Long documents
Very large inputs: long reports, books, whole codebases.
Models that declare a feature for this task, with the cost of a standard job. The size of the job is our assumption.
Open in the catalog with this filter: 162 Compare the first models All free models
- Models listed
- 164
List entries: 162. A free route of a model is its own entry, next to the paid model.
Our assumed job. Requests: 3. Tokens per request: 400,000 in, 4,000 out.
Cost of this job. Our assumption for this job. Requests: 3. Input tokens per request: 400,000. Output tokens per request: 4,000. Share of input served from cache: 0%. The prices are real; the size of the job is not.
Free route. Rate limits apply and the route can differ from the paid one.
Models 164
-
Hy4 flash
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$0.04 Cost of the job $0.0614 · mixed / 1M tokens promo -
Extract
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$0.05 Cost of the job $0.03 · mixed / 1M tokens promo -
Summarize
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$0.05 Cost of the job $0.03 · mixed / 1M tokens promo -
Solar Mini 4
Context window: 524k tokens as declared. It says how much fits, not how well the model uses it.
$0.06 Cost of the job $0.0875 · mixed / 1M tokens promo -
Ling 3.1 Flash
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$0.07 Cost of the job $0.09 · mixed / 1M tokens via Novita promo -
Qwen3.5-Flash
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$0.08 Cost of the job $0.1138 · mixed / 1M tokens -
Particle-1
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$0.09 Cost of the job $0.1775 · mixed / 1M tokens -
Inkling 2 Mini
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$0.11 Cost of the job $0.1588 · mixed / 1M tokens via PrimeIntellect -
Muse Spark 1.2 Contributor
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$0.12 Cost of the job $0.125 · mixed / 1M tokens -
Muse Spark 1.3 Contributor
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$0.12 Cost of the job $0.125 · mixed / 1M tokens -
Ripple 65B Preview
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$0.12 Cost of the job $0.15 · mixed / 1M tokens via PrimeIntellect -
Gemini 2.5 Flash Lite
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$0.12 Cost of the job $0.175 · mixed / 1M tokens -
GPT-4.1 Nano
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$0.12 Cost of the job $0.175 · mixed / 1M tokens via Azure -
Nemotron 3.5 Super VL
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
The free route differs in: Max output: 131k (other version: 944k).
$0.12 Cost of the job $0.175 · mixed / 1M tokens via Crusoe -
Muse Ember
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$0.13 Cost of the job $0.20 · mixed / 1M tokens -
MiMo-V2.6-Flash
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$0.17 Cost of the job $0.175 · mixed / 1M tokens -
Qwen3.8 Flash
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$0.19 Cost of the job $0.23 · mixed / 1M tokens -
Qwen3.8 Omni Flash
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$0.19 Cost of the job $0.23 · mixed / 1M tokens -
GLM 5.3 Flash
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$0.19 Cost of the job $0.2375 · mixed / 1M tokens -
MiniMax M3.1 Flash
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$0.19 Cost of the job $0.2625 · mixed / 1M tokens Cheaper off-peak -
Solar Pro 4
Context window: 524k tokens as declared. It says how much fits, not how well the model uses it.
$0.19 Cost of the job $0.2625 · mixed / 1M tokens promo -
GPT-6 Luna
Context window: 1.1M tokens as declared. It says how much fits, not how well the model uses it.
$0.25 Cost of the job $0.20 · mixed / 1M tokens Price rises above 272k tokens -
GPT-6 Luna Pro
Context window: 1.1M tokens as declared. It says how much fits, not how well the model uses it.
$0.25 Cost of the job $0.20 · mixed / 1M tokens Price rises above 272k tokens -
Qwen3.7 Flash
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$0.25 Cost of the job $0.055 · mixed / 1M tokens Price rises above 32k tokens -
Gemini 3.1 Flash Lite
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$0.32 Cost of the job $0.5625 · mixed / 1M tokens -
Gemini 3.1 Flash Lite Preview
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$0.32 Cost of the job $0.5625 · mixed / 1M tokens -
Inkling 2 Small
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$0.37 Cost of the job $0.475 · mixed / 1M tokens via Cloudflare -
DeepSeek V4.1 Flash 1017
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$0.37 Cost of the job $0.525 · mixed / 1M tokens Cheaper off-peak -
LongCat 2.0
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$0.37 Cost of the job $0.525 · mixed / 1M tokens via AtlasCloud promo -
MiniMax M3
Context window: 524k tokens as declared. It says how much fits, not how well the model uses it.
