 1M tokenscache $0.00294
at list
1M
—
Checking…
muse-spark-openat list
Input $1.25 Output $4.25per 1M tokenscache $0.15
at list
1M
—
Checking…
gemini-4-argonat list
Input $2.00 Output $10.00per 1M tokenscache $0.10
at list
1M
—
Checking…
step-5-previewat list
Input $1.00 Output $2.70per 1M tokenscache $0.10
at list
1M
—
Checking…
claude-haiku-5-5Input $0.025 Output $0.125per 1M tokenscache $0.0025Above 200,000 prompt tokens: input $0.125, output $0.625, cache read $0.0125 per 1M tokens.
−75%
1M
—
Checking…
gpt-6.1-solat list
Input $2.00 Output $10.00per 1M tokenscache $0.10Above 200,000 prompt tokens: input $4.00, output $15.00, cache read $0.20 per 1M tokens.
at list
1M
—
Checking…
claude-sonnet-5-5Input $0.50 Output $2.50per 1M tokenscache $0.05
−75%
1M
—
Checking…
qwen3.8-max-primeat list
Input $4.00 Output $12.00per 1M tokenscache $0.50
at list
1M
—
Checking…
gpt-6-lunaat list
Input $0.10 Output $0.50per 1M tokenscache $0.01Above 200,000 prompt tokens: input $0.20, output $0.75, cache read $0.02 per 1M tokens.
at list
1M
—
Checking…
gpt-6-solat list
Input $2.00 Output $10.00per 1M tokenscache $0.20Above 200,000 prompt tokens: input $4.00, output $15.00, cache read $0.40 per 1M tokens.
at list
1M
—
Checking…
claude-opus-5-5Input $1.00 Output $5.00per 1M tokenscache $0.05
−75%
1M
—
Checking…
grok-4.7—
Input $2.00 Output $6.00per 1M tokenscache $0.50Above 200,000 prompt tokens: input $4.00, output $12.00, cache read $1.00 per 1M tokens.
—
500K
—
Checking…
mimo-v2.6-flashInput $0.112 Output $0.224per 1M tokenscache $0.00224
−20%
1M
—
Checking…
qwen3.8-omni-flashat list
Input $0.15 Output $0.47per 1M tokenscache $0.016
at list
1M
—
Checking…
deepseek-v4.1-flashInput $0.154 Output $0.462per 1M tokenscache $0.0046
−49–62%
1M
—
Checking…
gpt-6-astraat list
Input $10.00 Output $50.00per 1M tokenscache $1.00Above 200,000 prompt tokens: input $20.00, output $75.00, cache read $2.00 per 1M tokens.
at list
1M
—
Checking…
muse-spark-1.3Input $1.00 Output $3.40per 1M tokenscache $0.12
−20%
1M
—
Checking…
gemini-3.8-flashInput $0.6375 Output $3.1875per 1M tokenscache $0.06375
−15%
1M
—
Checking…
claude-fable-5-1Input $2.50 Output $12.50per 1M tokenscache $0.0625
−75%
1M
—
Checking…
qwen3.8-flash-nextInput $0.12 Output $0.376per 1M tokenscache $0.0128
−20%
1M
—
Checking…
glm-5.3-flashat list
Input $0.0284 Output $0.0923per 1M tokenscache $0.0284
at list
1M
—
Checking…
nemotron-3.5-lightning—
Input $0.066 Output $0.176per 1M tokenscache $0.033
—
262K
—
Checking…
muse-glimmer-30bat list
Input $0.30 Output $1.20per 1M tokenscache $0.04
at list
131K
—
Checking…
claude-sonnet-5Input $0.50 Output $2.50per 1M tokenscache $0.05
−75%
1M
—
Checking…
deepseek-v4-flashat list
Input $0.06 Output $0.18per 1M tokenscache $0.015
at list
1M
—
Checking…
claude-haiku-4-5Input $0.25 Output $1.25per 1M tokenscache $0.025
−75%
200K
—
Checking…
gpt-oss-120bat list
Input $0.03 Output $0.15per 1M tokenscache $0.03
at list
131K
—
Checking…
deepseek-v4-proInput $0.70 Output $2.10per 1M tokenscache $0.10
−47%
1M
—
Checking…
qwen3.7-flashInput $0.024 Output $0.104per 1M tokenscache $0.0048
−20%
1M
—
Checking…
qwen3.6-35bat list
Input $0.05 Output $0.70per 1M tokenscache $0.025
at list
262K
—
Checking…
claude-opus-5Input $1.25 Output $6.25per 1M tokenscache $0.125
−75%
1M
—
Checking…
claude-fable-5Input $2.50 Output $12.50per 1M tokenscache $0.25
−75%
1M
—
Checking…
claude-opus-4-8Input $1.25 Output $6.25per 1M tokenscache $0.125
−75%
1M
—
Checking…
USD per 1M tokens, except image models billed per image. Official prices appear only where a published reference exists. Models marked for long-context rates charge different rates above their prompt-token threshold.
Latency comes from standardized status probes with a 16-token output limit.