$0.37 Cost of the job $0.525 · mixed / 1M tokens -
Gemini 2.5 Flash
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$0.39 Cost of the job $0.85 · mixed / 1M tokens -
Gemini 3.5 Flash Lite
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$0.39 Cost of the job $0.85 · mixed / 1M tokens -
Nova 2 Lite
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$0.39 Cost of the job $0.85 · mixed / 1M tokens -
Qwen3.5 Plus 2026-02-15
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$0.41 Cost of the job $0.585 · mixed / 1M tokens Price rises above 256k tokens -
Llama 4 Maverick
Context window: 524k tokens as declared. It says how much fits, not how well the model uses it.
$0.43 Cost of the job $0.5125 · mixed / 1M tokens via Parasail -
GLM 5.3 FlashX
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$0.46 Cost of the job $0.59 · mixed / 1M tokens -
GLM 5.3 FlashX Legal
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$0.46 Cost of the job $0.59 · mixed / 1M tokens -
Qwen3.5 Plus 2026-04-20
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$0.48 Cost of the job $0.675 · mixed / 1M tokens Price rises above 256k tokens -
UnslopNemo 12B
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$0.48 Cost of the job $0.40 · mixed / 1M tokens via Parasail -
Beam 1.0 501B A23B
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$0.49 Cost of the job $0.60 · mixed / 1M tokens via DigitalOcean -
GPT-4.1 Mini
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$0.50 Cost of the job $0.70 · mixed / 1M tokens -
GPT-5.6 Luna
Context window: 1.1M tokens as declared. It says how much fits, not how well the model uses it.
$0.50 Cost of the job $0.45 · mixed / 1M tokens Price rises above 272k tokens -
GPT-5.6 Luna Pro
Context window: 1.1M tokens as declared. It says how much fits, not how well the model uses it.
$0.50 Cost of the job $0.45 · mixed / 1M tokens Price rises above 272k tokens -
MiMo-V2.5
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$0.50 Cost of the job $0.80 · mixed / 1M tokens via Venice -
Hy4
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$0.52 Cost of the job $0.6254 · mixed / 1M tokens promo -
MiMo-V2.6-Pro
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$0.53 Cost of the job $0.5438 · mixed / 1M tokens -
DeepSeek V4 Flash Vision Exp
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$0.54 Cost of the job $0.66 · mixed / 1M tokens via GMICloud -
Inkling Small
Context window: 524k tokens as declared. It says how much fits, not how well the model uses it.
$0.55 Cost of the job $0.6375 · mixed / 1M tokens via DeepInfra -
Claude Haiku 5.5
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$0.63 Cost of the job $0.20 · mixed / 1M tokens Price rises above 100k tokens -
Gemini 3 Flash Preview
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$0.64 Cost of the job $1.13 · mixed / 1M tokens -
Qwen3 Coder Flash
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$0.66 Cost of the job $0.39 · mixed / 1M tokens Price rises above 32k tokens -
Palmyra X5
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$0.79 Cost of the job $1.95 · mixed / 1M tokens via Amazon Bedrock -
Mistral Large 4
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$0.87 Cost of the job $1.05 · mixed / 1M tokens -
Qwen3.6 Flash
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$0.94 Cost of the job $0.4219 · mixed / 1M tokens Price rises above 256k tokens -
Gemini 3.6 Flash
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$0.95 Cost of the job $1.50 · mixed / 1M tokens -
Gemini 3.7 Flash
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$0.95 Cost of the job $1.50 · mixed / 1M tokens promo -
Gemini 3.8 Flash
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$0.95 Cost of the job $1.50 · mixed / 1M tokens promo -
Qwen-Plus
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$0.96 Cost of the job $0.39 · mixed / 1M tokens Price rises above 256k tokens -
Pareto 26.10
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$1.00 Cost of the job $1.40 · mixed / 1M tokens -
Pareto 26.10 Preview
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$1.00 Cost of the job $1.40 · mixed / 1M tokens -
Hy4 preview
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$1.03 Cost of the job $1.25 · mixed / 1M tokens Cheaper off-peak -
DeepSeek V4 Pro 0423
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$1.10 Cost of the job $1.10 · mixed / 1M tokens via SiliconFlow -
Qwen3.7 Plus
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$1.20 Cost of the job $0.56 · mixed / 1M tokens Price rises above 256k tokens -
Step 5 Preview
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$1.23 Cost of the job $1.43 · mixed / 1M tokens -
Inkling
Context window: 524k tokens as declared. It says how much fits, not how well the model uses it.
$1.25 Cost of the job $1.76 · mixed / 1M tokens via Together -
ERNIE-Light-DT-1.0
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$1.40 Cost of the job $1.83 · mixed / 1M tokens -
Muse Spark 1.1
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$1.55 Cost of the job $2.00 · mixed / 1M tokens -
Muse Spark 1.2
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$1.55 Cost of the job $2.00 · mixed / 1M tokens -
Muse Spark 1.3
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$1.55 Cost of the job $2.00 · mixed / 1M tokens -
Muse Spark Open
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$1.55 Cost of the job $2.00 · mixed / 1M tokens via Fireworks -
Qwen3.6 Plus
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$1.61 Cost of the job $0.7313 · mixed / 1M tokens Price rises above 256k tokens -
GLM 5.3
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$1.73 Cost of the job $2.15 · mixed / 1M tokens -
Qwen4 Max
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$1.76 Cost of the job $2.14 · mixed / 1M tokens promo -
Qwen3.7 Max
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$1.82 Cost of the job $2.21 · mixed / 1M tokens -
Gemini 4 Hydrogen
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$1.89 Cost of the job $3.00 · mixed / 1M tokens -
Gemini 3.5 Flash
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$1.91 Cost of the job $3.38 · mixed / 1M tokens -
GLM 5.3 Prime
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$2.08 Cost of the job $2.58 · mixed / 1M tokens via Alibaba -
Fugu Max
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$2.47 Cost of the job $3.00 · mixed / 1M tokens -
Qwen3.8 2.4T A95B
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$2.47 Cost of the job $3.00 · mixed / 1M tokens -
Qwen3.8 Max (0902)
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$2.47 Cost of the job $3.00 · mixed / 1M tokens -
GPT-6.1 Terra
Context window: 1.1M tokens as declared. It says how much fits, not how well the model uses it.
$2.49 Cost of the job $2.00 · mixed / 1M tokens Price rises above 272k tokens -
GPT-6.1 Terra Pro
Context window: 1.1M tokens as declared. It says how much fits, not how well the model uses it.
$2.49 Cost of the job $2.00 · mixed / 1M tokens Price rises above 272k tokens -
GPT-4.1
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$2.50 Cost of the job $3.50 · mixed / 1M tokens -
Claude Sonnet 5
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$2.52 Cost of the job $4.00 · mixed / 1M tokens -
Claude Sonnet 5.5
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$2.52 Cost of the job $4.00 · mixed / 1M tokens -
Gemini 4 Argon
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$2.52 Cost of the job $4.00 · mixed / 1M tokens promo -
Gemini 4 Carbon
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$2.52 Cost of the job $4.00 · mixed / 1M tokens promo -
Kimi K3.1 Pro
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$2.52 Cost of the job $4.00 · mixed / 1M tokens -
Grok 4.20
Context window: 2M tokens as declared. It says how much fits, not how well the model uses it.
$3.06 Cost of the job $1.56 · mixed / 1M tokens Price rises above 200k tokens -
Grok 4.20 Multi-Agent
Context window: 2M tokens as declared. It says how much fits, not how well the model uses it.
$3.06 Cost of the job $1.56 · mixed / 1M tokens Price rises above 200k tokens -
Grok 4.3
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$3.06 Cost of the job $1.56 · mixed / 1M tokens Price rises above 200k tokens -
Gemini 2.5 Pro
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$3.18 Cost of the job $3.44 · mixed / 1M tokens Price rises above 200k tokens -
Gemini 2.5 Pro Preview 06-05
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$3.18 Cost of the job $3.44 · mixed / 1M tokens Price rises above 200k tokens -
Claude Sonnet 4.6
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$3.78 Cost of the job $6.00 · mixed / 1M tokens -
Ember-1
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$3.78 Cost of the job $6.00 · mixed / 1M tokens -
Gemini 4 Neon
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$3.78 Cost of the job $6.00 · mixed / 1M tokens -
Kimi K3
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$3.78 Cost of the job $6.00 · mixed / 1M tokens -
Grok 4.5
Context window: 500k tokens as declared. It says how much fits, not how well the model uses it.
$4.94 Cost of the job $3.00 · mixed / 1M tokens Price rises above 200k tokens -
Grok 4.6
Context window: 500k tokens as declared. It says how much fits, not how well the model uses it.
$4.94 Cost of the job $3.00 · mixed / 1M tokens Price rises above 200k tokens -
Grok 4.7
Context window: 500k tokens as declared. It says how much fits, not how well the model uses it.
$4.94 Cost of the job $3.00 · mixed / 1M tokens Price rises above 200k tokens -
Qwen3.8 Max Prime
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$4.94 Cost of the job $6.00 · mixed / 1M tokens -
GPT-6 Sol
Context window: 1.1M tokens as declared. It says how much fits, not how well the model uses it.
$4.98 Cost of the job $4.00 · mixed / 1M tokens Price rises above 272k tokens -
GPT-6 Sol Pro
Context window: 1.1M tokens as declared. It says how much fits, not how well the model uses it.
$4.98 Cost of the job $4.00 · mixed / 1M tokens Price rises above 272k tokens -
GPT-6.1 Sol
Context window: 1.1M tokens as declared. It says how much fits, not how well the model uses it.
$4.98 Cost of the job $4.00 · mixed / 1M tokens Price rises above 272k tokens -
GPT-6.1 Sol Pro
Context window: 1.1M tokens as declared. It says how much fits, not how well the model uses it.
$4.98 Cost of the job $4.00 · mixed / 1M tokens Price rises above 272k tokens -
GPT-6.2 Sol
Context window: 1.1M tokens as declared. It says how much fits, not how well the model uses it.
$4.98 Cost of the job $4.00 · mixed / 1M tokens Price rises above 272k tokens -
GPT-6.2 Sol Pro
Context window: 1.1M tokens as declared. It says how much fits, not how well the model uses it.
$4.98 Cost of the job $4.00 · mixed / 1M tokens Price rises above 272k tokens -
Gemini 3.1 Pro Preview
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$5.02 Cost of the job $4.50 · mixed / 1M tokens Price rises above 200k tokens -
Gemini 3.1 Pro Preview Custom Tools
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$5.02 Cost of the job $4.50 · mixed / 1M tokens Price rises above 200k tokens -
GPT-5.6 Terra
Context window: 1.1M tokens as declared. It says how much fits, not how well the model uses it.
$5.02 Cost of the job $4.50 · mixed / 1M tokens Price rises above 272k tokens -
GPT-5.6 Terra Pro
Context window: 1.1M tokens as declared. It says how much fits, not how well the model uses it.
$5.02 Cost of the job $4.50 · mixed / 1M tokens Price rises above 272k tokens -
Claude Opus 5.5
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$5.04 Cost of the job $8.00 · mixed / 1M tokens -
Muse Wonder
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$5.04 Cost of the job $8.00 · mixed / 1M tokens -
MiMo-V2.6-Pro-UltraSpeed
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$5.32 Cost of the job $5.44 · mixed / 1M tokens -
GPT-5.4
Context window: 1.1M tokens as declared. It says how much fits, not how well the model uses it.
$6.27 Cost of the job $5.63 · mixed / 1M tokens Price rises above 272k tokens -
Claude Opus 4.6
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$6.30 Cost of the job $10.00 · mixed / 1M tokens -
Claude Opus 4.7
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$6.30 Cost of the job $10.00 · mixed / 1M tokens -
Claude Opus 4.8
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$6.30 Cost of the job $10.00 · mixed / 1M tokens -
Claude Opus 5
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$6.30 Cost of the job $10.00 · mixed / 1M tokens -
Claude Sonnet 4.5
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$7.47 Cost of the job $6.00 · mixed / 1M tokens Price rises above 200k tokens -
GPT-5.6 Sol
Context window: 1.1M tokens as declared. It says how much fits, not how well the model uses it.
$9.96 Cost of the job $8.00 · mixed / 1M tokens Price rises above 272k tokens -
GPT-5.6 Sol Pro
Context window: 1.1M tokens as declared. It says how much fits, not how well the model uses it.
$9.96 Cost of the job $8.00 · mixed / 1M tokens Price rises above 272k tokens -
Claude Fable 5.2
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$10.08 Cost of the job $16.00 · mixed / 1M tokens -
Fugu Ultra
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$12.54 Cost of the job $11.25 · mixed / 1M tokens Price rises above 272k tokens -
Fugu Ultra v2
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$12.54 Cost of the job $11.25 · mixed / 1M tokens Price rises above 272k tokens -
GPT-5.5
Context window: 1.1M tokens as declared. It says how much fits, not how well the model uses it.
$12.54 Cost of the job $11.25 · mixed / 1M tokens Price rises above 272k tokens -
Claude Fable 5
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$12.60 Cost of the job $20.00 · mixed / 1M tokens -
Claude Fable 5.1
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$12.60 Cost of the job $20.00 · mixed / 1M tokens -
GPT-6.2 Astra
Context window: 1.1M tokens as declared. It says how much fits, not how well the model uses it.
$19.92 Cost of the job $16.00 · mixed / 1M tokens Price rises above 272k tokens -
GPT-6.2 Astra Pro
Context window: 1.1M tokens as declared. It says how much fits, not how well the model uses it.
$19.92 Cost of the job $16.00 · mixed / 1M tokens Price rises above 272k tokens -
GPT-6 Astra
Context window: 1.1M tokens as declared. It says how much fits, not how well the model uses it.
$24.90 Cost of the job $20.00 · mixed / 1M tokens Price rises above 272k tokens -
GPT-6 Astra Pro
Context window: 1.1M tokens as declared. It says how much fits, not how well the model uses it.
$24.90 Cost of the job $20.00 · mixed / 1M tokens Price rises above 272k tokens -
GPT-5.4 Pro
Context window: 1.1M tokens as declared. It says how much fits, not how well the model uses it.
$75.24 Cost of the job $67.50 · mixed / 1M tokens Price rises above 272k tokens -
GPT-5.5 Pro
Context window: 1.1M tokens as declared. It says how much fits, not how well the model uses it.
$75.24 Cost of the job $67.50 · mixed / 1M tokens Price rises above 272k tokens -
DeepSeek V4 Flash 0423
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$0.1125 mixed / 1M tokens in $0.09 · out $0.18 via DeepInfra Price disputed -
DeepSeek V4 Flash 0731
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$0.09 mixed / 1M tokens in $0.06 · out $0.18 via DeepInfra Price disputed -
DeepSeek V4 Pro 0813
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$1.98 mixed / 1M tokens in $1.32 · out $3.96 Cheaper off-peak Price disputed -
DeepSeek V4.1 Flash
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$0.21 mixed / 1M tokens in $0.12 · out $0.48 via River Price disputed -
Dots3-Note Preview
Context window: 512k tokens as declared. It says how much fits, not how well the model uses it.
Ends December 31, 2026
Free -
ERNIE-5.5-Flash-Preview
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
Free -
GLM 5.2
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
$2.15 mixed / 1M tokens in $1.40 · out $4.40 Price disputed -
GPT Chat Latest
Context window: 400k tokens as declared. It says how much fits, not how well the model uses it.
$11.25 mixed / 1M tokens in $5.00 · out $30.00 -
GPT-5
Context window: 400k tokens as declared. It says how much fits, not how well the model uses it.
Ends December 11, 2026
$3.44 mixed / 1M tokens in $1.25 · out $10.00 -
GPT-5 Image
Context window: 400k tokens as declared. It says how much fits, not how well the model uses it.
Text tokens only: image or audio output is priced separately.
Ends December 11, 2026
$10.00 mixed / 1M tokens in $10.00 · out $10.00 -
GPT-5 Image Mini
Context window: 400k tokens as declared. It says how much fits, not how well the model uses it.
Text tokens only: image or audio output is priced separately.
Ends December 1, 2026
$2.38 mixed / 1M tokens in $2.50 · out $2.00 -
GPT-5 Mini
Context window: 400k tokens as declared. It says how much fits, not how well the model uses it.
Ends December 11, 2026
$0.6875 mixed / 1M tokens in $0.25 · out $2.00 -
GPT-5 Nano
Context window: 400k tokens as declared. It says how much fits, not how well the model uses it.
Ends December 11, 2026
$0.1375 mixed / 1M tokens in $0.05 · out $0.40 -
GPT-5 Pro
Context window: 400k tokens as declared. It says how much fits, not how well the model uses it.
Ends December 11, 2026
$41.25 mixed / 1M tokens in $15.00 · out $120.00 -
GPT-5.1
Context window: 400k tokens as declared. It says how much fits, not how well the model uses it.
$3.44 mixed / 1M tokens in $1.25 · out $10.00 -
GPT-5.1-Codex
Context window: 400k tokens as declared. It says how much fits, not how well the model uses it.
$3.44 mixed / 1M tokens in $1.25 · out $10.00 via Azure -
GPT-5.1-Codex-Max
Context window: 400k tokens as declared. It says how much fits, not how well the model uses it.
$3.44 mixed / 1M tokens in $1.25 · out $10.00 via Azure -
GPT-5.1-Codex-Mini
Context window: 400k tokens as declared. It says how much fits, not how well the model uses it.
$0.6875 mixed / 1M tokens in $0.25 · out $2.00 via Azure -
GPT-5.2
Context window: 400k tokens as declared. It says how much fits, not how well the model uses it.
$4.81 mixed / 1M tokens in $1.75 · out $14.00 -
GPT-5.2 Pro
Context window: 400k tokens as declared. It says how much fits, not how well the model uses it.
$57.75 mixed / 1M tokens in $21.00 · out $168.00 -
GPT-5.2-Codex
Context window: 400k tokens as declared. It says how much fits, not how well the model uses it.
$4.81 mixed / 1M tokens in $1.75 · out $14.00 via Azure -
GPT-5.3-Codex
Context window: 400k tokens as declared. It says how much fits, not how well the model uses it.
$4.81 mixed / 1M tokens in $1.75 · out $14.00 -
GPT-5.4 Mini
Context window: 400k tokens as declared. It says how much fits, not how well the model uses it.
$1.69 mixed / 1M tokens in $0.75 · out $4.50 -
GPT-5.4 Nano
Context window: 400k tokens as declared. It says how much fits, not how well the model uses it.
$0.4625 mixed / 1M tokens in $0.20 · out $1.25 -
Ling 3.2 Flash
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
Free -
Lyria 3 Clip Preview
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
No data Priced per item, not per token -
Lyria 3 Pro Preview
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
No data Priced per item, not per token -
Nemotron 3 Ultra
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it. Applies to the free route.
The free route differs in: Context window: 1M (other version: 262k); Max output: 66k (other version: 16k); Structured output: Not listed (other version: Yes).
$0.925 mixed / 1M tokens in $0.50 · out $2.20 via KT -
Nemotron 3.5 Lightning
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it. Applies to the free route.
The free route differs in: Context window: 1M (other version: 262k); Max output: 66k (other version: 236k); Structured output: Not listed (other version: Yes).
$0.085 mixed / 1M tokens in $0.06 · out $0.16 via DeepInfra -
Nova Premier 1.0
Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.
No data